Where agentic AI actually ships work

Concrete workflows where Codex, Claude Code, MCP and related tools earn their place: shape, gate, and outcome.

Use-case map

Choose the workflow before the tool

Each route starts with one bounded job, one approval point, and one result the team can verify.

Refactor

A multi-file refactor where tests are the contract and the agent does the mechanical work.

Shape: Read-only review, agreed scope, working branch, test gate, diff reviewed in passes.
Outcome: Large refactors become days of agent work plus review, with tests as the safety artefact.

CodexClaude Code

Knowledge

New joiners ask repo questions with grounded references before taking senior time.

Shape: Codex or Claude Code gets read-only repo access plus a short guide for good questions and escalation.
Outcome: New joiners reach the first useful PR a week earlier. Senior time is reserved for the questions the agent cannot answer well.

CodexClaude CodeGemini

Migration

A version bump, API rename or dependency swap where each file follows the same rule.

Shape: Rule and example first. Agent applies it file by file with tests and a small checklist.
Outcome: Migrations that would have stalled in a backlog get done in days. The written rule is the durable artefact for the next migration.

Codex

Eval

A small set of repeatable tasks with known-good outputs for every model or workflow change.

Shape: Three to five tasks, written prompts, known-good outputs and an automated comparator in the repo.
Outcome: Model and prompt changes stop being a vibes call. The team has a short list of tasks it knows the workflow should pass.

CodexClaude Code

Next step

Send the task, the risk, and the result you need. The first call can stay narrow.