Agentic Engineering Workshop
Master AI coding agents. Three days that change how your team builds software.
Request a WorkshopWorkshop at a Glance
An intensive, hands-on format designed for engineering teams.
- Days
- 3
- Focused, immersive format
- Participants
- 6-7
- Small group, maximum attention
- Lab-to-Theory
- 2:1
- Learn by doing, not by listening
- Day 1 SEEING See What the Agent Sees
- Day 2 SHAPING Shape the Context
- Day 3 SHIPPING Ship What You Trust
What You'll Learn
Six skills that separate agentic engineers from prompt users.
- 01
Read Agent Behavior
Detect drift, hallucination, and context decay before they compound into trust debt. Map capability ceilings before you delegate.
- 02
Write Effective Plans
Create specifications for short-horizon and long-horizon tasks — with constraints, checkpoints, and definitions of done.
- 03
Validate Systematically
Apply a six-layer validation framework that goes beyond "it compiles and tests pass" — including automated trust thresholds.
- 04
Intervene at the Right Moment
Know when to let the agent run, when to redirect, and when to stop — the skill that prevents wasted cycles.
- 05
Manage Agent Fleets
Decompose work across multiple agents using Git worktrees. Spawn, supervise, and reap — fleet management, not one-shot tools.
- 06
Build Corporate-Ready Workflows
Agent instruction files as team infrastructure (works for Claude Code and GitHub Copilot), MCP integration, agent credential security, scheduled and event-triggered automation, and the autonomy progression.
The Three Days
A progressive curriculum that builds skill upon skill.
You Can't Control What You Can't Read
- Model, harness, context — the three-layer vocabulary for understanding agents
- Capability ceilings — knowing what agents can and cannot do before you delegate
- Context engineering — why agents forget, hallucinate, and drift
- Your first plan — writing specifications agents can follow
Shape the Context, Shape the Output
- Planning checkpoints — structured workflows for short-horizon and long-horizon tasks, across Claude Code, GitHub Copilot, and any planning-capable agent
- Drift detection — catching silent violations before they compound
- Filesystem as context — persistent knowledge beyond vector search
- Intervention techniques — when to redirect vs. restart vs. let it run
Ship Fast, Ship True
- Validation framework — six layers, capability ceilings, and automated trust thresholds
- Fleet management — decomposition patterns, parallel agents, and Git worktree isolation
- MCP, agent security, and routines — protocol integration, credential risks, and where agents live outside the terminal
- Capstone project — full synthesis of every skill under time pressure
Pricing
Bring the workshop to your team. On-site in Switzerland or remote.
Per Participant
- 3 days of intensive, hands-on training
- Committable agent instruction file tailored to your codebase (Claude Code and GitHub Copilot formats)
- 30-day practice guide with weekly milestones
- Six-layer validation checklist for every PR
Team Package
- Everything in Per Participant
- Dedicated workshop for your team only
- Customizable to your tech stack and codebase
- Save up to 17% with a full team
For Your Engineering Team
AI coding agents promise velocity. Without the right skills, they deliver trust debt — code that looks correct but fails under pressure, accumulating invisible cost that your most senior engineers pay later.
This workshop teaches the supervision skills that make agent-assisted development sustainable: reading agent behavior, writing plans agents can follow, validating output systematically, and building the verification infrastructure that lets your team scale with confidence.
Participants leave with an agent instruction file they can commit on Monday (CLAUDE.md for Claude Code, .github/copilot-instructions.md for GitHub Copilot), a validation checklist for every PR, and a 30-day practice guide that turns workshop skills into daily habits.
Request a Workshop
Tell us about your team and we'll get back to you within two business days.
Submitting this form opens your email client. You can also write to us directly at [email protected]