We provide course about Codex Intermediate in english. Same problem as Claude Code at team scale, with a Codex-specific twist. Because Codex has multiple surfaces, the inconsistency is two-dimensional. One developer uses the CLI in workspace-write with on-request approvals.
Course description:
Another runs the desktop app on full-auto. A third has Codex Cloud running unsupervised on the main branch. The reviewer sees all three in the same PR queue. Without one shared operating model, AI-amplified velocity becomes AI-amplified review debt.
Course objectives:
• Run one shared loop across the team using the right Codex surfaces for each task
• Write an AGENTS.md a new engineer can use on day one without asking questions
• Decompose tickets into reviewable units
• Use Codex for refactoring, tests, and debugging without creating review debt
• Review an AI-assisted diff against a checklist instead of taste
• Compose Codex Cloud, subagents, and AGENTS.md into one end-to-end team workflow
Course content:
Module 1:
• Where uneven Codex adoption breaks things. Bigger PRs, longer review cycles, change failure rate creep. Round-the-room diagnostic of the team's current state.
Module 2:
• AGENTS.md as a living document. Belongs in: build commands, conventions, traps, review rules. Does not belong in: things Codex can read from the code itself. Lab: the room co-writes an AGENTS.md for a supplied legacy codebase.
Module 3:
• Tickets to implementation-ready briefs. A brief that a junior engineer and Codex can both act on. Lab: each participant briefs a real ticket from their own backlog.
Module 4:
• The quality loop. Refactoring with tests as the safety net, tests that check behaviour rather than implementation, debugging with hypotheses. Lab: a refactor of a brittle module with verification that catches the silent regression.
Module 5:
• AI-assisted review that catches things. What to look for in a Codex-generated diff. The plausible-but-wrong failure mode. When to reject and re-plan instead of asking for fixes. Lab: grade three Codex-generated PRs.
Module 6:
• Composing shared workflows. The high-leverage move at team scale: AGENTS.md plus subagents plus Codex Cloud plus skill, chained as one workflow. Three canonical compositions: automated PR review, new-engineer onboarding, documentation-on-commit. The room builds one endto end for their stack.
Instructors: Rogier Muller & Vasilis Tsolis
Rogier Muller is CTO of BlueMonks Group, an Amsterdam-based fintech compliance company, and co-founder of several companies. He`s a lifelong coder who moved early into AI-assisted software development. Today, he is the only person in the world to combine official ambassador roles across the three leading agentic engineering platforms: Cursor, Claude Code, and Codex.
Rogier has hosted numerous events worldwide and works closely with engineering teams, founders, and AI tooling companies on the practical adoption of agentic software development. His specific expertise is using agentic engineering in highly regulated environments, including but not limited to fintech, financial services, KYC/CDD, AML, GDPR, AFM-supervised contexts, auditability, data isolation, and compliance-heavy software delivery.
Vasilis Tsolis is a pioneer in document intelligence and agentic coding helping teams to change how they work across industries. He is an official Ambassador for Cursor, OpenAI Codex and n8n. He is the partner of Cognitiv+, an AI consultancy and software factory that helps organisations practically implement and adopt AI with enterprise confidence.
He has co-founded several companies and trains development teams across the US and EU on AI-assisted coding, with a consistent focus on integrating it into real workflows without losing control of the codebase. Background: engineering and law, twenty years across AI, construction, energy, and tech. Vasilis has worked with JPMorgan, Intel, PwC, and others along the way.
Target audience:
Software engineers, senior developers, tech leads inside a team that has been using Codex unevenly. The course assumes a mix of enthusiasts and skeptics. That mix is the whole point.
Prerequisites:
• At least two weeks of Codex use on real work
• Familiar with Git, PRs, and review on an existing codebase
• Has read at least one AI-generated PR critically
• Has completed the pre-course self-assessment
Language:
• The course is given in english
Course material:
The course fee includes course documentation, exercises, lunch and refreshments for in class events only.