Skip to main content

Fabian Meyer

Staff Agentic Engineer

Bremen, Germany

I help companies make the move to agentic engineering.

That means shaping how teams work with agents, building the tooling and workflows that make the change stick, and staying hands-on so the practices hold up in real delivery.

agent-session — spec-code-verify

❯ agent run --workflow spec-code-verify

  1. specticket → structured specpassed
  2. codetask patterns · skills · subagentspassed
  3. verifyquality gates · automated checkspassed

→ reviewable result, ready for human review

❯

The workflow from my workshop at Rheinwerk Spotlight »Coding mit KI«

01Focus

Focus

What I spend time on right now.

  • Agentic engineering transformation

    Moving companies to agentic engineering by defining the target way of working, guiding teams through the shift, and making sure adoption shows up as real delivery impact.

    Four pillars

    • Specification
    • Implementation
    • Tools
    • Verification

  • Agent-ready tooling and workflows

    Integrating agents into existing delivery tooling and building spec-driven development workflows that let engineers move from executing process to reviewing outcomes.

  • Enablement and coaching

    Workshops, pairing, and shared standards that help engineers build confidence with agents and grow the skills that matter when agents write most of the code.

  • Speaking and sharing

    Sharing what I learn about agentic engineering through talks and workshops, and bringing those sessions to more stages, teams, and events.

    Stages so far

    • Rheinwerk Online-Kurs
    • Rheinwerk Spotlight »Coding mit KI«
    • Agentic Conf Hamburg 2026

02Experience

Experience

Current and previous roles across agentic engineering, technical leadership, and software engineering.

  1. Sep 2026 - PresentCurrent

    Staff Agentic Engineer

    Cordes & Graefe KG

    Staff-level role leading the organisation's move to agentic engineering.

    • Drive the organisation-wide shift to agentic engineering across teams and delivery.
    • Build agent-ready tooling, workflows, and spec-driven development practices.
    • Enable engineers through coaching, workshops, and shared standards.

  2. Oct 2025 - Sep 2026

    Chapter Lead Vue | Sales & Settlement

    eventim Tech GmbH

    Chapter leadership role within Sales & Settlement, alongside hands-on engineering work at eventim Tech.

  3. Apr 2022 - Sep 2026

    Software Development Expert

    eventim Tech GmbH

    Software engineering role focused on shipping product work while growing frontend quality, team effectiveness, and agentic engineering adoption.

03Speaking

Speaking

Talks, sessions, and speaking work I want to keep building over time.

View Speaking

04Labs

Labs

Projects, experiments, and side builds that show what I work on outside day-to-day product delivery.

Explore Labs

  • Status: WIP

    Pladder

    Push-to-talk dictation for macOS, built for talking to coding agents. Hold a key, speak, let go, and about 300 ms later the prompt is in Claude Code, Codex, Cursor or OpenCode. It runs entirely on device, works offline in 25 languages, and is free and MIT licensed.

    • Swift
    • macOS
    • On-device AI
    • Speech-to-text

    Next up

    1. 01Ship a signed download so installing no longer means building from source.
    2. 02Graduate the experimental on-device polish step that turns "wait, no, Friday" into "Friday".
    3. 03Keep pushing release-to-paste latency down, with a benchmark for every change.

  • Status: WIP

    Habit Tracker

    A local-first habit tracker based on Atomic Habits, built end to end by a seven-stage agent software factory. Plan habits around the identity you want to build, work through a focused daily queue, reflect on misses, and get coaching grounded in the four laws of behavior change. It installs as a PWA, works offline, and keeps all data on your device.

    • Nuxt
    • PWA
    • Software factory
    • Agentic engineering

  • Status: WIP

    Good Vibes Only

    Claude Code plugins that take care of the annoying parts of agent work, so agents stay on track and you do not have to babysit them. The first plugin, usage-limits, lets long agent runs survive a usage limit. Claude pauses cleanly and picks up in the same thread once the window resets.

    • Claude Code
    • Agent skills
    • Agentic engineering

Let's talk.

Want to discuss a talk, a workshop, or an internal session? Email is the best starting point.

hello@fmeyer.dev

Fabian Meyer

fmeyer.dev • © 2026