All lessons
Agentic AI

Grounding an agent on a knowledge graph

Vector search finds similar text; a graph encodes relationships. Agents that reason about your business need both, and this is how you wire them up.

SCIKIQSCIKIQ Academy05 Jul 2026 · 6 min read

An agent that only does similarity search can answer “what does our refund policy say?” but not “which customers are exposed to the delayed supplier?” The second is a relationship question — it needs a graph.

Grounding an agent on a knowledge graph gives it structured context: entities, their attributes, and the edges between them. The agent can traverse from a supplier to affected products to the customers who ordered them, and cite every hop. Expose that graph as a tool over the Model Context Protocol and any compliant agent can use it under your access controls.

The result is an agent whose answers are explainable and auditable — because they are grounded in governed relationships, not statistical guesses.

Read the full Agentic AI track →

More Agentic AI lessons

Data Integration

Automating Schema Drift Handling in Data Integration Processes

Source schemas change without warning. Learn the patterns that let pipelines absorb new, renamed and dropped columns instead of breaking overnight.

16 Jul 20266 min read
Data Governance

Writing your first data contract

A data contract turns an implicit handshake between producer and consumer into something your pipeline can enforce automatically, before data breaks.

12 Jul 20265 min read
Semantic Modelling

From star schema to a governed metric

Your dimensional model is the physical truth; the metric layer is the shared meaning on top of it. Here is how to get cleanly from one to the other.

10 Jul 20266 min read