Content Repurpose

Turn one piece of content into several formats. The AI drives through Angles, Produce, and a review checkpoint.

Marketing 5 steps 2 checkpoints 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

"Turn this blog post into a LinkedIn post and a newsletter blurb"

you — in any AI chat

  1. 1

    Source Intake

    Capture the source you are repurposing. Do not start producing yet.

    Record:

    • The source itself — paste the text, or the link plus a summary
    • The core message and the two or three key points worth carrying
      across formats
    • The original audience and tone, as a reference point
    • Target channels — where the repurposed versions will go

    If the source is missing or you cannot identify its core points, ask
    the operator before advancing.

    Save the source, its core points, and the target channels as a task
    note with task_notes_add. The next step — Angles — reads this note.

  2. 2

    Angles

    Read the task notes with task_notes_list — the note from the Source
    Intake step contains the source, core points, and target channels.
    Work from it.

    Propose one angle per target format. What good looks like:

    • For each channel: the format, the specific angle, and which of the
      source's key points it leads with
    • Angles that genuinely differ by channel — not the same takeaway
      reworded
    • A note on length and tone expected for each channel

    Save the per-format angle list as a task note with task_notes_add. Then
    ask the operator to approve the angles before producing any version.
    This is a checkpoint — the AI cannot advance until you approve.

    The AI pauses here and waits for a human to approve before the conversation continues.
  3. 3

    Produce Versions

    Read the task notes with task_notes_list — the note from the Angles
    step contains the approved per-format angles, and the Source Intake
    note holds the core points to stay faithful to. Work from them.

    Produce each version following its approved angle. For every channel:

    • Write it to that channel's format, length, and tone
    • Carry the source's key points accurately — no new claims the source
      did not make
    • Make it stand on its own, readable without the original

    Save all produced versions as a task note with task_notes_add, labeled
    by channel. If the set exceeds 10,000 characters, split across notes or
    store where the operator keeps documents and record the location. The
    Review step reads this note.

  4. 4

    Review

    Read the task notes with task_notes_list — the note from the Produce
    step contains every version, and the Source Intake note holds the
    original points to check against. Work from them.

    Review each version:

    • It matches its approved angle and channel format
    • Every claim is faithful to the source
    • Tone fits the channel; nothing reads as a blunt copy-paste
    • No placeholder text or unfinished section

    Ask the operator to approve the full set for publishing. This is a
    checkpoint — publishing is the irreversible moment, so the AI cannot
    advance until you approve. If you reject, the workflow returns to
    Produce Versions.

    The AI pauses here and waits for a human to approve before the conversation continues.
    If rejected → returns to produce
  5. 5

    Complete

    Every version is approved and ready to publish. Confirm the final set
    is saved as a task note, then close out the task.

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

Why this workflow?

Without a workflow

  • The same article gets copy-pasted everywhere and reads wrong on every channel
  • Three half-finished repurposed versions sit in three different chats with no idea which is current
  • Versions go out before anyone checks they still match the source's claims and tone
  • Nobody can trace which channel versions came from which source piece or what was changed

With ConvOps

  • The AI drives a set of Angles you approve, so each version is shaped for its channel before anything is written
  • The AI saves the source, the angles, and each version as notes, so a later session resumes with the full set intact
  • The AI pauses at a review checkpoint so you sign off on every version before it publishes
  • Every step — Source, Angles, Produce, Review — is logged, so the trail from original to every version 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.