DOCUMENT OPS

Draft board narrative from KPI deltas and prior commentary

On request, an agent compares current KPIs against last quarter, reads the prior board narrative, and writes a draft narrative section explaining the changes.

CategoryDocument Ops
Enginepaperclip
Difficultyadvanced
Triggermanual
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerOperator triggers narrative draft manually
  • ActionPull current and prior KPIs and compute deltasSnowflakeSnowflake
  • ActionRead prior narrative for tone from CodaCodaCoda
  • ActionDraft narrative explaining changes with OpenAIOpenAI
  • ActionAppend draft as suggestions to deckGoogle DriveGoogle Drive
  • OutputRoute review request to chief of staffSlack

What it does

Generates the hardest part of the board deck — the written story behind the numbers. An agent reads the current quarter's KPIs, the prior quarter's figures, and the previous board commentary, then drafts narrative prose that explains what moved and why, in a voice consistent with past decks.

When to use it

Reach for it when the numbers are settled but you still face a blank narrative slide. Ideal for execs who want a defensible first draft of the commentary to edit rather than write from scratch.

How it works

  1. 1The operator triggers the workflow manually once KPIs are locked.
  2. 2The agent pulls current and prior-quarter KPI tables from Snowflake and computes the deltas.
  3. 3It reads the previous quarter's narrative from the board Coda doc for tone and continuity.
  4. 4Using an OpenAI model, it drafts a narrative section explaining each material change, with callouts where data is ambiguous.
  5. 5It appends the draft narrative to the deck in Google Drive as tracked suggestions.
  6. 6It routes a review request to the chief of staff in Slack with the draft and the underlying delta table.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect SnowflakeWarehouses, queries, shares.
  2. 2
    Connect CodaDocs, packs, automations.
  3. 3
    Connect OpenAIModels, embeddings, files.
  4. 4
    Connect Google DriveDocs, sheets, slides, files.
  5. 5
    Connect SlackChannels, DMs, threads, mentions.
  6. 6
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  7. 7
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  8. 8
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.