BrowseAll ecosystems
Everything in the atlas
210 of 2341
Domain: 2
Signals
Content
More: SAP Community
Group by: Ecosystem
EntryBySignalsLast activity
No ecosystem
[Part – 2] Enrich CAP based Services with Behaviors using Annotations[Part – 2] Enrich CAP based Services with Behaviors using AnnotationsThe second half of a two-part walkthrough of CAP's behavioral annotations, following on from access control and input validation in the first part. This post works through @cds.autoexpose, @cds.api.ignore, @cds.persistence.exists/skip, @cds.on.insert/@cds.on.update and the @odata.Type/@odata.singleton mapping overrides, all shaping how a CDS model is projected into a service, which is data modelling. Alongside these it covers @cds.query.limit for default and maximum page sizes (pagination and streaming), @odata.etag with exclusive and shared locks for optimistic concurrency (concurrency control), and @cds.search for scoping $search to chosen elements (search), each with a CDS code example.published 2023-01-29
#BTP #SAPCAP: Quirky Nuggets (N03-N04)#BTP #SAPCAP: Quirky Nuggets (N03-N04)Two unrelated findings in one post, which is the format of the series: the OData operators tried against a CAP service — with a schema of deliberately awkward types to try them on — and undeploying database artifacts, which is the half people hit in anger. Numbered N03 and N04 of a run that continues either side.Ajit_K_Panda, published 2023-06-05
#BTP #SAPCAP: Quirky Nuggets (N03-N04)
Deployment changed in @sap/cds-dk 8.9.0, 2025-03-31. Affects A recipe, Runnable code.
⚡Unlocking the Power of LLMs in CAP: Understanding llms.txt and llms-full.txt⚡Unlocking the Power of LLMs in CAP: Understanding llms.txt and llms-full.txtllms.txt and llms-full.txt for CAP — a plain-text map of the documentation, written for an agent that arrived by fetching a URL rather than one somebody configured. The convention the atlas uses for itself, applied to capire.Yogananda, published 2025-05-18
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 1/3A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 1/3The concepts before the code: what the GPT model and its API actually offer, and what the finished chat application looks like — personalities included. Written in the weeks when the ground was moving under it, and the post carries its own change log to prove it: GPT-3.5 added on 1 March, GPT-4 on 15 March, and an admission that a series planned as two posts became three.published 2023-02-22
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 1/3
cap-ui5-gpt-chat: no published releases, repository quiet for 41 months. Affects Runnable code.
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 2/3A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 2/3The backend: CAP with TypeScript, the entities holding chats and personalities, and the service that talks to the API. This is where the streamed completion and the repositories behind the handler come from, which is the part of the sample still worth lifting even though the model access has since been superseded by AI Core.published 2023-02-24
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 2/3
cap-ui5-gpt-chat: no published releases, repository quiet for 41 months. Affects Runnable code.
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 3/3A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 3/3The SAPUI5 frontend of the sample, and mostly an argument for writing UI5 in TypeScript: ES imports in place of sap.ui.define, a class with real private members in place of the underscore convention, and the service types generated from the CDS model copied into the UI package, so one IChats interface types the OData object the controller reads. The second half is structure — a formatter class and a singleton LayoutManager called from the XML view through core:require, a confirmation helper taking a callback, a dialog class resolving a promise, a generic createEntity<T> on a service class — all of it to keep every controller under 100 lines. What it says about arranging a UI5 app holds whatever model sits behind the chat; the tooling around it is of its date, and the post calls UI5's TypeScript support experimental.published 2023-02-27
A ChatGPT-like chat app built with modern SAP technologies (CAP, SAPUI5) – Part 3/3
cds2types. Affects Runnable code.
A Guide to CDS Metadata Extensions, Fiori App Generation and SAP UI5 Controller ExtensionsA Guide to CDS Metadata Extensions, Fiori App Generation and SAP UI5 Controller ExtensionsWalks through a RAP-based Fiori elements app end to end: layering UI annotations onto a CDS view through a separate ABAP metadata extension object, gated by @Metadata.allowExtensions on the base view and ordered across extensions by a required @Metadata.layer value. Generates the app in SAP Business Application Studio from the published OData V4 service's merged $metadata document, then adds an SAP UI5 controller extension — registered in manifest.json against a Fiori elements lifecycle hook — only for behaviour the annotations cannot express.ankitapaul229, published 2026-07-27
A Practical Real-Time CTI Widget for SAP Sales Cloud V2A Practical Real-Time CTI Widget for SAP Sales Cloud V2A small CAP backend, a WebSocket channel and a UI5 widget in an iframe — enough to get telephony events into Sales Cloud without any custom backend inside the CRM. The smallness is the design.gizemsoylutr, published 2025-11-28
A Use Case for HANA Cloud Knowledge Graph: AI‑Driven Tender AnalysisA Use Case for HANA Cloud Knowledge Graph: AI‑Driven Tender AnalysisMatching unstructured text against internal data, using both HANA engines at once — the Knowledge Graph for the relationships and the Vector Engine for similarity — with CAP holding the application and its data. Notes that the Knowledge Graph Engine is off by default and has to be enabled when the instance is created, which is the kind of thing that stops a weekend.giacomo_dantonio, published 2026-03-19
ABAP + MCP: Let AI Do Real Development in Your SAP SystemABAP + MCP: Let AI Do Real Development in Your SAP Systemabap-adt-mcp is an open-source MCP server that gives an AI agent full ABAP development capability over ADT: it searches, reads, edits, activates and unit-tests objects, and runs ATC checks, on a connected S/4HANA Cloud or on-premise system, acting as the signed-in developer. It runs on abap-adt-api, the same REST client Eclipse's own ADT tooling uses, and sits beside SAP's own ADT MCP Server, shipped with ADT for VS Code and Eclipse under a different server key, and marianfoo's abap-docs, a read-only server over the ABAP Keyword Documentation and Clean ABAP. Each destination carries a policy — read-only, allowed packages, denied tables and tools — the server checks before every call, and an optional audit file logs each tool call with its outcome and policy gate.Willian_Saez, published 2026-09-03
ABAP development tools for Visual Studio Code is now available on the VS Code marketplace!ABAP development tools for Visual Studio Code is now available on the VS Code marketplace!Announces the marketplace release of ABAP development tools for Visual Studio Code, an extension that works against any ABAP system already reachable from ADT for Eclipse and is focused on RAP UI service development, so the Fiori/SAPUI5 frontend and the ABAP backend can be built in the same tool. It ships a built-in ADT MCP Server, disabled by default and switched on from the extension settings, and points readers to a documentation template for capturing ABAP-specific rules in a project's AGENTS.md file for chat agents such as Microsoft Copilot.thomasalexander_ritter, published 2026-06-01
ABAP development tools for Visual Studio Code: Patch 1.0.1 releasedABAP development tools for Visual Studio Code: Patch 1.0.1 releasedA patch to SAP's ABAP development tools for Visual Studio Code, released after two weeks of user feedback: RFC destinations with password logon return, undoing what the first release had dropped, and the extension now ships the AGENTS.md template its documentation already carried, so a project gets agent guidance built in rather than copied by hand. The author still recommends duplicating the template and adding project-specific instructions, since the time spent on that onboarding is what the agent's results depend on.thomasalexander_ritter, published 2026-06-12
ABAP development tools for Visual Studio Code: Version 1.1 releasedABAP development tools for Visual Studio Code: Version 1.1 releasedVersion 1.1 of ABAP development tools for Visual Studio Code adds two tools to the extension's local ADT MCP Server: a unified, git-like diff for a transport request, and a runner for ABAP Test Cockpit checks, both meant for an agent to call rather than a person to click through. Both are new instances of what agent access to your code already covers for ABAP — reading and acting on a real system through ADT — reaching now into a transport's changes and a check run rather than only source and objects.thomasalexander_ritter, published 2026-07-21
Adapting SAP Joule for Purchase Order Creation from an Existing Purchase RequisitionAdapting SAP Joule for Purchase Order Creation from an Existing Purchase RequisitionA custom Joule Agent and Joule Skill, built in Joule Studio, classic edition to extend SAP Joule past its built-in Purchase Order display and change features: a buyer's single sentence naming a Purchase Requisition number becomes a created Purchase Order, with the skill wrapping the Purchase Requisition and Purchase Order OData V4 APIs as Action Packages reached through two destinations. The author anchors the agent's success condition to a PurchaseOrderNumber in the skill's output rather than an HTTP status code, and reports that the Purchase Requisition item structure does not map one-to-one onto the Purchase Order creation payload.jonathanvi59, published 2026-08-19
Adding a Swagger UI to Your SAP Cloud Application Programming Model / Node.js ServiceAdding a Swagger UI to Your SAP Cloud Application Programming Model / Node.js ServiceThe problem stated from the other side of the wire: a CAP and HANA backend consumed by frontend developers with no SAP background, who said in the first meeting that they could not work from what the service offered. A browsable API page is the answer, and this is the post the Swagger UI plugin indexed here exists to serve.published 2020-01-23
Adding a Swagger UI to Your SAP Cloud Application Programming Model / Node.js Service
cds-swagger-ui-express has been through 11 major lines since this was published, most recently 0.9 (2024-07), 0.10 (2024-10), 0.11 (2026-02). Affects Runnable code.
Adding Immutable Blockchain Proofs to SAP With CAP - Cardano and OData V4Adding Immutable Blockchain Proofs to SAP With CAP - Cardano and OData V4The write-up behind ODATANO, by its author: how a public blockchain gets reachable from CAP as an ordinary OData V4 service rather than through a bespoke client. The premise it starts from is worth the read on its own — SAP systems are trusted but mutable, which is what an immutable anchor is for — and Cardano is chosen for peer-reviewed research and formal methods rather than for popularity. Written as an experiment with feedback invited, not as a recommendation.maxalexweber, published 2026-05-15
Agentic AI on BTP: a Multi‑Agent App with Pydantic AIAgentic AI on BTP: a Multi‑Agent App with Pydantic AISplits a single CAP/TypeScript agent that had grown to juggle five BTP MCP servers behind one bloated tool list into btp-multiagent-app, a Python and Pydantic AI rewrite where the Cloud Foundry and BTP Core MCP servers each get a dedicated specialist agent, with an audit log specialist scaffolded but left disabled, behind an orchestrator whose only tools are delegation calls to those specialists, which is the agent-tooling pattern the piece works through. Each specialist authenticates to its MCP server over Streamable HTTP with OAuth 2.1, and a shared module centralises the SAP AI Core GenAI Hub model setup behind two credential layouts, one for local runs and one for the Cloud Foundry service binding, the LLM integration side of the rewrite. Tool lists per agent drop from well over a hundred to a dozen or two, and routing failures become separable from tool-misuse failures by reading the trace.published 2026-05-03
Agentic AI on BTP: a Single Agent with LangGraphAgentic AI on BTP: a Single Agent with LangGraphA CAP TypeScript agent puts a LangGraph StateGraph in front of AzureOpenAiChatClient from @sap-ai-sdk/langchain, reaching SAP AI Core's Generative AI Hub, and lets its tool-calling loop draw on five deployed MCP servers — OData MCP Proxy, CI MCP Server, AI Core MCP Server, BTP MCP Server and BTP CF MCP Server — through @langchain/mcp-adapters' MultiServerMCPClient. Because agent, servers and APIs share one XSUAA tenant, the chat service forwards the signed-in user's own JWT instead of a service account, so each downstream server enforces that user's own authorizations. Past roughly a hundred combined tools the single prompt slows down and stops separating concerns, which is why the author's next post splits it into one specialist agent per MCP server behind an orchestrator.published 2026-05-03
An Innovative Language Exchange App developed with SAP Build Apps, CAP, Kyma, and OpenAIAn Innovative Language Exchange App developed with SAP Build Apps, CAP, Kyma, and OpenAIA dormant internal app at SAP Japan revived with AI, built to solve a problem the team actually had — colleagues who could not talk to each other. Build Apps on the front, CAP on Kyma behind it, OpenAI in the middle.javieryw, published 2024-01-31
An Innovative Language Exchange App developed with SAP Build Apps, CAP, Kyma, and OpenAI
LLM integration changed in @cap-js/ai 1.0.0, 2026-04-28. Affects Runnable code.
