Trainings

Duration

2 days

Who it's for

• Whole DevOps teams: developers, QA / test engineers, ops / platform
• Mixed-role cohorts adopting agentic workflows together
• Engineering managers training their teams alongside them

Prerequisites

• Comfortable with git and the command line
• Writes features in at least one language (TS/Python/Go/etc.)
• Own laptop or desktop with Claude Code or OpenCode installed, plus at least an active Claude Pro subscription

What you'll learn

• Ship a working feature on a starter repo — tests, hooks, CI green from minute one
• Recognise the failure modes of AI-generated code in your own work
• Practise test-first with an agent without writing fake-passing tests
• Set up hooks and quality gates that survive the next sprint
• Use existing MCP servers in real workflows
• Leave with a governance starter your team can actually use

Price

€349 ex. VAT

Programme

Day 1 Quality engineering with agents

1. 01

   Agents in your SDLC: where they fit, where they break

   • Where an agent earns its place in the SDLC, and where it doesn't
   • What an agent actually is vs. chat vs. automation
   • Quality stakes: every agent change is a code change that ships
2. 02

   Failure modes of AI-generated code

   • Hallucination, silent regression, false-green builds
   • Scope drift and undeclared rewrites
   • How to spot each before they ship
3. 03

   Test-first with agents

   • The TDD loop with an agent driver
   • When tests precede code, when they don't, why it matters
   • Tests that prove behaviour vs. tests that satisfy the model
4. 04

   Hooks + quality gates

   • Pre-commit checks: lint, format, type-check
   • Custom hooks for agent-specific risks
   • Fast feedback loops that don't get bypassed
5. 05

   Lab: build your first feature with quality discipline

   • End-to-end on a starter repo: brief → tests → code → review
   • Run today's quality stack against your own changes
   • Cohort feedback before Day 2
6. 06

   Regression strategy + governance basics

   • Golden tests, snapshot guards, property-based checks, mutation testing, etc.
   • Stress-testing agent output on real edges
   • What a sensible team review policy looks like

Day 2 Agent mechanics + capstone

1. 07

   Context architecture

   • CLAUDE.md / AGENTS.md design
   • Rules files and project-wide configuration
   • Hierarchy: user, project, local overrides
2. 08

   Context window mechanics

   • Compression and summaries
   • Priming and recency bias
   • Strategies for long sessions
3. 09

   Using MCP servers

   • MCP overview
   • Connect existing servers (Filesystem, GitHub, Linear, etc.)
   • Scope and permission best practices
4. 10

   Intro to Skills & Rules

   • When to write a skill
   • When to write a rule
   • Your first own skill
5. 11

   Ship a feature end-to-end

   • Implement a feature on a starter repo from a brief
   • Apply Day-1 quality stack + Day-2 context tooling (MCP, skills, rules)
   • Demo and review with the cohort