Jonathan Gelin

Image Jonathan Gelin, developer experience architect

Coding agents are becoming a commodity. Adapting your teams and your SDLC is the hard part.

That is the part I help with: the strategy, and the harness that connects agents to your standards, your CI/CD and your data.

Book a 30-minute call How I can help

20+ years improving how teams deliver software, now helping organizations get past the AI pilot.

The AI factory I build with you

Automation is the accelerator: it pushes more work to the agents. Checks and reviews are the brakes, and good brakes are what let you go faster without drowning in low-quality pull requests. Here is each part, and what I bring to it.

Automation Accelerator starts agents on New ticketPull requestFailing pipelineNightly schedule I wire agents into your pipelines and schedules

Guides steer before it acts

Context & memoryI make your repos and docs readable for agents
Conventions & pluginsI turn your standards into plugins and skills that teach the LLM your environment, rules, conventions and knowledge
Agent Claude Code, Devin, Cursor, Pi, DeepSeek LLM I help choose the tools and roll them out to every team

Sensors Brakescheck after it acts

EvaluationI test your skills, plugins and rules like code: evals and compliance checks on every change
MonitoringI monitor the agents: use cases, skills used, tokens and cost, so the data shows what to improve in the harness

Steering loop: every review becomes a rule, so the same comment is never written twice.

Foundations RepositoriesNx buildCI/CDTestsConventions I make them agent-ready

From ticket to production, at agent speed

Code is no longer the bottleneck. The factory moves every step around it to agent speed, with a human at each gate. Each stage hands a file to the next.

Plan

The agent does
Turns an idea or a ticket into a clear intent.
Human gate
Product owner accepts it
Output
intent.md
Measure
Time from idea to accepted intent

I set up: Intent templates and connectors to your tracker

Spec

The agent does
Writes the spec, applying your security and compliance skills.
Human gate
Tech lead approves risky changes
Output
spec.md
Measure
Rework after the build starts

I set up: Skills that encode your policies, applied while writing

Build

The agent does
Plans the change, then codes it in parallel sessions.
Human gate
Engineer approves the plan before any code
Output
plan.md + diff
Measure
First-pass merge rate

I set up: Plugins and skills that teach the LLM your environment, rules, conventions and knowledge

Test

The agent does
Runs the tests until they pass; a second agent verifies.
Human gate
Automatic gate: CI and evals
Output
green tests
Measure
Eval pass rate

I set up: Evals that run whenever a skill, rule or hook changes

Review

The agent does
Reviews every pull request against the spec and your standards, and pushes fixes.
Human gate
Reviewer approves the PR
Output
reviewed PR
Measure
PRs with real review comments

I set up: A review agent that owns your coding standards

Release

The agent does
Prepares and runs the deployment, sandboxed.
Human gate
A named person authorizes production
Output
deployment
Measure
Lead time to production

I set up: Hooks as approval gates, scoped credentials

Monitor

The agent does
Tracks agent usage and diagnoses anomalies, then writes the next intent.
Human gate
A human authorizes the fix
Output
new intent + eval
Measure
Cost per team, time to diagnosis

I set up: Agent telemetry: use cases, skills, tokens, cost

Every incident becomes a new intent and a new eval, and the loop starts again. Git keeps the audit trail.

More than building: advice and advocacy

The tools change every quarter. Knowing where the market goes, and bringing people along, matters as much as the code.

Advise and challenge the strategy

An outside view on your AI plans, from someone who rolls them out.

  • Which tools, in which order
  • Build or buy, and where the risks are
  • Pushing vendors for enterprise features

Keep you ahead of the market

I test the tools myself and turn the noise into clear recommendations.

  • Claude Code, Devin, Cursor, Pi, DeepSeek
  • Harness engineering, skills, MCP, factories
  • Short, opinionated notes on what matters

Advocate for developers

Adoption is a people topic. I explain, demo and teach until it sticks.

  • Workshops and internal demos
  • Conference talks, in English and French
  • Articles on what works in practice
Nx Champion badge

Nx Champion. Speaker at React Brussels, Monorepo World, DevFest Nantes, This Is Learning Conf. 24 articles and 4 talks

How I work

The principles I bring to every engagement, learned from rolling out agents in real organizations.

  • Don’t outsource the thinking

    Agents amplify the design you did, or the lack of it. The architecture and the plan stay human decisions.

  • Review where the leverage is

    Research and plans get the closest human review. A wrong plan costs far more than a wrong line of code.

  • Brakes before accelerators

    Raise the quality bar with checks and review agents before adding more agents. Otherwise you only produce more rework.

  • Stay in the smart zone

    Small, focused contexts beat long conversations. Sub-agents control context; they are not job titles.

  • Measure, then decide

    Telemetry and evals decide which plugins to improve or retire, not opinions or vendor demos.

  • Pick one tool and get reps

    Adoption is a culture change led from the top, with depth on one tool rather than comparing five. Without it, juniors ship more with AI while seniors clean up after it.

20+ years, one thread

Every step has been about how teams build software better. AI is the next step, not a change of direction.

  1. 2006

    Developer

  2. 2013

    Lead developer & Scrum master

  3. 2017

    DX architect & Nx

  4. 2024

    AI in the SDLC

  5. 2026

    AI engineering factory

What people say

He reshaped how we think about and work with our tooling from the ground up. Jonathan also brought strong AI skills to the table, introducing AI carefully and intentionally, only where it genuinely made sense.

Image Jose Badeau
Head of Technical Excellence at Caseware

He has the energy and passion, the vision, and technical expertise to drive a team, suggest roadmaps, and implement solutions at an amazing speed and quality.

Image Miguel Perez Sanchis
Software Engineer at Julius Baer

Jonathan was entrusted with the challenge of leading our teams through the migration of a substantial legacy frontend codebase to a modern, state-of-the-art monorepo.

Image Karel Frederix
Senior Software Engineer at Marigold

He sports a can-do mentality and manages to raise the quality bar across an Engineering department. Sound boarding with him does not get boring: never condescending, always enlightening.

Image Igor Kalders
Engineering Manager at Marigold
All 17 recommendations

Organizations I've worked with

  • Image Swift
  • Image Julius Baer
  • Image Caseware
  • Image Entain
  • Image Marigold
  • Image Thalys
  • Image Sodexo
  • Image Thales
  • Image European Commission
  • Image Fednot
  • Image RTBF
  • Image Roularta
  • Image Edebex
  • Image I.R.I.S.

Latest writing

What I learn in real engineering organizations.

All articles and talks

Image

Let's talk about your AI factory

A stalled pilot, agents that ignore your standards, no idea what the tools really bring? A 30-minute call is usually enough to see where I can help.

Book a 30-minute call or write to [email protected]