API Composition: Seamless Enterprise Data Access for Developers and AI AgentsAPI Composition: Seamless Enterprise Data Access for Developers and AI AgentsAPI Composition (formerly Graph, a capability of API Management) curates business data graphs from existing SAP and non-SAP API providers, so a query can navigate and expand relationships across systems through one composed API rather than hand-written integration code. Palak walks through combining SAP S/4HANA warehouse-stock data with Everstream Analytics risk data into one API, then exposing that composed API as an MCP server so an AI agent calls it with the same semantic context — the scenario behind API Management's MCP servers coverage.published 2026-07-27
Automate your Job Postings Using Generative AI (ChatGPT) & SAP Build Process Automation AppsAutomate your Job Postings Using Generative AI (ChatGPT) & SAP Build Process Automation AppsA process that drafts its own text: ChatGPT writing job postings, SAP Build Process Automation carrying them through approval, and CAP in between. Presented as a generic pattern the author expects to be adapted rather than copied.shivamshukla12, published 2023-08-10
Autonomous Diagnostics on Kyma Unplugged: Goose + LiteLLM + KRO + SAP AI Core in ProductionAutonomous Diagnostics on Kyma Unplugged: Goose + LiteLLM + KRO + SAP AI Core in ProductionAn in-cluster autonomous diagnostic pipeline on Kyma Unplugged (open-source Kyma, noted to also run on SAP BTP, Kyma runtime): a Goose agent with kubectl access calls SAP AI Core through a LiteLLM proxy, and most of the post is about the quirks of that route — drop_params silently swallowing unrecognised parameters and beta headers, streaming that has to be off when tools are attached, and prompt caching that sits on the Orchestration V2 API rather than the foundation-model path the LiteLLM provider hits. A second Node.js proxy reaches that API, and the author reports caching unconfirmed at production scale, which leaves the roughly $0.004 per static run a target rather than a measured figure. Spend metrics reach SAP Cloud Logging over OTLP through Kyma's Telemetry MetricPipeline while the health analysis itself lands in Kubernetes custom resources read in Busola, and the stack is declared as KRO Resource Group Definitions applied with one Terraform command.quovadis, published 2026-07-09
Banking Sentinel: A Multi-Agent Credit-Risk Copilot on SAP BTP, Built on a Mixed AI StackBanking Sentinel: A Multi-Agent Credit-Risk Copilot on SAP BTP, Built on a Mixed AI StackThe risk it is chasing is a graph problem stated in banking terms: a borrower who looks safe alone and is the linchpin of a group ten times the size. Multi-agent, mixed AI stack, on BTP and CAP.Shahid, published 2026-06-24
Banking Sentinel: A Multi-Agent Credit-Risk Copilot on SAP BTP, Built on a Mixed AI Stack
Agent tooling changed in @cap-js/agents 0.9.1, 2026-08-14. Affects A recipe, Runnable code.
Basic code's of ABAPBasic code's of ABAPNine standalone ABAP reports built around REUSE_ALV_GRID_DISPLAY and CL_SALV_TABLE, covering display, screen validation, spool creation, Excel upload and table maintenance without SM30. One report raises and catches a custom exception class with RAISE EXCEPTION and TRY/CATCH, the class-based mechanism error handling names for ABAP; another submits a job to spool, converts it to PDF with CONVERT_ABAPSPOOLJOB_2_PDF and exports a CL_SALV_TABLE result to Excel before mailing both, producing document output from spool rather than Form Builder.RakeshZore, published 2025-09-30
Beginners Guide to Advanced Event MeshBeginners Guide to Advanced Event MeshA scenario-by-scenario walkthrough of Advanced Event Mesh, run through Cloud Integration iFlows: publishing and consuming queue messages, dead message queue setup with retry counts and acknowledgment modes, direct messages, durable topic endpoints and selectors, time-to-live, REST Delivery Points, replay by replication group message ID, parallel consumers with partition keys, and the request-reply pattern. Each scenario is built and verified step by step against a Solace trial account standing in for AEM.PriyankaChak, published 2025-07-24
Beyond Basic AI Error Handling in SAP CPI - A Rules-First Architecture with HANA Cloud LearningBeyond Basic AI Error Handling in SAP CPI - A Rules-First Architecture with HANA Cloud LearningBuilds a rules-first error-diagnosis pipeline on Cloud Integration in SAP Integration Suite: a Groovy classifier resolves known failures — auth, timeout, malformed payload — deterministically, and only genuinely novel errors reach an LLM through the AI Adapter, after a sanitizer script replaces every payload leaf value with a typed placeholder before it leaves the tenant. SAP HANA Cloud, reached over JDBC, holds a fingerprinted dedup cache and an accumulating table of past diagnoses. It also documents the AI Adapter configuration — Advanced mode, a Bearer-prefixed Secure Parameter, and a connection/processing URL split — needed to reach a non-SAP OpenAI-compatible endpoint, found by the author to be undocumented.Krishna_Karthik, published 2026-06-11
Boost your CAP Development with AI: Introducing the MCP Server for CAPBoost your CAP Development with AI: Introducing the MCP Server for CAPThe announcement of the development-tool half of the two things called MCP here: a server that gives an agent context about the project in front of it and relevant CAP examples, so Claude Code or Copilot steers better. Names the agents it was tried with, which is more than most announcements do.published 2025-09-03
BTP Audit Log MCP Server: Security Monitoring with AI AssistantsBTP Audit Log MCP Server: Security Monitoring with AI AssistantsWouter Lemaire builds an MCP server over SAP BTP's Audit Log Retrieval API using odata-mcp-proxy, with a single entity set and zero custom code, so an AI assistant can answer natural-language questions like "Were there any configuration changes yesterday?" by calling AuditLogRecords_list against a BTP destination authenticated with the Audit Log service's service key. It covers the destination setup, the entity-set configuration that maps the PascalCase entity name to a lowercase auditlogrecords path, and handling the API's 500-record pagination limit.published 2026-03-13
BTP Cloud Foundry MCP Server: Managing CF Environments with AIBTP Cloud Foundry MCP Server: Managing CF Environments with AIWalks through a server built on odata-mcp-proxy that exposes the Cloud Foundry V3 API's 28 entity sets — apps, orgs, spaces, services, networking, quotas — as MCP tools from a JSON config with no application code. It shows the config shape that bridges the API's snake_case paths to PascalCase tool names via a urlPath field, and the OAuth2 client-credentials destination setup an assistant needs to reach a CF landscape.published 2026-03-13
Build Your AI Agent prototype for free using SAP CAP, LangChain and Ollama cloudBuild Your AI Agent prototype for free using SAP CAP, LangChain and Ollama cloudA CAP Node.js service action calls an Ollama-hosted model through LangChain's ChatOllama, with the API key read from a .env file instead of any destination or credential binding — the hand-rolled-key route SAP's own SDK call exists to avoid. The same handler then builds a LangChain agent with createAgent and one mock tool, so a question about restaurants triggers a tool call and any other question does not, independent of the @cap-js/agents plugin's A2A-served harness.rajeevgoswami1, published 2026-08-29
Building a CAP service with cds‑mcp and Cline — HANDS‑ON SUPER BASIC GUIDE [ with screenshots ] 🍌Building a CAP service with cds‑mcp and Cline — HANDS‑ON SUPER BASIC GUIDE [ with screenshots ] 🍌Somebody following the CAP MCP server announcement all the way through, and writing down what it cost: a CAP service in VS Code wired to S/4HANA through a destination, plus the real bumps — Windows PATH and global installs — that the announcement does not have.smarchesini, published 2025-09-21
Building a Generative AI-powered Inventory Assistant with SAP CAP, RAG, and Vector DatabaseBuilding a Generative AI-powered Inventory Assistant with SAP CAP, RAG, and Vector DatabaseAn existing CAP stock application turned into a question-answering one, and the part worth reading is the schema: three tables, not one — the products, an archive of the text that was embedded, and a separate lookup table holding the vectors. Retrieval finds candidate products by similarity and then reads the real rows, so the answer is grounded in records rather than in the embedded text.furkan5, published 2025-11-07
Building a Pro-Code Agent on SAP BTP — Part 2: The Agent (LangGraph + GenAI Hub)Building a Pro-Code Agent on SAP BTP — Part 2: The Agent (LangGraph + GenAI Hub)Part 2 of a three-part series builds a separate, non-CAP Node/TypeScript agent that calls the Part 1 CAP service's MCP tools and reasons through SAP AI Core via @sap-ai-sdk/orchestration, using LangGraph's createAgent ReAct loop for provider-agnostic model calls across GPT, Claude and Gemini deployments. It explains why the tool's Zod schema and model-facing description are the agent's actual contract, the gotcha between a foundation-models deployment and an orchestration-scenario one, and how edge-case testing replaced date inference with a server-computed daysOverdue field after the agent wrongly called a delayed order 'on schedule'.rodfior, published 2026-08-20
Building a Pro-Code Agent on SAP BTP — Part 3: Joule Integration via A2ABuilding a Pro-Code Agent on SAP BTP — Part 3: Joule Integration via A2AThe third instalment of a three-part series deploys an already-built CAP service and LangGraph agent to SAP BTP, Cloud Foundry Runtime, wraps the agent in an A2A protocol server, and registers it with SAP Joule through a capability YAML and the @sap/joule-studio-cli, confirming the chain works end to end inside a real Joule assistant. It covers CAP's default JWT/XSUAA authentication in production, what a test deployment needs to get past it, and the cf push, mbt build and environment wiring that run both apps as separate Cloud Foundry containers. A closing section names what stays unfinished by design — a long-lived AI Core service key, no authentication on the BTP destination, no principal propagation — as the gap between this MVP and a production posture.rodfior, published 2026-08-20
Building a Real‑Time Currency Conversion iFlow using SAP Cloud Integration (CPI)Building a Real‑Time Currency Conversion iFlow using SAP Cloud Integration (CPI)A step-by-step build of a currency-conversion integration flow in Cloud Integration: an HTTPS sender adapter accepts JSON, a content modifier stores the currencies and amount as exchange properties, and a Request-Reply step calls an external rate API before a Groovy script renders the result as an HTML table. A Global Exception Subprocess centralizes error handling for the whole flow, turning the MPL ID, error type and message into HTML and mailing it as a notification to a support address.RajeshwerRao_G_1, published 2026-04-01
Building an LLM Agent in CAP Java with Spring AIBuilding an LLM Agent in CAP Java with Spring AIThe Java counterpart to the author's own Node.js post, and written as one: connecting to AI Core with the SAP AI SDK, then calling an agent and a tool through Spring AI. Opens with a section on libraries and workflows — which framework does what, and what is left to you — before any code.published 2026-06-08
Building an LLM Agent in CAP Java with Spring AI
Agent tooling changed in @cap-js/agents 0.9.1, 2026-08-14. Affects Runnable code.
