FINANCE
Budget Overrun Vendor Investigation Agent
On demand from a Slack command, an agent investigates which vendors drove a department over budget using BigQuery.
How it runs
The automated pipeline, trigger to output.
- TriggerSlack command names department and periodSlack
- ActionQuery and decompose overrun by vendorBigQuery
- LogicRank contributors and form hypothesis
- ActionDraft root-cause findings memoOpenAI
- OutputStore memo in Coda and reply in SlackCoda
What it does
This is an agent-driven investigation. A finance lead asks in Slack why a department went over budget, and the agent queries BigQuery to decompose the overrun by vendor, isolates the largest contributors, reasons about likely causes, and writes a findings memo to Coda. It answers the why, not just the how much.
When to use it
Use it when a month closes over budget and someone needs an answer fast. Instead of an analyst hand-pulling queries, the agent does the decomposition and drafts the memo, leaving a human to review and act.
How it works
- 1A Slack slash command names the department and period to investigate.
- 2The agent issues BigQuery queries to break the overrun down by vendor and line item.
- 3It reasons over the results to rank contributors and form a root-cause hypothesis.
- 4OpenAI helps draft a clear findings memo with the breakdown and recommended next steps.
- 5Coda stores the memo and the agent replies in Slack with a link and the headline finding.
Set it up
What you configure once, before turning it on.
- 1Connect SlackChannels, DMs, threads, mentions.
- 2Connect BigQueryDatasets, queries, schemas.
- 3Connect OpenAIModels, embeddings, files.
- 4Connect CodaDocs, packs, automations.
- 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.