MODULE 7 · DAY 2
The Multi-Agent Incident Crew
One agent grows into a crew of four — sharing one model
Gourav Shah · School of DevOps & AI · Hands-on
M7·01
What you'll learn
Why a crew, when a single agent is enough, and the two ways to build one.
The orchestrator changes — the skills, MCP tools, and model stay exactly the same.
M7·02
One agent doing everything gets unfocused
Cram triage, retrieval, fixing and safety into one prompt and the roles blur.
A 1.5B laptop model handles four tight tasks reliably — but not one giant task blindly.
M7·03
A hospital, not a superhero
No single doctor greets you, diagnoses, prescribes, and countersigns their own order.
Four staff share one health record; four agents share one model endpoint.
M7·04
Three things a single agent can't replicate
The properties that earn the extra prompts and latency.
Specialisation, separation of concerns, and a review loop — especially for consequential actions.
M7·05
When is a single agent enough?
Multi-agent adds real overhead. Don't reach for it by default.
The M6 single agent is the right tool until an action needs a countersign.
M7·06
The Incident Crew pipeline
A sequential pipeline with a relevance gate that can short-circuit.
The gate asks one yes/no question so a catastrophically wrong fix never reaches the output.
M7·07
Two paths to multi-agent
Declarative profiles by default; a framework when you need more control.
Reach for a framework when you need deterministic, auditable control over a complex workflow.
M7·08
Swap the orchestrator, not the tools
Skills, MCP tools, and guardrails are the same layer underneath every crew.
Build against the standard, swap the implementation — the same lesson as the OpenAI-compatible endpoint.
M7·09
One model, four agents
Agents are cheap Python calls. The model is the expensive part — and it's shared.
Four separate model instances would cost 4× the memory for zero gain — all four call one endpoint.
M7·10
Wire the crew with the Compose Spec
Each agent a lightweight service, all sharing one endpoint, tools, and memory.
One growing compose file gains a crew service — reusing the tools and memory you already built.
M7·11
The Reviewer — human-in-the-loop proxy
It doesn't decide whether to fix; it decides whether the fix is safe to show a human.
The crew produces a vetted recommendation; the human engineer retains final authority.
M7·12
TO THE LAB
Swap the orchestrator, keep the crew
Read the four profiles, run both incidents, watch the relevance gate work.
Then Module 8 — harden & ship. · Gourav Shah · School of DevOps & AI
M7·13