Building an LLM Agent using CAPBuilding an LLM Agent using CAPThe argument is that CAP is already most of what an agent framework wants — services, handlers, a typed model — so the agent is built inside it rather than beside it. AI Core through sap-ai-sdk, then Langchain for the agent and its tools. Long, with a TLDR at the top for people who want the shape without the walk.published 2026-05-27
Building an LLM Agent using CAP
Agent tooling changed in @cap-js/agents 0.9.1, 2026-08-14. Affects Runnable code.
Building and Consuming an MCP Server in SAP Integration Suite - Connecting it to Claude and JouleBuilding and Consuming an MCP Server in SAP Integration Suite - Connecting it to Claude and JouleA hands-on walkthrough of building a native MCP server artifact on SAP Integration Suite's Integration Cell runtime: an API artifact built from an OpenAPI 3.0 specification (the author converted the SAP Business Accelerator Hub's Swagger 2.0 OData spec) through API Management policies, with the MCP artifact's own Authorization policy set to the api.invoke scope for Developer Hub credentials or a custom role such as ESBMessaging.send for BTP OAuth credentials. The same server is then wired to Claude as a custom connector over an OAuth redirect, and to a Joule Studio agent through BTP destinations carrying the sap.mcp.tools.enabled property, with three worked agents (CPI monitoring, a SuccessFactors testing flow, IDoc reprocessing) run from both.Padmanathan_Vijayan, published 2026-09-11
Building Custom Joule Skills via RFC: Guide for SAP S/4HANA and ECC IntegrationBuilding Custom Joule Skills via RFC: Guide for SAP S/4HANA and ECC IntegrationWalks a Joule skill from a spoken question about a production order's status to an answer in SAP Build Workzone: a Cloud Connector tunnel and a destination in the BTP cockpit reach the S/4HANA or ECC system, a BAPI/RFC Action Project in SAP Build wraps the BAPI that reads the order, and Joule Studio, classic edition turns the action into a skill and deploys it. Establishing the connection and its destination before the action project exists is RFC connectivity and Destinations done for a low-code consumer rather than a CAP service. The action type here is BAPI/RFC, alongside the OData actions Joule Studio's own entry names.Robin-Qiu, published 2026-04-01
Building Durable AI Agents - Announcing the cds-langgraph-persistence PluginBuilding Durable AI Agents - Announcing the cds-langgraph-persistence PluginThe announcement, and the argument behind it. Treating an agent as a software architecture rather than a model with tools makes a list of production requirements — identity, authn and authz, multitenancy, persistence, event-driven flows, scalability, observability, CI/CD — and the author's point is that CAP already answers most of them for BTP, which is what makes LangGraph inside CAP Node.js worth doing. The post then narrows to one of those requirements, durability, and the checkpointer that supplies it. Written from a year of building agents next to real business systems rather than as a framework tour.merbinjanselm, published 2026-07-15
Building Durable AI Agents - Announcing the cds-langgraph-persistence Plugin
@mi8y/cds-langgraph-persistence has been through 3 major lines since this was published: 0.5 (2026-07), 0.6 (2026-07), 0.7 (2026-09). Affects Runnable code.
Building MCP Servers with SAP Integration Suite: What to Design, Not Just How to ConnectBuilding MCP Servers with SAP Integration Suite: What to Design, Not Just How to ConnectArgues that the tool design, not the connection, is the hard part of putting an API in front of an agent. Works one request — create a customer — through eight endpoint-shaped tools, where the agent carries ids between calls and rebuilds the business rules each run, then through a single intent-shaped create_customer that hides the sequence; and says what separates the two: a business operation for a name, parameters a caller can supply without a lookup, the rules in the server rather than the prompt, and a description written for an agent choosing a tool. The SAP Integration Suite half is short — three creation paths, an iFlow behind the API artifact when a tool has to cross systems — and it closes on a checklist to run before publishing.published 2026-07-07
Calling bound / unbound CAP actions from Fiori elements application.Calling bound / unbound CAP actions from Fiori elements application.invokeAction from the Fiori elements Edit flow API, with the difference between bound and unbound actions spelled out first because the call shape differs. Under three thousand characters and it answers exactly one question.vidhyasagarmule, published 2024-09-07
Calling Claude from ABAP: How I Wired SAP AI Core into a Real Business ScenarioCalling Claude from ABAP: How I Wired SAP AI Core into a Real Business ScenarioA proof of concept wiring SAP AI Core's Claude deployment directly into ABAP with no CAP layer between them: two SM59 HTTP destinations, a hand-written OAuth 2.0 client-credentials exchange, and a regex to unwrap Claude's system/messages response envelope. Most of the effort goes into a system prompt that constrains the model to return one fixed JSON schema of filter fields, which ABAP deserialises with /UI2/CL_JSON and exposes through a RAP custom action so a Fiori search field can drive an OData V4 filter.PranayGaroo, published 2026-06-04
Calling the Sales Order (A2X) OData V2 API from BTP Using a Service Consumption ModelCalling the Sales Order (A2X) OData V2 API from BTP Using a Service Consumption ModelWalks through ABAP's Service Consumption Model for OData V2 in ABAP Development Tools for Eclipse: generating a client proxy from the Sales Order (A2X) API's downloaded EDMX, then using it from an ABAP console class to create a deep sales order with items, texts, partners and pricing elements, read it back and patch a field. The client itself is built the way HTTP clients describes for SAP BTP ABAP environment: a communication arrangement resolved through cl_http_destination_provider=>create_by_comm_arrangement, handed to cl_web_http_client_manager=>create_by_http_destination, reaching the inbound SAP_COM_0109 scenario configured on the SAP S/4HANA Cloud Public Edition side.Katsiaryna_Darapeika, published 2025-02-04
Calling the Sales Order (A2X) OData V4 API from BTP Using a Service Consumption ModelCalling the Sales Order (A2X) OData V4 API from BTP Using a Service Consumption ModelWalks through calling SAP S/4HANA Cloud Public Edition's Sales Order (A2X) OData V4 API from an ABAP class on SAP BTP ABAP environment: a communication arrangement on each side, a Service Consumption Model built in ADT from the API's downloaded EDMX, and a client proxy wired through cl_http_destination_provider=>create_by_comm_arrangement and cl_web_http_client_manager=>create_by_http_destination, the same HTTP clients pattern for ABAP for Cloud Development. The sample class creates a deep sales order with an item, a text, a partner and a pricing element, reads it back, then updates a field guarded by its ETag.Katsiaryna_Darapeika, published 2025-02-06
CAP WebSocketsCAP WebSocketsThe early one, from 2021, before an adapter existed to make it ordinary. Read for what the problem looked like when it had to be solved by hand.vvdries, published 2021-01-26
CAP, CDS, CDL, CSN and jq - finding associationsCAP, CDS, CDL, CSN and jq - finding associationsHow associations are actually represented once CDL is compiled into CSN, worked out by parsing the machine-readable form with jq. Useful less as a recipe than as a way in: anything that wants to reason about a CDS model without the compiler has to read CSN, and this is what that looks like from the outside.published 2024-04-16
CAP: GraphQL as new protocolCAP: GraphQL as new protocolWritten days after @cap-js/graphql appeared, by somebody who went looking for it — an introduction to GraphQL alongside what the adapter actually does to a CAP service. The first outside account of the capability, and still one of very few.jhodel18, published 2023-03-18
CAP: GraphQL as new protocol
@cap-js/graphql has been through 11 major lines since this was published, most recently 0.12 (2025-05), 0.13 (2025-07), 0.14 (2025-10). Affects Runnable code.
cds-toon-ai-protocol-adapter: a pragmatic way to cut AI token costs using SAP CAPcds-toon-ai-protocol-adapter: a pragmatic way to cut AI token costs using SAP CAPNames a cost most CAP-plus-LLM writing ignores: every JSON payload streamed to a model is billed by its verbosity, in latency as well as money. The plugin brings TOON — Token-Oriented Object Notation — to a CAP service so the wire format changes without the service code doing so, in a REST variant and an OData one, with token counts reported on both sides.published 2026-01-25
Claude Code via MCP: Poor man's Joule, or a practical tool?Claude Code via MCP: Poor man's Joule, or a practical tool?The author drives Claude Code against a live ABAP system through vibing-steampunk, an ADT-to-MCP bridge that locks and unlocks objects on the agent's behalf so the model can concentrate on the change: extending an ALV report, turning its SELECT into a CDS view, and answering ad-hoc questions over the report's own data. Where Claude got it wrong — a RAP scaffold missing the fields RAP's locking mechanism needs, ORDER as a reserved word — the piece asks where that knowledge would go as a Skill, and concludes Skills' filesystem basis has no home in a system reached only through MCP.k1000, published 2026-03-08
Claude ported ABAP functions to new APIClaude ported ABAP functions to new APIA first-person account of using Claude Code, driven through the sapcli command line, to install and repair RFC function modules that let a CI pipeline control abapGit and gCTS remotely, rather than treating git as a way to read ABAP source. Instead of trusting a local checkout, Claude read the abapGit login manager class and queried the target system's own type catalogue through sapcli, then used what it found to update a renamed API method and swap a TABLES parameter's structure for the table type BAPIRET2_T.jakub_filak, published 2026-03-16
Cloud Integration with Document AICloud Integration with Document AIWalks through connecting Cloud Integration to SAP Document AI: an iFlow posts a prescription PDF to Document AI's job API, polls the job endpoint until it completes, and a groovy script reads back the result, keeping only the fields above a stated 60% confidence threshold. The scenario is a hospital extracting a new patient's past illnesses, allergies and blood group from uploaded prescriptions, matched against a custom extraction schema.PriyankaChak, published 2025-08-10
Communicate from a Java Application to ABAP via WebSocket RFC using JCo - Migration GuideCommunicate from a Java Application to ABAP via WebSocket RFC using JCo - Migration GuideWalks a JCo setup from classic CPIC-based RFC to WebSocket RFC: swap the application- or message-server logon properties for jco.client.wshost and jco.client.wsport, and implement DestinationDataProvider's getSSLContext (and, for mTLS, getClientCertificate) since the new connection runs over TLS. It covers building the PKI trust on both sides — a local PKCS12 keystore for the Java side, STRUST's SSL-Server Standard certificate exported and imported for mutual trust on the ABAP side — and notes that on BTP, JCo paired with the Destination service already implements this via the Connectivity service, so the custom SSLContext work can be skipped there.simon_luser, published 2025-01-21
Connecting a Custom MCP Server to Joule Work Desktop: A Seamless and Secure Authentication FlowConnecting a Custom MCP Server to Joule Work Desktop: A Seamless and Secure Authentication FlowWalks through connecting a custom MCP server to Joule Work Desktop: a Dynamic Client Registration handshake (RFC 7591) followed by an Authorization Code + PKCE flow through the organisation's SSO via XSUAA or IAS, so authentication establishes the human identity that Joule then attaches to every subsequent tool call. That forwarded identity lets the BTP backend apply its existing authorization checks and row-level data filtering instead of a second permission model, and a role change in XSUAA revokes access on the next token refresh.published 2026-08-17
Connecting SAP Integration Suite with SAP Document AI and SAP Business AIConnecting SAP Integration Suite with SAP Document AI and SAP Business AIWalks through a Cloud Integration flow in SAP Integration Suite that pulls PDF purchase orders from a Gmail mailbox, extracts header and line-item fields through SAP Document AI's job-submission and polling API, and validates the result with SAP AI Core's generative AI hub using GPT-5-mini as a quality check rather than the source of the extracted values. Groovy steps combine the Document AI confidence score and the model's score into one figure that routes low-scoring purchase orders to manual review, with no S/4HANA posting performed.subhojitSaha, published 2026-08-24
Connecting SAP Integration Suite with Slack: A Hands‑On Guide with Open ConnectorsConnecting SAP Integration Suite with Slack: A Hands‑On Guide with Open ConnectorsA walkthrough builds an integration flow on SAP Integration Suite that receives JSON over an HTTPS sender, transforms it with Groovy, and posts a formatted message to a Slack channel through the Slack Open Connector. An Exception Subprocess catches token, channel and connector-invocation failures and returns a structured error response, and the author verifies it by forcing a bad channel ID and confirming the error-notification email arrives.jareenabee_dudekula, published 2026-03-20
Create a Business Service using CDS, Node.js, SQLite and a OData serviceCreate a Business Service using CDS, Node.js, SQLite and a OData serviceThe stack at its smallest — CDS, Node, SQLite, an OData service — worked through at length. Nothing cloud in it, which is the point: it is the shape of a CAP service before any of the platform arrives.raybanton, published 2021-07-12
Create a Business Service using CDS, Node.js, SQLite and a OData service
Database connectors has changed twice since this was published, most recently in @sap/cds 10.1.0, 2026-09-07. Affects A recipe, Runnable code.
