Weekly Report

Produce a weekly status report from inputs to published. The AI drives Gather, Draft, and a review checkpoint.

Operations 4 steps 1 checkpoint Human approval Self-correcting
Use this workflow

Free to start · runs with your own AI

Workflow steps

Runs inside your AI conversation · the orchestrator drives

"Write this week's status report for my team"

you — in any AI chat

  1. 1

    Gather

    Collect the inputs for this report before drafting.

    Record:

    • The reporting period and the audience for the report
    • What got done this week — completed work, shipped items, results
    • In-progress work and where it stands
    • Blockers and risks
    • Any metrics or numbers to include
    • What is planned for next week

    Pull from notes, task updates, or the operator's recollection. If a key
    area is empty, ask before assuming nothing happened.

    Save the gathered inputs as a task note with task_notes_add. The next
    step — Draft — reads this note.

  2. 2

    Draft

    Read the task notes with task_notes_list — the note from the Gather
    step contains the week's inputs. Work from it.

    Write the report. What good looks like:

    • A one- or two-line headline summary of the week
    • Wins and completed work
    • In-progress work with status
    • Blockers and risks, with what is needed to clear them
    • Metrics, if any, with plain context
    • Next week's plan

    Keep it scannable — a stakeholder should grasp the state in under a
    minute. State numbers plainly; do not inflate.

    Save the full report draft as a task note with task_notes_add. The
    Review step reads this note.

  3. 3

    Review

    Read the task notes with task_notes_list — the Draft note holds the
    report and the Gather note holds the source inputs. Work from them.

    Review the report:

    • Every claim and number traces back to a gathered input
    • Blockers are stated honestly, not buried
    • The summary matches the body
    • Nothing important from the inputs was dropped

    Ask the operator to approve the report for publishing. This is a
    checkpoint — once published it informs decisions, so the AI cannot
    advance until you approve. If you reject, the workflow returns to Draft.

    The AI pauses here and waits for a human to approve before the conversation continues.
    If rejected → returns to draft
  4. 4

    Publish

    Read the task notes with task_notes_list — the Review note holds the
    approved report. Work from it.

    Publish the report to its audience — the channel, doc, or email the
    team uses. Save the published report as a task note with task_notes_add
    so the record of what was sent stays on file, then close out the task.

  5. Workflow complete — outcome delivered, every step on record.

Why this workflow?

Without a workflow

  • The weekly report becomes a last-minute scramble that leaves out the blocker that mattered
  • The update ships with a number that was never checked and a claim nobody verified
  • Each week the report looks different and readers cannot find what they need
  • Last month's reports are scattered across chats and nobody can trace what was claimed when

With ConvOps

  • The AI drives a Gather step first, so the report is built on the week's real inputs, not memory
  • The AI pauses at a review checkpoint so you confirm the report before it is published
  • The AI drives the same structure every week, so wins, blockers, and next steps land in the same place
  • Every step — Gather, Draft, Review, Publish — is logged, so every report's history is already there

Related workflows

Ready to automate?

Stop re-explaining your process. Pick a template, start a task, and let the AI drive the work through your workflow.