FINANCE
Chase missing context on low-confidence card charges via cardholder DM
For card charges the matcher can't confidently code, DMs the cardholder in Slack to ask what the charge was.
How it runs
The automated pipeline, trigger to output.
- TriggerNew Stripe card transactionStripe
- ActionMatch merchant and score confidence in BigQueryBigQuery
- LogicBranch: route low-confidence charges to chase
- ActionDM cardholder in Slack for business purposeSlack
- ActionDraft memo from reply with LLMOpenAI
- OutputPost draft to controller channelSlack
What it does
Some charges can't be coded from the merchant name alone — a generic marketplace, a one-off vendor, a split purchase. This workflow detects those low-confidence cases, asks the cardholder directly in Slack for the business purpose, and folds their answer into a draft memo that goes to the controller.
When to use it
Use this when ambiguous charges are the bottleneck and the fastest path to a correct memo is simply asking the person who swiped the card. Pairs well with the daily digest, which handles the confident cases.
How it works
- 1A new Stripe card transaction fires the trigger.
- 2The merchant is matched against the BigQuery vendor master, returning a confidence score.
- 3A branch routes only low-confidence or unmatched charges into the chase path.
- 4The flow DMs the cardholder in Slack asking what the charge was for and captures the reply.
- 5An LLM combines the reply with the charge data into a draft GL-coded memo.
- 6The finished draft posts to the controller channel for sign-off.
Set it up
What you configure once, before turning it on.
- 1Connect StripeCustomers, subscriptions, payments.
- 2Connect BigQueryDatasets, queries, schemas.
- 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.