Create CDS Views and expose through OData service in CAPMCreate CDS Views and expose through OData service in CAPMViews defined in CDS and then exposed, which is the whole of what a small CAP service is. Written step by step from cds init onward in Business Application Studio.VenkateshMundru, published 2025-08-11
Creating a meal generator application with SAP Build, Cloud Application Programming and openAICreating a meal generator application with SAP Build, Cloud Application Programming and openAIIngredients in, meal suggestions out, assembled from BTP services plus OpenAI and Google APIs. A small application built for the pleasure of it, and useful here as the plainest example of CAP holding the middle of a generative flow.former_member793421, published 2023-07-17
Custom Functions in OData V4 – SAP Cloud Application Programming ModelCustom Functions in OData V4 – SAP Cloud Application Programming ModelFunctions rather than actions, and the distinction is where it starts: a function must return data and must never change any, so it is the read-only half of custom operations. Then how to declare and implement one on a CAP service.Roopa_N, published 2021-04-28
Custom Functions in OData V4 – SAP Cloud Application Programming Model
OData changed in @cap-js-community/odata-v2-adapter 1.10.0, 2023-04-05. Affects A recipe.
Custom Joule Agent for SAP Ariba SLP - Building an AI Agent for Supplier Registration ApprovalCustom Joule Agent for SAP Ariba SLP - Building an AI Agent for Supplier Registration ApprovalBuilds a Joule Studio agent that reviews SAP Ariba SLP supplier registration tasks: four custom skills bind to Ariba's API (pending tasks, task detail, questionnaire answers, post a decision), each needing a precisely configured BTP destination and action, and the agent's own Expertise, Instructions and Additional Context sections carry the domain knowledge, the step order, and the scoring rubrics that decide approve, deny or deny-with-resubmit. The author contrasts this with an earlier hand-wired flow on SAP Build Process Automation, where every connection, variable and error path had to be designed and wired manually.Giancarlo-Martinez, published 2026-04-07
Decision Logic Modernization in SAP Integrations: Using SAP-RPT-1 for Intelligent Routing DecisionsDecision Logic Modernization in SAP Integrations: Using SAP-RPT-1 for Intelligent Routing DecisionsWalks through embedding SAP-RPT-1 — SAP's foundation model for classification and regression over tabular ERP data, hosted on SAP AI Core — into a Cloud Integration flow that picks the optimal 3PL logistics partner for an outbound delivery. The iflow sends historical deliveries from SAP HANA Cloud plus the new delivery as context rows to the model's in-context learning, with no training step, and routes on the returned prediction and confidence score, the mechanism predictive models's core coverage describes for SAP-RPT-1. The author is explicit that SAP-RPT-1 differs from general-purpose language models trained on text, which keeps this apart from an LLM-integration scenario.arunmaarirajha_kv, published 2026-02-16
Develop a full stack Business application with SAP Cloud Application Programming ModelDevelop a full stack Business application with SAP Cloud Application Programming ModelBuilds a full-stack CAP application in SAP Web IDE Full Stack's now-retired 'SAP Cloud Platform Business Application' template: a data-model.cds entity with its own service definition, then Fiori annotations on the generated OData. Building the project compiles that model into Catalog.xml and csn.json, the EDMX and CSN that metadata publishing says every exposed service gets. The entity and service definitions it writes by hand are the basic shape data modelling covers, though the webIDE and MTA tooling staged around them is gone.former_member584731, published 2018-11-29
Don't "let it crash", is this the new CAP guideline?Don't "let it crash", is this the new CAP guideline?Dinu traces a change in error handling in CAP's Node.js runtime: @sap/cds@8.2.0 adds a cds.server.shutdown_on_uncaught_errors config flag, defaulting to true, but invoking an operation with an undefined variable no longer takes the server down, with or without the flag, where the same code crashed it on cds@6 and cds@7, and the author notes the old behaviour was already missing in cds@8.1. It still crashes with features.odata_new_adapter turned off to use the old OData parser, so it is the new OData adapter, like the REST adapter before it, that answers an uncaught error with a 500 instead of taking the process down.Dinu, published 2024-09-06
Don't Wait for SAP: Unlocking MCP Servers in BAS Right NowDon't Wait for SAP: Unlocking MCP Servers in BAS Right NowA workaround post with a grievance behind it: MCP servers were promoted heavily at SAP TechEd, most IDEs support them, and Business Application Studio limits you to Joule. This is how to run them there anyway. Worth reading as evidence of where the tooling gap sits rather than only for the recipe, which by nature has a shelf life.published 2025-11-27
Dynamic OData from "any" API through SAP BTP KymaDynamic OData from "any" API through SAP BTP KymaPutting an OData face on a third-party API by way of Kyma, so the SAP side of a landscape can consume something that was never built for it. The word dynamic is doing work in the title — the shape is not modelled in advance.Gunter, published 2021-09-09
Edge Integration Cell : Design, deploy and manage APIsEdge Integration Cell : Design, deploy and manage APIsWalks through creating an API artifact in API Management on the customer-managed Edge Integration Cell runtime, including the option to generate the artifact by importing an OpenAPI specification rather than from a URL or by hand. It then attaches an Authentication policy and a Quota step capped at four calls per minute, deploys, and shows both the resulting 401 and the quota-breach error in the Monitor logs. The author frames it as the first of a series on Edge Integration Cell's policies.published 2023-11-15
Effective Axios Error Logging for Robust SAP IntegrationsEffective Axios Error Logging for Robust SAP IntegrationsTwo logged failures printed side by side, and the point is made by looking at them: one tells you what went wrong and one does not. Axios buries the useful part of an HTTP error, and this is what to unwrap before logging it from a CAP service.Sahil2508, published 2025-08-31
Elevating Data Privacy in SAP CAP based GenAI Applications with CAP LLM PluginElevating Data Privacy in SAP CAP based GenAI Applications with CAP LLM PluginThe question underneath the enthusiasm: what leaves your landscape when a prompt goes to a model. The plugin's answer is to anonymise the sensitive fields through HANA before the prompt is sent, and this is the post that explains why that is the design rather than an option.AkashAmarendra, published 2024-02-02
Empowering Your Data Analytics with GPT-3 and SAP CAP IntegrationEmpowering Your Data Analytics with GPT-3 and SAP CAP IntegrationFree text in, SQL out, answer back in a sentence — the model writes the query, CAP runs it, and the model turns the rows into prose. Written in the GPT-3 window, so the model access has dated, but the three-step shape has not, and it is a different bet from retrieval: nothing is embedded, the schema is the context.Former Member, published 2023-03-10
Enhancing Business Processes with SAP BTP AI in SAP Integration SuiteEnhancing Business Processes with SAP BTP AI in SAP Integration SuiteWalks through a post-exit iflow in SAP Integration Suite that calls an LLM through SAP AI Core's Generative AI Hub to turn a customer's free-text return comment into one of a fixed set of SAP rejection-reason codes, so an inbound ORDERS05 IDoc carries a decision (E1EDP01-ABGRU) the ERP can act on without pausing for manual review. The worked example is a Commerce Cloud returns flow into S/4HANA; the piece argues the same bounded-classification pattern fits other narrative fields — delivery-exception remarks, expense-claim justifications — where the cost of an LLM call is repaid by removing a human review step, and points to a colleague's post on the Generative AI Hub orchestration workflow for the guardrailing (prompt templating, data masking) it only names.arunmaarirajha_kv, published 2025-12-15
Enhancing Enterprise Applications: AI-powered User Experience with SAP CAP AI PluginEnhancing Enterprise Applications: AI-powered User Experience with SAP CAP AI PluginStarts from the blank form nobody wants to fill in, and asks what an enterprise application should do about it. The AI is in service of that rather than the subject of it.published 2026-04-29
Enhancing Unit Testing in SAP CAP Java Applications with GitHub CopilotEnhancing Unit Testing in SAP CAP Java Applications with GitHub CopilotBuilt on SAP's own CAP Java unit-testing guide, and the question is narrow: how much of that does an assistant actually write for you. The author's own getting-started post is the one to read first.Anjali_Pathak, published 2025-09-04
Evaluating SAP’s new MCP servers: UI5, CAP, and Fiori tools in practiceEvaluating SAP’s new MCP servers: UI5, CAP, and Fiori tools in practiceSomeone trying SAP's three new MCP servers rather than repeating the announcement. It sets the official positioning first — MCP as the bridge from coding assistants to SAP tooling across Cursor, Windsurf, Copilot, Cline and Claude Code, with best-practice scaffolds and BTP-aligned guardrails — and then reports what using them is actually like. The rare kind of post that tests a vendor claim.published 2025-09-04
Event Driven SAP CAP on Kyma with Agentic AI and UI Auto RefreshEvent Driven SAP CAP on Kyma with Agentic AI and UI Auto RefreshA prototype, described as one: a plain CAP application made to react to external events on Kyma, with an agent in the loop and the UI refreshing itself rather than being reloaded. Short — it reports what was built and why, not how to rebuild it.Shahid, published 2025-12-01
Explaining SAP Joule for HR Business Users & Functional Consultants.Explaining SAP Joule for HR Business Users & Functional Consultants.Written for HR business users and functional consultants, this walks through how SAP Joule is provisioned on SAP BTP and wired into SuccessFactors: the Joule instance sits in a BTP subaccount, SAP Build Work Zone is created alongside it, and Identity provisioning syncs users from SuccessFactors into Build Work Zone while Cloud Identity Services authenticates the launch through an IAS tenant. It lists five prerequisites for the connection — a BTP global account, a Joule entitlement, Cloud Identity Service and SuccessFactors admin access, and the right personas — and notes that running BTP's booster adds the Joule permission to the SuccessFactors user's profile.santanuray_learner, published 2025-03-23
Expose RFCs as MCP Tools in Integration SuiteExpose RFCs as MCP Tools in Integration SuiteWalks through creating an MCP server in SAP Integration Suite from an RFC source: an on-premise RFC destination labelled for Integration Cell inclusion, a search over the backend's function modules (minimum seven characters), and up to 50 selected modules each becoming a tool. Covers the resulting server's configuration (Source, Tools and Prompts, with no Resources section for this source) and the two scopes an RFC-based server's policy adds beyond an API-sourced one, API.invoke and ESBMessaging.send, plus the RFC receiver adapter used at runtime. Demonstrates the flow with a purchase-order scenario where an AI client calls BAPI_PO_CREATE1 and BAPI_PO_GETDETAIL1 as MCP tools.ronit199666, published 2026-09-24
Expose S/4HANA Cloud OData API as an MCP Server via CAP Node.jsExpose S/4HANA Cloud OData API as an MCP Server via CAP Node.jsA step-by-step walkthrough that wraps SAP S/4HANA Cloud's Outbound Delivery OData v2 API in a CAP Node.js service and exposes it through @cap-js/mcp, so an MCP client can list the generated tools, query the delivery entities and call a custom createDelivery action over JSON-RPC. The remote S/4HANA connection is configured two ways in package.json: direct Basic Authentication credentials for local hybrid testing, and a named BTP destination for the app once deployed to Cloud Foundry.Jacky_Liu1, published 2026-07-29
Expose S/4HANA Cloud OData API as an MCP Server via CAP Node.jsExpose S/4HANA Cloud OData API as an MCP Server via CAP Node.jsA CAP Node.js service imports the S/4HANA Cloud Outbound Delivery OData v2 API's EDMX metadata with cds import, proxies its reads and a custom createDelivery action against it, and annotates the service @protocol: ['odata-v4', 'mcp'] with @cap-js/mcp's per_action_tool setting on, so the custom action gets its own MCP tool rather than one generic call_action. It tests the result with raw JSON-RPC tools/list and tools/call requests before deploying to SAP BTP, Cloud Foundry Runtime.Jacky Liu, published 2026-07-29
