Codex training, OpenAI's agent on your projects
Codex is OpenAI's agent that works on files, folders and code repositories. Colombani.ai trains the teams that have chosen it: one day to apply it to their real tasks, half a day for executives to see what it does and what it costs. Exercises on your own files and repositories, by a trainer who uses Codex on client engagements every week.
In-house training, on-site or remote, for one to ten participants. From €1,000 excl. VAT per half-day and €1,800 per day for an in-company group; final price depends on group size and length, on quote. OPCO funding possible.
Colombani.ai, a Qualiopi-certified training provider based in Paris, France, offers two programmes dedicated to Codex, OpenAI's agent, in Paris, across France or remotely, in French or English; French companies can apply for OPCO funding. A one-day "Working with AI agents" course where each participant hands their tasks on files, folders and projects to the Codex app and leaves with a configured agent. A half-day briefing for executives, with live demonstrations of Codex, Claude Code and the other agents on the market. Colombani.ai uses Codex on engagements and publishes the coding agent comparison.
One programme per audience, dedicated to Codex
Each programme is part of the Qualiopi catalogue and uses your own cases: your folders, your projects, your repositories. The materials and installation guide are those of Codex.
AI agents training
Your teams hand Codex their tasks on files and folders: sorting and extracting documents, transforming data, scripts and automations, code review for technical teams. Everyone leaves with a configured agent and a checking routine.
- Codex app
- Files, folders, repositories
- Checking a result
AI training for executives and boards
What coding agents change for a team, demonstrated live: Codex, Claude Code and the others compared on a real case, what it costs, what to scope before letting them touch the code, and a prioritised action plan to take away.
- Codex and Claude Code compared
- Cost and scoping
- AI Act and data
A coding agent is scoped before it is rolled out
Codex reads your files, runs commands and edits repositories. Putting it in a team's hands without rules means unverifiable results. Colombani.ai teaches how to use it wisely: which tasks to entrust to it, how to write an instruction it understands, how to review what it produces, where its scope ends. This scoping comes from practice: Colombani.ai runs Codex on its own projects and its clients' projects, from sorting folders to reviewing code.
Ulysse Trin, founder of Colombani.ai, holds the Codex Solutions Practitioner then Codex Deployment Practitioner certifications, issued by OpenAI: qualifying then deploying Codex in a team. Colombani.ai uses Codex on engagements and publishes an updated comparison of coding agents, tested in production on the same tasks. Advice remains independent of vendors: if another agent, or a local model, better meets your constraint, it is the one recommended.
Read the coding agent comparison →Codex, from the first delegated task to written usage rules
-
Getting started
The Codex app, folder access, the first delegated task, reading what it did before accepting.
-
Business tasks
Sorting and extracting documents, transforming spreadsheets, automation scripts, recurring reports, on your own files.
-
Technical tasks
For teams that code: review, tests, scoped refactoring, and splitting the work between Codex and Claude Code.
-
Scope and data
What the agent may touch, what it must not see, where the context lives, the trace of its actions, the AI Act register.
Qualiopi-certified provider, OPCO funding possible
Colombani.ai is a Qualiopi-certified training provider (certificate QUA009472, training provider registration number 11757549975, this registration does not constitute State approval). These programmes are therefore eligible for OPCO funding, or FIF-PL funding for self-employed professionals, subject to the funding body's decision. The tool is chosen during the needs analysis and stated in the training agreement.
How to fund AI training through an OPCO →
Ulysse Trin
Founder of Colombani.ai, holder of the Claude Certified Architect Professional certification issued by Anthropic and of certifications issued by OpenAI
Engineer (Epitech, MSc AI), holder of the Claude Certified Architect Professional certification, issued by Anthropic, and of nine practitioner certifications issued by OpenAI, including ChatGPT Deployment Practitioner and ChatGPT Solutions Practitioner. Consultant, trainer and developer, he uses Claude and ChatGPT daily on client engagements and regularly tests Vibe, Copilot and Gemini to keep up with their changes; his programmes build on cases developed on those engagements.
Claude Certified ArchitectProfessional · Official Anthropic certification. Verify the credentialSee also the nine practitioner certifications issued by OpenAI → 
Do participants need to know how to code?
Not for the one-day programme: Codex works on files and folders without writing code, and the exercises start from each participant's tasks. Technical teams get their share with the sequences on repositories and code review.
Codex or Claude Code?
In 2026 the question is less about choosing than about sharing the work: both are scoped with the same method, and many teams use one to produce and the other to review. The executive briefing compares them live on your case; the comparison published by Colombani.ai details the differences in context, auditability and default security.
Do participants need a subscription?
Not for the executive briefing. For the one-day programme, each participant uses their own ChatGPT Plus, Business or Enterprise account, which gives access to Codex. The plan is chosen with you before the session, depending on the data involved.
Is the programme adapted to the tool or generic?
Adapted. The learning objectives and assessment are those of the programme in the Qualiopi catalogue, which makes it possible to request funding, subject to the funder's decision; the materials, the installation guide sent three days before and the exercises are those of the chosen tool, with its own features. One sequence compares the five main market tools (Claude, ChatGPT, Microsoft Copilot, Gemini and Mistral Vibe) from a confidentiality standpoint, whichever one you use.
Can it be funded through the CPF?
No. Colombani.ai programmes are not listed for CPF funding. As Colombani.ai is Qualiopi-certified, funding can be requested from your OPCO or the FIF-PL; the decision rests with the funder, according to its criteria and budgets.
Open enrolment or in-house training, on-site or remote?
In-house training, using your real cases and data, for one to ten participants. On-site in France or remote, as you prefer. An open-enrolment format is occasionally offered for the executive briefing.
Receive the programme and a quote
Tailored programme and quote within two business days.
Need Codex training?
Describe your teams, your use cases and the tool you use. Receive a response within 48 hours with a programme and a quote.