Thinking in Agents — 2-Day Deep Dive

Principles, practice, and adoption — with time to go deep

Everything from the 1-day workshop, but with room to breathe. Day one builds the mental models and gets everyone hands-on. Day two goes deep: orchestration patterns, enterprise adoption, and extended practice at your own codebase. Your team doesn't just learn the principles — they internalize them.

5–20 Teilnehmer~~März~~ ~~April~~ — Nächster freier Termin: Mai

Who it's for

Engineering teams that want real depth — not a surface-level overview, but the full system behind agent workflows.

Organizations rolling out agents across multiple teams and need a shared foundation of principles and methods.

Mixed groups of engineers, leads, and decision makers who need both the technical understanding and the strategic framework.

Why 2 days

Depth over speed. The 1-day format covers all the principles. Two days give your team time to actually apply them — iterate on real workflows, hit real problems, and solve them with support.

Overnight effect. Day one plants the mental models. Overnight, questions surface. Day two answers them at the right moment.

Full coverage. All 9 modules with extended hands-on sessions, live orchestration exercises, and enterprise adoption strategy.

Two days, nine modules

Day 1 — Foundations & first workflows

01
The Shift — Vibe coding vs. agentic engineering
Spectrum: autocomplete to orchestrator. Taste over syntax. Live demo: same task, different approach.
02
How Agents Work — LLMs, tool calls, agent loop
Context windows & failure modes. Agent loop: think, act, observe, repeat. Token economics & model tiers.
03
Hands-on — First workflows at your own code
Harness setup & model selection. Project instructions via CLAUDE.md. Trust boundaries & intervention points.
04
Harness Engineering — Configure and extend your agent runtime
Skills as reusable workflows. CLI tools as agent interfaces. Custom commands & automation layers.
05
Back Pressure — Tests, CI and quality gates
Tests as first-line defense. CI as organizational back pressure. The trust equation for agent autonomy.

Day 2 — Depth, orchestration & adoption

06
Taste & Architecture — The core skills when agents write most code
Code review as primary skill. System design decisions. Context management at task level.
07
Agent Orchestration — Scale from one agent to many
Parallel agents & task splitting. MCP servers. Live orchestration exercise.
08
Enterprise Reality — Adoption in real companies
Data policies & guardrails. What to adopt first. Agentic readiness scoring. Building the leadership case.
09
Extended Practice — Build, break, iterate
Extended hands-on session at your own repos. Real workflow challenges. Group review & feedback.

Content customizable on request. Full curriculum →

What your team takes away

Working workflows. Everyone leaves with agent workflows running on their own repos — tested and iterated over two days.

Shared mental models. The whole team speaks the same language: agent loops, context management, delegation patterns, back pressure.

Adoption roadmap. A concrete plan for rolling out agent workflows across your organization — with guardrails and priorities.

Investment

Format 2 days, in-person

Offer on request

Group size 4-20 people

Region DACH (in-person), remote on request

Language German or English

In-house in DACH, including preparation and follow-up. Travel costs as incurred.

Get in touch

Pick a date. I'll tailor the content to your stack and goals.

email x linkedin

← back to workshops