FINANCE

Generate a month-end deferred-revenue close narrative

At month-end, pulls the deferred-revenue rollforward from BigQuery, has an LLM write a plain-English narrative explaining the movement and the largest divergence drivers.

CategoryFinance
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerMonth-end schedule after ledger lock
  • ActionPull deferred-revenue rollforward from BigQueryGoogle BigQueryBigQuery
  • ActionDraft close narrative with OpenAIOpenAI
  • LogicFlag if divergence exceeds materiality
  • OutputDeliver memo to controller in SlackSlack

What it does

This workflow produces the written explanation a controller needs at close: it reads the deferred-revenue rollforward (opening, additions, recognized, ending) from BigQuery and uses an LLM to draft a narrative covering total movement, the contracts driving recognition this period, and any schedules that diverged from plan. The outcome is a review-ready memo instead of a blank text box.

When to use it

Run it on the last business day of the period when you need the deferred-revenue flux commentary for the close package or audit workpapers, and you want a consistent, sourced first draft every month.

How it works

  1. 1A month-end schedule triggers after the ledger is locked.
  2. 2A BigQuery action returns the rollforward plus the top divergence contracts for the period.
  3. 3An OpenAI step turns the figures into a structured narrative with the numbers cited inline.
  4. 4A logic step appends a flag if any divergence exceeds the materiality threshold so the controller can't miss it.
  5. 5The finished memo is delivered to Slack tagging the controller for review.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect BigQueryDatasets, queries, schemas.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect SlackChannels, DMs, threads, mentions.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    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.