INVOICE PROCESSING

Investigate a flagged billing spike and draft a vendor inquiry

When a vendor invoice spike is flagged, an agent reads the line items, compares them to prior invoices to find what changed.

CategoryInvoice Processing
Enginepaperclip
Difficultyadvanced
Triggerwebhook
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerSpike-flagged webhook with invoice idHTTP webhook
  • ActionPull invoice and vendor historyGoogle BigQueryBigQuery
  • LogicDiff line items to attribute increase
  • ActionDraft vendor clarification emailOutlook
  • OutputNotify reviewer with summarySlack

What it does

Takes a flagged spike beyond a simple alert: an agent opens the suspect invoice, reads its line items, and works out which charges drove the increase versus the vendor's prior bills. It then writes a specific, polite inquiry email naming the exact lines in question instead of a vague "why is this higher."

When to use it

Use this when spikes are common enough that manually diffing line items eats your AP team's time. It produces a ready-to-send draft so a human only reviews and clicks send.

How it works

  1. 1A spike-flagged webhook from your detection flow triggers the run with the invoice id.
  2. 2The agent pulls the flagged invoice and the vendor's recent invoice history from BigQuery.
  3. 3It diffs line items to attribute the increase to new charges, quantity changes, or rate changes.
  4. 4It drafts a clarification email citing the specific lines and the prior amounts.
  5. 5The draft is created in Outlook for an AP reviewer to approve and send, and a summary is posted to Slack.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect HTTP webhookTrigger any URL on agent actions.
  2. 2
    Connect BigQueryDatasets, queries, schemas.
  3. 3
    Connect OutlookMail, calendar, contacts.
  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.