BlogBlogtypeA post on somebody's own site or a community platform. Nobody edits it after publication, so it dates from the day it was written.See every one →SAP Community

Data Is More Than a Constant for the AI Engineer

Walks through SAP HANA Cloud's in-memory, multi-model engine as the data layer an agentic AI system depends on, with a worked SQL example that joins relational sales-office rows, a logistics graph table, spatial coordinates and a JSON configuration field in one query. A second script adds vector similarity against a stored REAL_VECTOR embedding and a z-score band over a KPI to flag offices resembling a known risk profile, run end to end against sample data. The claim running through both is that an agent's reliability depends on this combined data layer, not on the LLM alone.

Where it sits

Explains
Graph, spatial and document dataBTPGraph, spatial and document datacapabilityStoring and querying data that is not plain rows, such as a network of relationships, a geometry or a JSON document, in the database that already holds the rows instead of in a separate store per model. Free-text search over entities is [search](capability:search); similarity over embeddings is [retrieval-augmented generation](capability:retrieval-augmented-generation).SAP HANA CloudCAPBTPSAP HANA CloudserviceThe managed database under most of this: CAP's default target, the store Datasphere and Analytics Cloud sit on, and a service with plans and components.

Who is behind it

Daniel_Dukesauthor

Properties

About this work

declared and crawled
Published
declared
Published on
declared

More on this28

Group by28 of 28 pieces
Piece, what it offersStill applies
CAP in the age of AI #7 - vector embeddings wrap-up
YouTube — SAP Developers playlists, DJ Adams, Johannes Vogt, part 7 of 7
nothing recorded
CAP in the age of AI #6 - vector embeddings
YouTube — SAP Developers playlists, DJ Adams, Johannes Vogt, Daniel Schlachter, part 6 of 7
nothing recorded
SAP BDC in Business AI Platform: Contextualize and Reason
YouTube — SAP Developers playlists, SAP
nothing recorded
Bring "developers.sap.com" Into Your Dev Environment: SAP Developer Context for AI Coding Agents
YouTube — SAP Developers playlists, SAP
nothing recorded
Building your knowledge graph on SAP HANA Cloud
YouTube — SAP Developers playlists, SAP
nothing recorded
Combining AI Agents with the power of SAP HANA embedded ML (part 1)
YouTube — SAP Developers playlists, Vitaliy Rudnytskiy
nothing recorded
Building an SAP BTP Agent Architecture from Scratch: Python + CAP + HANA
SAP Community, neilaspin
nothing recorded
Automate Recurring Data Updates in SAP HANA Cloud
SAP Community, Joni
nothing recorded
Accelerating Your Analytics with Delta Table Replication into SAP HANA Cloud
SAP Community, SeungjoonLee
nothing recorded
Medallion Reference Architecture for Big Data Processing in SAP HANA Cloud
SAP Architecture Center, SAP Architecture CenterThe reasoningA reference
nothing recorded
SAP HANA Cloud as an Esri Geodatabase
SAP Architecture Center, SAP Architecture CenterThe reasoningA reference
nothing recorded
Unlock predictive and generative AI with your data in SAP HANA Cloud
SAP TechEd — session catalogueThe reasoning
nothing recorded
Agentic memory: Knowledge graph engine and recall in SAP HANA Cloud
SAP TechEd — session catalogue, Markus FathThe reasoning
nothing recorded
Knowledge graph and agent memory: Build an agent that remembers
SAP TechEd — session catalogue, Markus Fath, Thomas HammerA recipe
nothing recorded
Build your custom knowledge layer with SAP HANA Cloud
SAP TechEd — session catalogue, Sebastian SchmidtThe reasoning
nothing recorded
SAP HANA Data Lake Files (HDLF) Basic Functionalities
YouTube — SAP Developers playlists, SAP
nothing recorded
Talking to your database: The new data exploration tools in SAP HANA Cloud
SAP TechEd — session catalogueThe reasoning
nothing recorded
Stop guessing, start counting: How generative AI fixed an inventory mess
SAP TechEd — session catalogueThe reasoning
nothing recorded
SAP HANA Cloud as a self-managed database: Advisors and automation
SAP TechEd — session catalogueThe reasoning
nothing recorded
Build AI agents and applications natively on SAP HANA Cloud
SAP TechEd — session catalogueThe reasoning
nothing recorded
Modernize your database landscape with SAP HANA Cloud
SAP TechEd — session catalogueThe reasoning
nothing recorded
SAP HANA Cloud advisors and automation
SAP TechEd — session catalogueThe reasoning
nothing recorded
Building agentic applications with SAP HANA Cloud
SAP TechEd — session catalogueA recipe
nothing recorded
Get hands on with tabular AI and forecasting models in SAP HANA Cloud
SAP TechEd — session catalogue, Markus FathA recipe
nothing recorded
Flexible analytics at speed: Calculation views in SAP Business Data Cloud
SAP TechEd — session catalogue, Thomas HammerThe reasoning
nothing recorded
Road map for SAP HANA Cloud: What’s next for the AI database
SAP TechEd — session catalogue, Thomas HammerThe reasoning
nothing recorded
SAP HANA Cloud: The data foundation for contextualizing and reasoning
SAP TechEd — session catalogueThe reasoning
nothing recorded
SAP HANA Cloud as the AI database for SAP Business Data Cloud
SAP TechEd — session catalogue, Thomas HammerThe reasoning
nothing recorded

Details

Graph4 edges
POINTS OUT →
explainsGraph, spatial and document datacapability, core only
explainsSAP HANA Cloudartifact
published onSAP Communitypublishing source
discovered viaSAP Communityagentic-ai-tag
Source
Type
blog
Published on
Host
community.sap.com
First seen
History1
  • Entered the atlasDiscovered via SAP Community · agentic-ai-tag.
For your agent
Ref
content:data-is-more-than-a-constant-for-the-ai-engineer-2
JSON
/content/data-is-more-than-a-constant-for-the-ai-engineer-2.json
MCP
Connecting an agent