MODULE 6 · DAY 2
The Declarative Agent
Agentic RAG, an agent you write down, not code up.
Gourav Shah · Containers for GenAI & Agentic AI · School of DevOps & AI
M6·01
What you'll learn
Write an agent, not just call a model.
M6·02
1 · From a docs assistant to an agent
M6·03
Naive RAG is passive, it always retrieves
Every question takes the same road.
M6·04
2 · The analogy: a job description and a rulebook
M6·05
Onboard an engineer, don't script a robot
You hand a new hire three documents, not a flowchart.
M6·06
Declarative Markdown vs a hand-coded robot
Edit a Markdown file, don't touch the code.
M6·07
3 · The three files that define Aria
M6·08
The anatomy of a 2026 agent
Five parts, one thin glue script.
M6·09
4 · Agentic RAG versus naive RAG
M6·10
Agentic RAG, decide first, then act
Does this need the runbooks? Decide first.
M6·11
A 1.5B model can route reliably
Two classes, temperature 0, simple for a small model.
M6·12
5 · MCP tools via ToolHive
M6·13
Real tools through an MCP gateway
ToolHive is the hub, each server its own spoke.
M6·14
Each tool server in its own sandbox
thv run fetch starts proxy and DNS containers too.
M6·15
Guardrails refuse before the model runs
A hard regex gate, not a soft prompt plea.
M6·17
Memory, a librarian who shelves by meaning
Aria's memory, reused unchanged from Module 5.
M6·19
8 · Declarative versus framework
M6·20
The whole agent ships in a container
Markdown, skills, and MCP config in one image.
M6·21
TO THE LAB
The agent IS Markdown + skills + tools
Read the three files, run Aria, wire in a tool.
Next: Module 6 Lab, then M7 — the crew. · Gourav Shah · School of DevOps & AI
M6·22