INVOICE PROCESSING

Flag Silent Price Hikes on Recurring Vendor Invoices via Email

Watches your invoice inbox, compares each new vendor invoice against that vendor's historical baseline.

CategoryInvoice Processing
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew invoice email arrives in labeled Gmail inboxGmailGmail
  • ActionExtract vendor, total, and line items from the invoiceOpenAI
  • ActionLook up vendor's historical invoices to build baselinePostgreSQLPostgres
  • LogicCompute price drift % and compare against tolerance
  • ActionRecord this invoice's amounts to the history tablePostgreSQLPostgres
  • OutputPost drift alert to finance Slack channelSlack

What it does

Many vendors raise prices quietly between billing cycles, and the increase hides inside an otherwise routine invoice. This workflow catches that drift automatically. When a new invoice email arrives, it extracts the vendor, the total, and the per-line amounts, looks up what that same vendor has charged historically, and computes the percentage change. If the increase exceeds your threshold, it posts a structured alert to Slack so finance can question it before it gets paid.

When to use it

Run this if you pay the same vendors on a recurring basis (SaaS, utilities, logistics, retainers) and want a tripwire on silent rate increases. It is most valuable for teams that approve invoices by habit and rarely re-check the numbers.

How it works

  1. 1A new invoice email lands in a labeled Gmail inbox and triggers the run.
  2. 2The agent parses sender, vendor name, invoice total, and line items.
  3. 3It queries Postgres for that vendor's prior invoices to build a rolling baseline.
  4. 4A logic step computes drift percentage and compares it to your tolerance.
  5. 5If drift is within tolerance, the invoice is logged and the run ends quietly.
  6. 6If drift exceeds tolerance, a Slack alert fires with the old price, new price, delta, and a link to the source email.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect GmailRead, draft, send, label.
  2. 2
    Connect PostgresAny Postgres URL — query, write, migrate.
  3. 3
    Connect SlackChannels, DMs, threads, mentions.
  4. 4
    Connect OpenAIModels, embeddings, files.
  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.