Skip to main content
Home: Florian Bruniaux Engineering & AI

Florian Bruniaux / Explore

Search the site

Search in English or French, or jump to a section.

↑ ↓ to navigateEnter to openEsc to close

EN
Colour theme
Contact me

Hands-on Fractional Chief AI Officer (CAIO)

Florian Bruniaux

From AI strategy to code.

Harness engineering specialist

I help leaders choose where to invest in AI, then work with their teams to change how they organise, build and review.

Built in the open

All projects

Rust CLI

RTK

Reduce the noise in command output.

A Rust CLI proxy for more compact agent context. First and main contributor in Q1 2026, then an evangelist.

TypeScript Context engineering

ctxharness

Keep agent instructions grounded.

Detect stale facts and check the context your agents rely on in CLAUDE.md, AGENTS.md and related files.

Python MCP

Search Console MCP

Connect agents to real SEO work.

Structured access to search analytics, URL inspection and technical SEO tools through MCP.

Experimental

Agent Router ↗

Model, effort and skill routing for coding tasks. Public source; no measured cost gain claimed.

Under the hood / Harness engineering

Inside the agent harness.

Follow a request through the context, tools and checks around an AI model.

Explore the workshop
Florian at his desk, with Crew agents and smaller subagents working across a pencil-drawn workshop: context shelves, a model engine, tools, checks and a return pipe.
A human sets the direction. Agents work with context, tools and checks.
NOV 2026 New in my guide AI Design Patterns All updates

What I’m exploring

I’m currently exploring inference: where to run models, which hardware to use and what it costs. I collect my research and reference material in the Claude Code Guide.

AI ADOPTION / HANDS-ON LEADERSHIP

Building an agentic organisation

From support to engineering, we decide who does what, which steps agents can handle and how teams check the results.

Explore the services

A RECENT ENGAGEMENT / ANONYMISED

Team training and a shared agent harness

In an ongoing engagement, I trained teams, configured their harness, created a dedicated repository and built a shared knowledge base.

Let's discuss your situation →

What are you working on?

Start with the question you need to answer.

Subscribe to the newsletter

Prefer a sequence? Follow a reading path →

Latest writing

GUIDE ·

Designing a bounded review loop

Build a bounded review loop with frozen inputs, separate execution and outcome fields, retry limits, evidence handoffs and human escalation.

SPEAKING / FROM STRATEGY TO CODE

Conferences, podcasts & live sessions

From the boardroom to the pull request.

Invite me for a conference talk, podcast, live session or executive briefing. I adapt the technical depth to the audience, drawing on my work building AI systems and helping teams adopt them.

  • For technical audiences: harness engineering, agent context, code review and reliable workflows, with implementation details.
  • For product and non-technical teams: practical uses, limitations and how AI changes everyday work.
  • For leadership and executive committees: AI strategy, investment choices, governance and organisational transformation.
Florian Bruniaux presenting a code-review workflow on stage, with a slide showing three review tools and a shared verification workflow.
Dev With AI, Paris · From code to merge
Florian Bruniaux speaking into a microphone during a Tech Ready panel.
Tech Ready · AI adoption
A full meetup room at WeScale during a presentation on the AI tooling ecosystem.
Generative AI Paris · WeScale