Module 10: Build Your Domain Agent
Duration: 120 minutes Day: Day 3, Session 4
The hands-on lab for this module lives in the Hermes repository. This is the primary build module of Day 3 — everything from Modules 7, 8, and 9 converges here into a working agent. Read the Concepts page first, choose your track, then open the Hermes lab guide.
What This Module Is About
This is where you stop learning about agents and start building one. Everything converges: your SKILL.md from Module 7, your tool configuration from Module 8, the design patterns from Module 9, and your impact assessment from Module 4.
The output is a working domain agent — deployed on Hermes, connected to real or simulated infrastructure, capable of executing your operational runbooks autonomously.
Choose Your Track
| Track | Domain | Key Skills | Infrastructure |
|---|---|---|---|
| Track A: DB Health and Tuning | RDS PostgreSQL | Slow query analysis, parameter tuning, connection pool monitoring | Real or simulated RDS (mock data provided) |
| Track B: Cost Anomaly and FinOps | AWS Cost Explorer | Cost trend analysis, right-sizing, unused resource detection | Real or simulated Cost Explorer (mock data provided) |
| Track C: Kubernetes Health | (Consolidated into Module 8) | (See note below) | (See note below) |
Tracks A and B produce the same type of artifact: a complete Hermes agent profile (SOUL.md + config.yaml + skills/) with simulated data for testing when real infrastructure is not available.
Track C: Testing Consolidated into Module 8
Track C learners: Your testing lab has been consolidated into the Module 8 "Build and Test Your Kubernetes Agent" lab. That 90-minute lab combines tool wiring (formerly Module 8) with agent testing (formerly Module 10), eliminating redundant setup and giving you an immediate feedback loop: configure, test against clean cluster, inject failures, evaluate diagnostics — all in one session.
This module (Module 10) is for Tracks A and B only. Track C learners should proceed directly to Module 12: Fleet Workflows.
If you completed your Module 4 impact assessment — choose the track closest to your capstone candidate (Track A or B for this module). You will extend this agent in Module 13 for your capstone.
Learning Objectives
By the end of this module, you will be able to:
- Build a complete domain agent from scratch by combining skills, tools, and configuration into a working Hermes profile
- Test against simulated infrastructure data using the provided mock datasets when real infrastructure is not available
- Evaluate agent output quality using a structured checklist: accuracy, completeness, confidence calibration, and actionability
- Identify what your agent cannot reliably do — the boundary conditions where it needs human judgment rather than autonomous action
Prerequisites
- Modules 7 and 8 completed (you have a SKILL.md and understand tool configuration)
- Module 9 completed (you understand design patterns)
- Hermes installed and running
- Track C: Not applicable — Track C testing is now part of Module 8 consolidated lab
Module Contents
| Section | Content | Time |
|---|---|---|
| Reading | Concepts: Agent Anatomy and Build Strategy | 20 min |
| Reading | Reference: Agent Profile Structure and Output Evaluation | 10 min |
| Lab | Build Your Domain Agent — Track A or B (Hermes repo). Track C: see Module 8 | 80 min |
| Quiz | Module 10 Assessment | 10 min |
| Exploratory | Stretch Projects | Optional |
What "Done" Looks Like
At the end of the lab, your agent can receive a task like "Investigate the connection pool saturation on our RDS instance" and:
- Load the relevant skill automatically based on the trigger
- Execute the diagnostic procedure against real or simulated data
- Reason about the evidence using the decision trees in the skill
- Generate a structured diagnosis with root cause hypothesis, supporting evidence, recommended actions, and escalation decision
That is a working domain agent. It will not be perfect — and the concepts reading covers what "good enough" means and how to improve from here.