FINANCE

Draft a board-ready runway narrative each month

Monthly, pull actuals from Snowflake and the live runway figures from Coda, have an agent draft a plain-English runway narrative explaining the change.

CategoryFinance
Enginepaperclip
Difficultyadvanced
Triggerschedule
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerMonthly pre-board schedule
  • ActionPull trailing actuals from SnowflakeSnowflakeSnowflake
  • ActionRead runway + scenarios from CodaCodaCoda
  • ActionAgent drafts runway narrativeOpenAI
  • ActionAppend draft to board docCodaCoda
  • OutputPost draft to Slack for sign-offSlack

What it does

Once a month this workflow turns raw runway math into a narrative the board can read. It gathers the latest actuals from Snowflake and the current runway figures from your Coda model, then an agent drafts a short write-up: what burn was, how runway moved versus last month, what drove the change, and which scenario the company is tracking. The draft is appended to the board doc in Coda and posted to Slack for the CFO to approve.

When to use it

Use it when you spend hours each month translating spreadsheet deltas into board commentary. Best for finance leads who want a defensible first draft grounded in real numbers rather than writing the runway section from scratch.

How it works

  1. 1A monthly schedule kicks off ahead of the board meeting.
  2. 2The workflow pulls trailing actuals from Snowflake.
  3. 3It reads current runway and scenario figures from Coda.
  4. 4An agent drafts the narrative, citing the month-over-month burn and runway change.
  5. 5The draft is written into the board section of the Coda doc.
  6. 6A review-request with the draft is posted to Slack for CFO sign-off.

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 SlackChannels, DMs, threads, mentions.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    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.