The audience is support and, in most setups, the whole company, so the changelog has to be plain rather than clever. Codex is quick at turning API responses into structured output, and a week of merged pull requests is exactly that: a list to read, sort into five buckets, and credit by handle. Twenty-three merges is still a short run.
Run a staged conversation — no account needed. The agent handles it for real while a simulated world answers its tool calls; nothing touches real accounts, and nothing is actually sent.
Friday 15:00 changelog tick
It is Friday 15:00 in Berlin. Twenty three pull requests merged across the api and dashboard repos this week, including one that renames a field in the settlement webhook payload and one that removes a reporting endpoint two customers still call. The audience is support and the twelve merchants on the beta.
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect GitHub
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Slack
One sign-in. The agent acts through your account, scoped to what this template uses.
Repo context
Which repositories to cover, who reads this changelog (customers, support, the whole company), and who to tag when a repository goes silent or a call fails.
Changelog style
How your changelog should read: how technical to get, whether dependency bumps and internal refactors make the cut, and how long it can run before people skim.
Runs on Codex
Preselected for this page — connect your Codex account during setup, or switch to NoClick's built-in models with one click.
Watch it handle a test run
A staged conversation against a simulated world — then it’s live.
Latest release, compare against head, merged pull requests for the week: three API shapes with an obvious relationship between them.
Cost tracks the schedule rather than the repository, so a busy week and a quiet one land in roughly the same place.
Not for the writing, but the raw material is pull request metadata and commit messages, and a harness at home in that data makes fewer mistakes about what counts as a revert pair or a dependency bump. Those get skipped by instruction. Quiet Noise Week checks that seven Dependabot bumps produce a short changelog rather than a padded one.
Free to start. Guided setup, a test run against staged conversations, and it's live.