Exposing Calculation View with Dynamic Client via OData APIExposing Calculation View with Dynamic Client via OData APIGetting a HANA Cloud calculation view — built in Business Application Studio and deployed to an HDI container, which is the recommended way to build native HANA artifacts — out through an OData API. The gap it fills is the one between HANA-native development and a service a client can call, which CAP does not cover for artifacts it did not generate.published 2023-10-04
Extend SAP SuccessFactors on SAP BTP with CAP - Create the CAP ServiceExtend SAP SuccessFactors on SAP BTP with CAP - Create the CAP ServiceWalks through writing a service definition in SAP Business Application Studio that projects entities from an existing CDS model: one entity gets @odata.draft.enabled because Fiori Elements only shows CRUD actions on a draft-enabled entity, and a read-only projection of an already-imported SuccessFactors OData entity fails with the generic handlers because the call is delegated to the remote service, so a custom handler is needed. Running cds watch then serves the entities, drafts and $metadata at the declared service path.published 2022-03-23
Extending Standard S/4 HANA OData API'sExtending Standard S/4 HANA OData API'sWalks through extending a standard S/4HANA OData API with a custom field, preferring OData V4 over V2 for its closer OASIS compliance and simpler service enablement, then tracing the extensibility objects documented for the entity before touching any code. The custom field reaches the API by layering three CDS view extensions — extendView on I_Product, extendViewEntity on R_ProductTP and on A_Product_3 — following the projection chain down to where the base table is first selected, built in ABAP Development Tools for Eclipse.JuanDK78, published 2026-04-08
From Dashboard to Conversational AI in Minutes: Adding MCP to an Existing CAP ApplicationFrom Dashboard to Conversational AI in Minutes: Adding MCP to an Existing CAP ApplicationA walkthrough of adding @cap-js/mcp to an existing CAP service behind the SuccessFactors Localization Dashboard: two annotations (@odata, @mcp) expose the service over MCP beside its existing OData endpoint, and doc comments added to the 18 entities and their fields are surfaced through the describe tool so a querying model gets business context instead of bare field names. During local development cds watch auto-registers the endpoint in ~/.claude.json, and the author connects the same endpoint to Joule Work Desktop as an MCP connector so users can ask coverage questions in natural language.i533678, published 2026-08-24
From SAP Integration Suite iFlow to MCP Tools: Exposing OData APIs to AI AgentsFrom SAP Integration Suite iFlow to MCP Tools: Exposing OData APIs to AI AgentsBuilds an MCP Server artifact inside SAP Integration Suite's Integration Cell runtime that fronts a Northwind OData V4 API through a Cloud Integration iFlow, turning each OpenAPI operation into a tool an agent can call. Walks through the OAuth2 client-credentials flow against XSUAA and the authorization policy scope — ESBMessaging.send in place of the default API.invoke — that gates access to the MCP server, then tests the server from Claude Code.published 2026-07-14
From SAP Sales and Service Cloud V2 APIs to AI: Building an MCP Server with CAP Node.jsFrom SAP Sales and Service Cloud V2 APIs to AI: Building an MCP Server with CAP Node.jsA step-by-step CAP Node.js walkthrough that wraps the SAP Sales Cloud V2 Case API as a remote service, then exposes the resulting service over both OData V4 and MCP through a single @protocol: ['odata-v4', 'mcp'] annotation together with @cap-js/mcp's per_action_tool setting. Each CDS action — listCases, getCaseById, createCase, patchCase — becomes its own MCP tool served at /mcp/caseservices, discoverable through tools/list and invoked from a natural-language request.pvsbprasad, published 2026-08-31
From SEGW to @OData.publish: Expose Your CDS View as OData in S/4HANAFrom SEGW to @OData.publish: Expose Your CDS View as OData in S/4HANAWalks through exposing an ABAP CDS view as an OData service in an on-premise S/4HANA system by adding the @OData.publish: true annotation, then registering and activating the generated service in SAP Gateway (transaction /IWFND/MAINT_SERVICE) before testing it with $filter, $top and $count. It sets this against the manual route through transaction SEGW, since the annotation generates the service, its navigation properties and its OData properties straight from the CDS view without a Service Builder project.rupalipunekar1234, published 2026-07-09
From SEO to MEO: Designing Joule-Ready API Layers for SAP Commerce CloudFrom SEO to MEO: Designing Joule-Ready API Layers for SAP Commerce CloudProposes 'Machine Experience Optimization' (MEO), the author's own term and explicitly not an SAP one, for a governed intent facade in front of SAP Commerce Cloud's OCC APIs so an assistant or a SAP Joule skill gets small, business-oriented operations instead of raw endpoints. Works through a full OpenAPI 3.0.3 contract for a product-search intent, with explicit read/write separation, a short-lived confirmation step and an idempotency key for the consequential 'place order' operation, and authorization checked against account and base-site boundaries rather than at the URL alone. The facade still delegates to Commerce's own services, facades and validation; it does not replace or bypass them.BhardwajAditya, published 2026-09-15
From Strategy Doc to Runtime Rule: Embedding SAP AI Standards into Claude CodeFrom Strategy Doc to Runtime Rule: Embedding SAP AI Standards into Claude CodeAn experiment in treating published engineering standards as machine-readable instructions an agent follows while it works, rather than as documents somebody is supposed to have read — hooks and skills wired so the rule applies at the moment code is written. The disclaimer is emphatic and worth carrying: a personal exploration, not an SAP product, not an endorsed approach, and readers are told to verify applicability through official channels. Read as a shape for the idea, not as a standard to adopt.ZYT, published 2026-06-25
From Zero to Fiori: Building SAP Apps with AI Agents (And Why I Use Markdown Files Instead of MCP)From Zero to Fiori: Building SAP Apps with AI Agents (And Why I Use Markdown Files Instead of MCP)Eleven entities and four Fiori apps in forty-five minutes, orchestrated rather than typed — and the author is careful to say it is a base to develop from, not something ready to ship. The markdown-files-as-instructions method is the transferable part.michal_majer, published 2025-12-10
GenAI Mail Insights - Leveraging the generative AI hub in SAP AI Core to improve customer supportGenAI Mail Insights - Leveraging the generative AI hub in SAP AI Core to improve customer supportA sample application rather than an explainer, and the author says so in the opening — enough talking, here is something that runs. Incoming support mail summarised and categorised through the generative AI hub in AI Core.martinfrick, published 2023-11-15
Generating Adobe Form Using RAP framework OData ServicesGenerating Adobe Form Using RAP framework OData ServicesModels a RAP root view entity and consumption view over a custom sales-order table, built with ABAP CDS, and exposes it through a service definition and an OData V2 UI service binding. A separate SEGW project implements GET_STREAM to call an Adobe Form driver class and stream the rendered PDF back as the response, with a computed link field added to the CDS view so the UI can open it. The PDF is generated in the backend and returned to the calling program rather than sent straight to a printer.Megastar, published 2025-03-18
Github Copilot VSCode - My Own SAP Development RulesGithub Copilot VSCode - My Own SAP Development RulesOne developer's rule files for Copilot, split by concern rather than kept as one prompt: CAP backend rules, UI5 frontend rules, Jest testing rules and Bruno collection rules, each with a scope narrow enough that an agent cannot read it two ways. The CAP file covers reusable types, managed data, soft-delete behaviour and service conventions; the UI5 file covers naming, view constraints and where annotations may live. It is the rule-file half of agent guidance rather than the skill half — nothing is packaged or published, and the value on offer is the shape of the split.radu_simen, published 2026-02-05
Give Your AI Agent Some Tools: Introducing the UI5 MCP ServerGive Your AI Agent Some Tools: Introducing the UI5 MCP ServerAnnounces @ui5/mcp-server, SAP's open-source MCP server for UI5 development, and walks through its initial six tools. get_project_info, get_api_reference and run_ui5_linter (which applies UI5 linter fixes) read the project's own version, manifest and code rather than an LLM's training data, which is what agent access to your code explains. create_ui5_app scaffolds a new JavaScript or TypeScript project, standalone or inside an existing CAP application, from templates with pre-configured OData model setups, which is generators.published 2025-09-03
Governance at Scale: Why a Clean Core Is What Makes Agent Governance EnforceableGovernance at Scale: Why a Clean Core Is What Makes Agent Governance EnforceableClosing a six-part clean-core series, the post argues that SAP's two agentic-AI governance mechanisms only work against a documented tool surface: MCP Gateway in SAP Integration Suite auto-translates API specifications into MCP tool schemas augmented with natural-language semantics, carrying forward existing authentication, authorization and rate limiting into the agentic layer, while AI Agent Hub, built on SAP LeanIX, discovers and runs verification assessments on agents, LLMs and MCP servers before the resulting badge is read by Joule Studio or SAP Integration Suite to decide what is trusted. Its argument holds the mechanisms up against an undocumented internal interface, where the auto-generated schema and the verification badge have nothing real underneath them, and against a consolidated CAP service exposing only released APIs, where both do.DEEPA_DORAIRAJ, published 2026-09-21
Graph intro series, part 8: Use Graph With OData v4Graph intro series, part 8: Use Graph With OData v4Part eight of the Graph intro series works through querying SAP Graph's unified business data graph over OData v4: inspecting the $metadata EDMX document for an entity type such as SalesQuote, then shaping the response with $select and nested $expand across navigation properties, and paging a collection with $filter, $orderby, $top and $skip. It stays with the protocol mechanics against the Graph sandbox endpoint rather than any one client library.florian_moritz, published 2024-03-19
HANA Cloud’s VECTOR EMBEDDING in CAP and Comparison with OpenAI EmbeddingHANA Cloud’s VECTOR EMBEDDING in CAP and Comparison with OpenAI EmbeddingTwo ways to produce the same embedding, run side by side: HANA Cloud's own VECTOR_EMBEDDING function against Azure OpenAI through the CAP LLM plugin. The CDS side is short — an element of type cds.Vector maps to REAL_VECTOR on deploy — so what remains is the comparison, which is the thing you cannot get from either product's documentation alone.lalitmohan, published 2025-04-09
How Redwood Software and SAP are shaping the next era of automation with Joule StudioHow Redwood Software and SAP are shaping the next era of automation with Joule StudioRedwood's Field CTO describes a tech preview where an SAP Basis administrator tells SAP Joule in natural language to pause background jobs and dependent Integration Suite iFlows for unplanned system maintenance; Joule acts as a control tower, triggering a pre-approved RunMyJobs workflow and asking for approval before the restart proceeds. The integration is built by publishing RunMyJobs operations to the SAP Business Accelerator Hub, securing access through SAP BTP with API keys and role-based permissions, and combining those actions into a skill inside Joule Studio's low-code design canvas.gmblom, published 2025-11-02
How to add OData v2 adapter proxy to your CAP projectHow to add OData v2 adapter proxy to your CAP projectThe problem is stated in one line — a UI5 application that only speaks OData v2 in front of a CAP service that speaks v4 — and the answer is a proxy in the middle rather than a rewrite of either end. Written while v4 support in the UI5 stack was still patchy, which is the whole reason the adapter exists.published 2020-06-30
How to add OData v2 adapter proxy to your CAP project
OData changed in @cap-js-community/odata-v2-adapter 1.10.0, 2023-04-05. Affects Runnable code.
