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. 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
Target audienceSoftware 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
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.
Duration: 1 day
Price: 10 900 NOK
Language: English
Format: Classroom, virtual classroom, or in-company
Hva er Codex Intermediate?
Codex Intermediate er et videregående kurs som bygger på grunnleggende bruk av Codex, og fokuserer på mer effektiv og strukturert bruk i reelle utviklingsprosjekter.
Hvem passer kurset for?
Kurset passer for utviklere som allerede har erfaring med Codex eller lignende AI-verktøy, og som ønsker å jobbe mer effektivt med komplekse oppgaver og kodebaser.
Trenger jeg forkunnskaper for å delta?
Ja, det anbefales at du har erfaring med utvikling, Git-baserte arbeidsflyter og grunnleggende bruk av Codex.
Er kurset praktisk rettet?
Ja, kurset er hands-on og inkluderer øvelser hvor du jobber med reelle scenarier, større kodebaser og mer avanserte arbeidsflyter.
Hva lærer jeg som er nyttig i praksis?
Du lærer hvordan du strukturerer prompts bedre, jobber mer effektivt med spesifikasjoner, håndterer sikkerhet og kontroll i agentbaserte arbeidsflyter, og hvordan du kvalitetssikrer og forbedrer generert kode.
