FINANCE

Match uncoded Stripe card charges to vendors and draft GL memos

When a new corporate-card charge lands without a memo, looks up the merchant against your vendor master, drafts a GL-coded memo.

CategoryFinance
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew Stripe card transactionStripeStripe
  • LogicFilter: missing memo or GL code
  • ActionMatch merchant to vendor master in BigQueryGoogle BigQueryBigQuery
  • ActionDraft GL-coded memo with LLMOpenAI
  • OutputPost draft to controller Slack for approvalSlack

What it does

Every new corporate-card transaction that arrives without a memo or GL code gets automatically matched to a known vendor, assigned a probable GL account, and packaged into a draft memo a controller can approve or correct in Slack — turning a manual end-of-month coding slog into a same-day review queue.

When to use it

Use this when your team racks up dozens of card charges a week and the controller spends hours at close chasing down what each line item was for. Best for finance teams already capturing card spend in Stripe Issuing.

How it works

  1. 1A new Stripe card transaction fires the trigger.
  2. 2A filter passes only charges with no memo or GL code attached.
  3. 3The merchant name and MCC are matched against a BigQuery vendor master to find the canonical vendor and its default GL account.
  4. 4An LLM drafts a plain-English memo plus the suggested GL code, confidence, and reasoning.
  5. 5The draft posts to the controller's Slack channel with Approve / Edit buttons for review.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect StripeCustomers, subscriptions, payments.
  2. 2
    Connect BigQueryDatasets, queries, schemas.
  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.