How to Connect Claude Code to ABAP with Zero-Config MCPHow to Connect Claude Code to ABAP with Zero-Config MCPWalks through wiring Claude Code, via its VS Code extension, to a live SAP system through an ABAP remote-filesystem extension built by Marcello Urbani and its built-in MCP server — a single toggle rather than a hand-rolled Node.js setup — so the agent searches, reads, writes, activates and assigns transports for ABAP objects over the same ADT REST API Eclipse uses, instead of guessing at tables and function modules it has never seen. The demo carries one plain-English prompt through to a real, activated ABAP program on a live S/4HANA system, including a transport-request dialog Claude worked through on its own.Nibedita, published 2026-07-05
How to create a Purchase Order through BAPI in the SAP through program ( SE38 ) T-CODE .How to create a Purchase Order through BAPI in the SAP through program ( SE38 ) T-CODE .Walks through creating a purchase order from an ABAP report (SE38) by filling the BAPIMEPOHEADER/BAPIMEPOITEM structures and their X-indicator counterparts, then calling BAPI_PO_CREATE1 within the same session. Its error handling centres on the BAPIRET2 return table: looping over entries typed E or A, skipping BAPI_TRANSACTION_COMMIT when one is found, and displaying the returned message text rather than assuming success once the function module returns.chandu_kumar_badukuri, published 2025-12-18
How to Perform Initial Loads from S/4HANA to Advanced Event Mesh with Odata PollHow to Perform Initial Loads from S/4HANA to Advanced Event Mesh with Odata PollWalks through building a Cloud Integration flow that polls the S/4HANA Business Partner OData API on a timer, splits the response into individual records, and publishes each as an event to Advanced Event Mesh through its adapter, with the topic set dynamically from a grouping property. Selects fields and expands associations with $select/$expand against an EDMX from the API Business Hub, and works around the OData V2 adapter's lack of JSON support by falling back to the HTTP adapter with an XML-to-JSON converter. Flags the trade-off: the pattern needs no backend change beyond activating the API, but the polled payload has to stay aligned with whatever event format the ERP pushes on change.AlexPfeil, published 2025-04-04
How to Reduce Prompt Token Costs Using Toon = Save MoneyHow to Reduce Prompt Token Costs Using Toon = Save MoneyToken spend treated as a running cost rather than a detail, and TOON as the lever. Companion reading to the CAP adapter for the same format that is indexed here.Yogananda, published 2025-11-12
How to Reduce Prompt Token Costs Using Toon = Save Money
LLM integration changed in @cap-js/ai 1.0.0, 2026-04-28. Affects A recipe, Runnable code.
How to rename an OData V4 service?How to rename an OData V4 service?Renaming an OData V4 service binding changes its Service Alias and the resulting service URL, breaking any app already deployed against the old one — shown on a /DMO/TRAVEL-based example in the SAP BTP ABAP environment by unpublishing, renaming and republishing the binding, then reading the new URL back from the OData V4 service catalog's ServiceGroups entry. It weighs that against two alternatives: adding a second service definition and publishing it as a new service version under the same binding, or creating an entirely new service definition and binding, which keeps the original URL live during the cutover.published 2026-07-04
How to subscribe or fetch data from solace to CPI using AEM Adapter : part-5How to subscribe or fetch data from solace to CPI using AEM Adapter : part-5Closes a series on event-driven architecture with Solace by detailing the subscriber side of an iFlow in Cloud Integration: an advanced event mesh adapter feeds an exception subprocess, and a Groovy step classifies each failure as recoverable, left to Solace's own retry, or non-recoverable, answered with a custom property that tells Solace to stop retrying before the message reaches an escalation layer. The escalation layer names email, ServiceNow and Loggly as destinations without explaining any of them.pavanKolla, published 2025-08-03
How to use Cloud SDK for AI in an existing CAP NodeJS Project in CommonJSHow to use Cloud SDK for AI in an existing CAP NodeJS Project in CommonJSA dependency that is ESM-only inside a project that is CommonJS, and the author's judgement that converting the project was too risky. What follows is the esbuild workaround, which is the honest answer when the ecosystem has moved and your codebase has not.Jacky_Liu1, published 2025-08-01
How to use reserved words as property names in your OData service?How to use reserved words as property names in your OData service?Setting a CDS view alias to a reserved OData word, such as Number, fails compilation with 'NUMBER is a reserved word'. The fix for a RAP-based OData service is the @odata.property.name annotation: it lets the underlying CDS view keep a compiler-safe name (NumberInStock) while the $metadata EntityType still exposes the field as Number, shown against a products view and its generated EDMX.Andre_Fischer, published 2025-11-10
Importing an external data model using CDS Graphical Modeler for Visual Studio CodeImporting an external data model using CDS Graphical Modeler for Visual Studio CodeWalks through the CDS Graphical Modeler for Visual Studio Code: creating a "Customers" entity, importing an external OData model from an edmx file into the CDS model, and drawing a managed association from the new entity to an entity from the imported namespace. The import happens through the modeler's GUI rather than the cds import command, and the imported edmx becomes a CDS file the modeler can open directly.Xiao-fei_Song, published 2022-05-09
Importing external edmx files to your CAP project using the CDS Graphical ModelerImporting external edmx files to your CAP project using the CDS Graphical ModelerAn EDMX downloaded from the API hub — API_BUSINESS_PARTNER in the example — imported into the CDS model and its entities exposed as projections, done through the graphical modeller rather than cds import. Barely a page long.Xiao-fei_Song, published 2021-05-19
Improving Exception Handling using Generative AI in SAP Cloud Integration (SAP CI/CPI)Improving Exception Handling using Generative AI in SAP Cloud Integration (SAP CI/CPI)Wires an Exception Subprocess in Cloud Integration to send a failed iFlow's caught exception text to Google Gemini's generateContent endpoint over the HTTP adapter, then parses the response in Groovy for a user-friendly error message, the likely causes, the steps to try and an HTTP status code to return to the sender. A Content Modifier holds the API key and the prompt as externalised properties, which the post says is what lets another model be put in their place, and a closing Groovy script writes the extracted fields to custom headers and log attachments and rebuilds them as an XML error response. The exception-subprocess wiring is given step by step and so is the Gemini call with its request format, which is why the piece sits on integration flows and on LLM integration.AdarshRao, published 2025-07-20
Integrate CAP application as outbound channel for SAP Document AIIntegrate CAP application as outbound channel for SAP Document AIDocument AI will call you back when extraction finishes, and the callback is where this goes wrong: the CAP application has to accept an unauthenticated POST from outside without dropping CSRF protection for everything else. The answer is a middleware hooked into the CAP bootstrap, and the post spends its length on the token lifecycle rather than on the extraction.sdeissenboeck, published 2026-04-22
Integrate Document Information Extraction into UI5 applicationIntegrate Document Information Extraction into UI5 applicationUploading an invoice from a UI5 application and getting the extracted fields back on screen, with a destination pointing at the Document Information Extraction API and a Refresh button polling until the job finishes. The polling is the honest part: extraction is asynchronous, and the post does not pretend otherwise. From 2022, so the service has since been renamed and the API moved, but the shape — upload, poll, map the result — is the shape it still is.published 2022-05-31
Integrating a Custom AI Model into SAP CAP Using AI LaunchpadIntegrating a Custom AI Model into SAP CAP Using AI LaunchpadYour own model rather than a hosted one: deployed to AI Core, made callable through AI Launchpad, then reached from CAP. The case a lot of companies ask about and few posts cover.egeAksoyek, published 2026-03-20
Integrating a Custom AI Model into SAP CAP Using AI Launchpad
LLM integration changed in @cap-js/ai 1.0.0, 2026-04-28. Affects Runnable code.
