All use cases

Weekly digests

The status update writes itself.

An agent reads a week of activity across the tools your team uses, separates decisions from chatter, and posts a digest people actually read.

How it works

Three steps to a standing task

  1. Step 01

    Name the sources

    Point the agent at the channels, repositories, and databases that hold the week's activity. Pin the ones it should always carry as context.

  2. Step 02

    Say what matters

    Decisions, blockers, and owners — or shipped work, review load, and CI health. The agent filters to what your audience needs rather than repeating everything.

  3. Step 03

    Schedule it for Friday afternoon

    Describe the cadence in plain English. The digest posts to the channel where the team already reads, every week, without anyone owning the task.

The run

What the agent actually does

Every step below is a real tool call: the agent reaches for the API it needs, reads what it finds, and acts.

Fridays at 4:00pm

Every Friday, summarize merged work, review backlog, CI health, and the decisions made this week.

  1. github·list PRs merged in the last 7 days
  2. github·list open PRs awaiting review
  3. slack·read #product and #eng threads
  4. code·separate decisions from discussion
  5. slack·post the digest to #engineering

Week of Mar 3

  • 38 PRs merged · median review time 6h
  • 5 PRs waiting more than 3 days
  • CI pass rate 94%, down from 97%
  • 3 decisions recorded, including the export beta

Reach

The tools this agent touches

Each one connects once, and the agent gets its complete API.

This task belongs to Operations. See the rest of what that team hands off.

FAQ

Questions, answered

Put an agent on weekly digests.

Describe the task, attach a trigger, and let it run around the clock.