FINANCE
Close Anomaly Narrative Drafter
An agent investigates each unexplained GL anomaly by pulling supporting transactions from Snowflake, drafts a plausible cause narrative.
How it runs
The automated pipeline, trigger to output.
- TriggerSchedule fires near close lock deadline
- ActionRead anomalies still lacking explanation
- ActionQuery top contributing transaction lines from SnowflakeSnowflake
- LogicAgent drafts cause narrative from line itemsOpenAI
- ActionWrite draft flux memo to Drive close folderGoogle Drive
- OutputPost memos-awaiting-review note to SlackSlack
What it does
For anomalies still missing an explanation near the lock date, this agent does the first-pass investigation a junior accountant would. It retrieves the largest contributing journal lines for the account from Snowflake, reasons about likely drivers such as accruals, reclasses, or one-time entries, and drafts a flux narrative. The draft is saved as a memo document in a Drive close folder, clearly marked as AI-drafted and pending human sign-off.
When to use it
Use it in the final hours of close to clear the long tail of unexplained variances faster, while keeping a human approver in the loop. Best for teams whose flux commentary is otherwise the bottleneck to sign-off.
How it works
- 1A schedule fires near the close lock deadline.
- 2The agent reads the list of anomalies that still lack an explanation.
- 3For each, it queries Snowflake for the top contributing transaction lines.
- 4The agent drafts a cause narrative grounded in those line items.
- 5It writes the structured flux memo to the Drive close folder, flagged as draft.
- 6It posts a Slack note listing the memos awaiting controller review.
Set it up
What you configure once, before turning it on.
- 1Connect SnowflakeWarehouses, queries, shares.
- 2Connect Google DriveDocs, sheets, slides, files.
- 3Connect SlackChannels, DMs, threads, mentions.
- 4Connect OpenAIModels, embeddings, files.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Finance workflows
Month-End Uncoded Spend Chaser via Snowflake to Slack
On a month-end schedule, queries Snowflake for unaccrued or uncoded expenses, groups them by department owner.
Receipt Upload OCR Policy Check with Manager Escalation
When an employee drops a receipt into a Drive folder, it extracts the line items, checks them against expense policy.
Weekly Proration Anomaly Audit to Notion
Each week it aggregates all flagged proration discrepancies from Snowflake, scores them against anomaly thresholds, and publishes a finance-ready audit page in Notion with totals.
Accrual Chase Board in Monday with Per-Owner Tasks
On a schedule it reads open uncoded expenses from Snowflake and creates or updates a Monday item per department owner.
Detect Mid-Cycle Plan Change Mischarges and Queue Credit Memos
Listens for Stripe subscription plan changes, recomputes the correct prorated amount.
Draft and Send Proration Over-Billing Correction Emails
For each confirmed over-billing credit, an agent drafts a clear, customer-specific apology email explaining the proration error and the credit applied.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.