Integrating SAP Document Information Extraction (Document AI) with SAP CAP – Step by StepIntegrating SAP Document Information Extraction (Document AI) with SAP CAP – Step by StepThe forward direction, in full: a PDF or scan arriving at a CAP service, sent to Document Information Extraction, and the fields coming back into the model. Long, and step-by-step in the literal sense — the service binding and the request shapes are all written out.furkan5, published 2025-10-09
Integration Suite: Building an MCP Server for a SAP CI Monitoring AssistantIntegration Suite: Building an MCP Server for a SAP CI Monitoring AssistantA step-by-step walkthrough of building an MCP Server artifact on SAP Integration Suite's Integration Cell runtime that wraps the Cloud Integration OData Message Processing Logs API, so a client such as Claude Desktop or VS Code can query failed interfaces in natural language instead of clicking through Monitor. It covers importing an OpenAPI 3.0 specification so each operationId becomes a discoverable tool, selecting tools/resources/prompts, and wiring two separate OAuth service keys — one read-only credential the HTTPS adapter uses against the monitoring API, another the MCP client uses to reach the deployed endpoint. The server is deliberately read-only and ships with no rate limiting or audit logging, which the author flags as missing before any write operation or production use.Daggolu_PremSai, published 2026-07-17
Introducing the Cloud Application Programming Model (CAP)Introducing the Cloud Application Programming Model (CAP)SAP's own general-availability announcement for CAP, laid out as a Golden Path: a data model and service defined in CDS gets a generated service provider that serves metadata publishing and CRUD requests, fills in primary keys and audit data, and writes trace and audit logs without application code. The same CDS model carries annotations that translate to OData vocabularies and generate a Fiori elements app skeleton, which is how Fiori annotations work in CAP.Daniel7, published 2018-06-05
Invoke OpenAPI-documented APIs remotely with SAP Cloud Application Programming ModelInvoke OpenAPI-documented APIs remotely with SAP Cloud Application Programming ModelThe other direction: consuming an API described by an OpenAPI document from CAP, rather than publishing one. Worth pairing with the plugin entries here, which all serve the outbound half.wittro, published 2022-08-30
Invoke OpenAPI-documented APIs remotely with SAP Cloud Application Programming Model
Destinations changed in @sap-cloud-sdk/connectivity 4.0.0, 2025-03-04. Affects Runnable code.
Invoking Business Agent Foundation Agents from ABAP: A Step-by-Step GuideInvoking Business Agent Foundation Agents from ABAP: A Step-by-Step GuideWalks through calling a Business Agent Foundation agent's chat endpoint from an on-premise ABAP report: an OAuth 2.0 client profile configured in SE80/SOAUTH2_CLIENT with client-credentials grant against the service key, an HTTP (type G) RFC destination in SM59 bound to that profile, and an ABAP report using CL_HTTP_CLIENT=>CREATE_BY_DESTINATION to POST a JSON message to the agent's sendMessage endpoint and extract the reply by splitting the response string. The destination and client code are the same shape as any outbound REST call from ABAP; nothing here is specific to the agent service beyond the request body and URL.tanmay_0117, published 2025-11-26
Is it time to switch to OData v4?Is it time to switch to OData v4?A recommendation with its caveat attached: use v4 on new projects, and be aware it is less mature than v2 in terms of what the SAP stack around it supports. Written after using it on a real extension project, which is what makes the caveat credible.MikeDoyle, published 2021-02-05
Joule for Developers with SAP BTP ABAP Environment-Setup GuideJoule for Developers with SAP BTP ABAP Environment-Setup GuideA step-by-step setup guide for SAP Joule for Developers, ABAP AI capabilities under its Q2 2026 limited-promotion licence: creating a BTP subaccount, adding ABAP environment and HANA compute-unit entitlements, enabling Cloud Foundry, configuring trust to Cloud Identity Services, creating the ABAP environment instance and assigning the developer role, then pointing ABAP Development Tools for Eclipse at the new system. It walks through the resulting Joule chat, predictive code completion, explain, ABAP Unit and CDS test-generation features inside a newly created ABAP Cloud project.YASHLAL, published 2025-09-11
Joule Studioがリリースされたので早速CAPアプリを自然言語で操作するカスタムスキルを構築してみたJoule Studioがリリースされたので早速CAPアプリを自然言語で操作するカスタムスキルを構築してみたA walkthrough of building a custom Joule Studio skill on a CAP bookshop app: cds add sample and cds add mta scaffold the project and its deployment descriptor, cds compile srv/ --to xsuaa generates the role template behind the @requires: 'admin' check on AdminService from the SAP Authorization and Trust Management service (XSUAA), and mbt build packages the app for deployment to the SAP BTP, Cloud Foundry Runtime. The skill reaches the deployed OData API through the SAP Destination service, configured with the OAuth2 Client Credentials grant using the client ID, secret and token endpoint from the app's XSUAA service key, so Joule answers a natural-language question about a book by its ID.takayuki_tanaka, published 2025-07-30
Lets Talk to the Database - CAP & SQLite Powered by Google Gemini-2.5-ProLets Talk to the Database - CAP & SQLite Powered by Google Gemini-2.5-ProNatural language against a CAP service on SQLite, with a non-SAP model doing the translation. Written as a learning exercise rather than a pattern, and the choice of Gemini over anything in the AI hub is the interesting part of it.ShivamShuklaSAP, published 2025-04-16
Major New Version of the hana-cli: How It Was Built with the Help of AI (and a Lot of Human Review)Major New Version of the hana-cli: How It Was Built with the Help of AI (and a Lot of Human Review)More features in two months than the previous two years — and the sentence after that is the reason to keep it: quality still needed the human review, and the post is about the rough edges rather than the headline. A maintainer reporting on their own process.thomas_jung, published 2026-03-11
Making the Case for Enhanced REST Adapter in SAP Integration SuiteMaking the Case for Enhanced REST Adapter in SAP Integration SuiteCatalogues what SAP Integration Suite's native HTTP adapter supports for authentication (Basic, OAuth 2.0 client credentials and client certificates on the sender; OAuth 2.0 client credentials and SAML bearer assertion on the receiver) and for error handling (retry on HTTP failure only, with no pattern-based retry, failure queues or dead-letter queues), and that it has no OpenAPI import or export. Three worked scenarios, FedEx shipment tracking, Avalara AvaTax and SAP Ariba's operational reporting API, name what that leaves to Groovy scripting: the other OAuth 2.0 flows, gzip and multipart payloads, and pagination that chains a nextPageToken by JSONPath, which is the case the piece makes for the third-party Advantco REST Adapter.peter_ha3, published 2025-07-14
MCP Server for SAP Incentive ManagementMCP Server for SAP Incentive ManagementA proof of concept putting SAP Incentive Management behind MCP so an agent can reach it, spanning the server, the backing APIs and SAP Advanced Workflow. The post opens with an unusually explicit disclaimer — personal capacity, no organisation's architecture or policies represented, and any real implementation needing customer and SAP review first — which is itself the useful part of reading it: it is a shape to think with, not a design to deploy.published 2026-07-16
MCP Servers are the New Z-TablesMCP Servers are the New Z-TablesA single CAP service exposed as three overlapping MCP servers tools, queried by the same prompt nineteen times, returned the same tool every time — evidence, the author argues, that tool selection rests on the resemblance between a prompt and a tool's description rather than on any binding a where-used list could enumerate before retiring it. It contrasts that setup with @cap-js/mcp, which exposes a whole service as three generic tools instead of one per operation, and quotes the adapter's own beta documentation admitting no rate limiting, audit logging, input validation or approval workflow, and no use as a gateway to SAP Application APIs. From there it names four small Tool governance practices it has adopted: an owner recorded in the tool's own metadata, logging every invocation, deprecating inside the description, and exposing fewer tools.published 2026-08-21
MCP Servers on SAP Integration Suite : Build Your First MCP Server from an APIMCP Servers on SAP Integration Suite : Build Your First MCP Server from an APIWalks through building an MCP server on SAP Integration Suite from an existing managed API — SAP S/4HANA's Purchase Order API — rather than from an HTTP endpoint or an RFC, which the same creation wizard supports but a later post in the series is left to cover. Selected API operations become MCP Tools with generated input and output schemas, the server inherits its Authentication policy from the source API, and a Process Integration Runtime service instance supplies the OAuth credentials an external client needs to invoke it. Ends by connecting the deployed server to Cline in VS Code and having it chain tool calls to answer a natural-language purchase-order query.published 2026-07-15
Messaging System for Transferring Error, Warning, and Information Messages from OData V4 Services to HTTP Client ApplicationsMessaging System for Transferring Error, Warning, and Information Messages from OData V4 Services to HTTP Client ApplicationsGetting a message out of a CAP service and onto a Fiori elements object page in a draft scenario — errors, warnings and information, each of which the UI treats differently. Co-written with one of the people on the OData side, and it spends its length on the message container rather than on the handler that fills it.arley-triana-morin, published 2022-08-11
Messaging System for Transferring Error, Warning, and Information Messages from OData V4 Services to HTTP Client Applications
OData changed in @cap-js-community/odata-v2-adapter 1.10.0, 2023-04-05. Affects A recipe, Runnable code.
Michael Jackson: AI Cognitive Pipeline on SAP BTP, SAP CAP, ElevenLabs, Claude, HANA DB, SolaceMichael Jackson: AI Cognitive Pipeline on SAP BTP, SAP CAP, ElevenLabs, Claude, HANA DB, SolaceA pipeline that listens to a song, identifies the historical events it references, retrieves knowledge about each and builds an emotional arc across the whole track. Not an enterprise use case, and useful precisely for that: the plumbing — CAP, HANA, Solace, Claude, ElevenLabs — is doing something the vendor demos never ask of it.Shahid, published 2026-05-18
Migration Journey from MuleSoft to SAP Integration Suite (CI)Migration Journey from MuleSoft to SAP Integration Suite (CI)Maps MuleSoft Anypoint's error handling onto SAP Integration Suite: the Global Error Handler and MuleSoft's built-in retries become Exception Subprocesses with scripted Groovy retry logic or JMS-based retry, since Cloud Integration has no automatic equivalent. MuleSoft's searchable logger text becomes Content Modifier headers and Groovy-scripted Message Log entries, correlated by application message ID and correlation ID for traceability across complex interfaces. The mapping is drawn from the author's own migration project across assessment, development and validation phases, and is explicitly flagged as not an SAP- or MuleSoft-approved design.Shailaja, published 2025-09-21
Moving from Hub Gateway to Direct S/4HANA OData V4: A Customized Reusable RAP Processing FrameworkMoving from Hub Gateway to Direct S/4HANA OData V4: A Customized Reusable RAP Processing FrameworkA generic base class for RAP custom-entity query providers — one implementation of IF_RAP_QUERY_PROVIDER~SELECT, subclassed per entity — lets a service expose OData V4 directly from S/4HANA instead of through a separate Gateway Hub. The framework loads entity configuration, extracts the request context, fetches and transforms backend data into the target entity shape, and returns it through the RAP response object, with field mapping and conversion exits left for each subclass to fill in.AnslemArnolda, published 2026-04-07
Multi-modal RAG Proof of Concept: facilitating tech supportMulti-modal RAG Proof of Concept: facilitating tech supportA report on a customer proof of concept rather than an implementation guide — there is no code in it. The reason it is here is the architecture paragraph: CAP holds the backend and the use-case logic, the LLM plugins and the SAP Cloud SDK for AI sit inside it, and gpt-4o is one of two nodes in a small langgraph. It opens with a disclaimer that SAP's own Grounding service is due to gain multi-modal features, which dates the whole thing on purpose.maxlienhardt, published 2025-06-03
Natural Language Queries for SAP CAP via MCP: The LLM Translates, CDS ExecutesNatural Language Queries for SAP CAP via MCP: The LLM Translates, CDS ExecutesThe division of labour is the argument, and it is in the subtitle: the model turns English into a CDS query and CDS runs it, so nothing generates SQL and nothing hallucinates a join. Schema annotations do the resolving. Long, with the package, the repository and the MCP registry entry all linked.Shahid, published 2026-06-25
New SAP Cloud Application Programming Model Sample for Many-to-Many Relationships and Fiori AnnotationsNew SAP Cloud Application Programming Model Sample for Many-to-Many Relationships and Fiori AnnotationsIntroduces SAP-samples/cloud-cap-hana-swapi, a CAP sample rebuilding the abandoned Star Wars API as a six-entity data model (Films, People, Planets, Species, Starships, Vehicles) chosen for its many-to-many, bi-directional relationships and its use as a Fiori Draft deep-editing test case. The author used CAP's OpenAPI functionality to generate both the Swagger UI test tool and entity diagrams for the data model, alongside the OData services and Fiori preview UI.published 2020-12-21
New tutorial for UI5 Middleware FE MockserverNew tutorial for UI5 Middleware FE MockserverA step-by-step tutorial accompanying a Devtoberfest session walks through @sap-ux/ui5-middleware-fe-mockserver across nine exercises: zero-config mock data generated from OData metadata, custom JSON datasets with consistent IDs and referential keys, JavaScript actions, multi-service and cross-service scenarios, tenant isolation through sap-client, returning 400/404/422/500/501 responses for UI error-handling tests, and offline end-to-end tests run with wdi5. A companion tool, ui5-middleware-odata-recorder, captures real backend OData traffic to generate the mock datasets used for offline replay.published 2025-10-14
No-Code MCP Servers with SAP Integration Suite: From REST API to AI AgentNo-Code MCP Servers with SAP Integration Suite: From REST API to AI AgentWalks through turning a deployed API artifact into a no-code MCP server in SAP Integration Suite's MCP Gateway: the API artifact's OpenAPI spec must be version 3.0.0-3.0.3, since Swagger 2.0 is rejected, and its backend is reached through a BTP Destination using OAuth2ClientCredentials so the agent calling the server never sees the backend secret. The API artifact's own Authorization policy sets an OAuth scope and Trust Upstream MCP Authorization, and the gotcha list traces a 403 on a valid token to that policy rather than to authentication, before the finished MCP server is published through Developer Hub and connected to Claude Code.eddiedu, published 2026-09-15
OData $batch Deleting Records Across Multiple Tables in Single TransactionOData $batch Deleting Records Across Multiple Tables in Single TransactionWalks through implementing a multi-table DELETE inside a single OData v2 $batch changeset on SAP Gateway: setting cv_defer_mode = abap_true in CHANGESET_BEGIN so more than one delete is collected per change set instead of being executed immediately, looping the collected operations in CHANGESET_PROCESS to delete from each backend table in turn, and issuing one COMMIT WORK in CHANGESET_END so all tables commit or roll back together. The example is a supplier master spread across basic, address, identification and purchasing-organisation tables, deleted as one logical unit of work instead of one HTTP call per table.Abhi_0118, published 2026-04-17
OData Deep Insert: Implementation and Real-Life ExamplesOData Deep Insert: Implementation and Real-Life ExamplesWalks through implementing OData Deep Insert on classic SAP Gateway: two entity types joined by an association in SEGW, and a redefined CREATE_DEEP_ENTITY method in the DPC_EXT class that unpacks the header and item payload and calls BAPI_SALESORDER_CREATEFROMDAT2 to create a sales order with its line items in one request instead of separate calls per item. Gives a sample JSON payload to test with Postman or /IWFND/GW_CLIENT and names the usual failure points — an unmapped association, a method that was never redefined, or a commit left out after the BAPI call.SRSATAPATHY, published 2025-09-15
OpenAPIs in the SAP ecosystemOpenAPIs in the SAP ecosystemWhere OpenAPI actually turns up across SAP's own services, from somebody who spends their time in that ecosystem. Orientation rather than implementation.ajmaradiaga, published 2022-10-10
Out-of-the-Box Document Grounding in SAP AI Core: RAG with SAP Help PortalOut-of-the-Box Document Grounding in SAP AI Core: RAG with SAP Help PortalWalks through SAP AI Core's document grounding: a default 'help.sap.com' data repository that is already grounded, queried either directly through /retrieval/search after labelling a resource group for grounding, or through the orchestration service's grounding_module_config paired with llm_module_config and templating_module_config to inject the retrieved chunks into a prompt. Shows the orchestration service as a unified interface for swapping LLM providers by changing a configuration parameter rather than application code.Joni, published 2025-04-15
Outbound Integration from SAP BTP, ABAP to SAP S/4HANA Cloud via Service Consumption ModelOutbound Integration from SAP BTP, ABAP to SAP S/4HANA Cloud via Service Consumption ModelWalks through ABAP's Service Consumption Model for OData in ABAP Development Tools for Eclipse: generating a V4 client proxy from a remote service's EDMX metadata, then calling one of its bound actions by hand because the 2311 release's ADT tooling does not yet generate that code. The client itself is built the way HTTP clients describes for SAP BTP, ABAP Environment — a communication arrangement resolved through cl_http_destination_provider=>create_by_comm_arrangement, handed to cl_web_http_client_manager=>create_by_http_destination to create the client.Pramathesh_t_s, published 2025-10-28
Parallel Data Filtering and Dropbox Integration Using SAP Cloud IntegrationParallel Data Filtering and Dropbox Integration Using SAP Cloud IntegrationA step-by-step build of an integration flow in Cloud Integration: a Start Timer triggers the flow, a Parallel Multicast splits student records by gender through XPath filters, and each branch uploads its file to Dropbox over a Receiver Adapter authorized against a Dropbox app's OAuth2 credentials. An Exception Subprocess captures the error message and a Mail Adapter sends it over SMTP, centralizing error handling and an email notification for the whole flow.Vurumind03, published 2025-12-10
Part 2 – Empowering SAP BTP CAP Services through Open API Spec and Annotations for Effective Communication, Collaboration and GovernancePart 2 – Empowering SAP BTP CAP Services through Open API Spec and Annotations for Effective Communication, Collaboration and GovernanceWalks through generating an OpenAPI specification for a Node.js CAP service: installing cds-swagger-ui-express, bootstrapping it in server.js, a sample CDS data model with associations and compositions, and the YUML diagram and endpoint details the Open API Preview renders in Business Application Studio. Also shows gating the Swagger UI behind a user-defined environment variable so it is served in development and QA subaccounts but excluded from the production deployment on Cloud Foundry. Second of a three-part series; the first covers the concepts and the third goes deeper into annotations.mohit_bansal3, published 2023-05-24
Part 3 – Empowering SAP BTP CAP Services through Open API Spec and Annotations for Effective Communication, Collaboration and GovernancePart 3 – Empowering SAP BTP CAP Services through Open API Spec and Annotations for Effective Communication, Collaboration and GovernanceThe closing part of a three-post series applies OData @Capabilities annotations — TopSupported, SkipSupported, CountRestrictions, UpdateRestrictions, DeleteRestrictions, FilterRestrictions, SelectSupport, SortRestrictions, SearchRestrictions, InsertRestrictions, ReadRestrictions and NavigationRestrictions — to three sample CDS entities (Purchase Order, Business Partner, Product) and shows the generated OpenAPI document changing with each one. The point it builds toward: the spec is a direct readout of the model and its annotations, not something edited by hand afterward.mohit_bansal3, published 2023-05-24
Prompt-Driven Development: Building Full-Stack SAP CAP Apps from User StoriesPrompt-Driven Development: Building Full-Stack SAP CAP Apps from User StoriesA user story in, a scaffolded full-stack CAP application out, through SAP Build Code and Joule. The question it is actually asking is how much of the foundational code is worth generating, and it answers by generating all of it.AnuradhaDhingan, published 2025-12-11
RAG with SAP HANA Cloud Vector Engine, GenAI Hub & CAPRAG with SAP HANA Cloud Vector Engine, GenAI Hub & CAPThe end-to-end version: a CAP service exposing the vector engine and the AI hub behind a couple of endpoints, answering where a CodeJam is on a given date. It has aged in a way the author has marked in the page itself — the section on the CAP LLM plugin now carries "(Outdated)" in its own heading — so read the embedding preparation and the retrieval shape, and check the plugin part against the package.KevinR, published 2024-05-21
Reading Between the Lines: Under-Documented Fiori Elements Capabilities in SAPUI5 1.149Reading Between the Lines: Under-Documented Fiori Elements Capabilities in SAPUI5 1.149Reads SAPUI5 1.149's framework source, not its release notes, to show Fiori Elements shifting side-effect refresh, AI field placeholders and multi-user drafting from controller extensions into what the backing service annotates. Event-driven SideEffects push over a WebSocket channel through @cap-js-community/websocket, while Draft handling gains ABAP RAP's live field locking on CAP Node.js through Sören Leibach's own cap-collaborative-draft plugin. Both rest on Fiori annotations such as Common.SideEffects and CollaborativeDraft.enabled, which the frontend reads rather than requiring a manifest flag.published 2026-07-09
Real-Time Architecture in SAP CAP: Mastering Asynchronous Jobs, Gateways with WebSocketsReal-Time Architecture in SAP CAP: Mastering Asynchronous Jobs, Gateways with WebSocketsThe other half of the author's own industrial-data post: mass ingestion is only useful if the screen keeps up, so background jobs push progress to the UI over WebSockets instead of the user reloading. Written from a mission-critical case rather than a demo.rgadirov, published 2026-03-12
Real-Time Architecture in SAP CAP: Mastering Asynchronous Jobs, Gateways with WebSockets
Async processing changed in @sap/cds 10.0, 2026-07-02. Affects A recipe.
Resolving date serialization issues when using an external OData v2 service with CAPResolving date serialization issues when using an external OData v2 service with CAPDates coming out of an external OData v2 service in a shape CAP does not expect, and what to do about it. A narrow bug report with a fix, and the kind of thing that costs an afternoon if nobody has written it down.pieterjanssens, published 2020-07-09
RFC/BAPIs Meet AI Agents: Why SAP Integration Suite MCP Server MattersRFC/BAPIs Meet AI Agents: Why SAP Integration Suite MCP Server MattersExplains that SAP Integration Suite's MCP Server artifact can expose RFC-enabled BAPIs, alongside API artifacts and HTTP endpoints, as MCP tools — letting BAPIs on SAP ECC or on-premise S/4HANA participate in agentic workflows without rewriting business logic or waiting for a full ERP transformation. Frames RFC support as a bridge for organisations still modernising rather than a recommendation to build new RFC-based integrations, and notes the exposed BAPIs inherit the server's existing authentication, rate limiting and IP filtering. A demo built against an SAP ECC backend shows an MCP client discovering and invoking several read-only BAPIs from natural-language prompts, with no custom wrapper code.arunmaarirajha_kv, published 2026-07-28
Running AI agents against SAP ECC 6.0: lessons from building an in-system MCP serverRunning AI agents against SAP ECC 6.0: lessons from building an in-system MCP serverNicolasHernandez recounts building and running, over two years, an MCP server written in plain ABAP behind a single ICF node, for SAP ECC 6.0 and S/4HANA on-premise customers that the ADT MCP Server and SAP Joule for Developers, ABAP AI capabilities do not reach. Authorization runs as the calling user rather than a technical RFC user, a choice forced by a customer security team after an earlier version used a technical RFC user, and a later security review found a display-authority check applied uniformly across every write endpoint. The failure modes that cost the most time sat in RFC connectivity itself: RFC_READ_TABLE's empty-table exception collapsed into a false success, a where-used filter was applied only after the row limit, and BAPI calls treated an empty string and an absent parameter as different, silently wrong inputs.NicolasHernandez, published 2026-08-28