INVOICE PROCESSING

Outlook invoice approval routing by amount and cost center

Reads emailed vendor invoices, looks up the cost center owner in BigQuery, and routes each invoice for approval to the right manager via Microsoft Teams using amount-based…

CategoryInvoice Processing
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerVendor invoice received in Outlook AP inboxOutlook
  • ActionExtract amount, vendor, and cost center code with OpenAIOpenAI
  • ActionResolve cost center owner and threshold in BigQueryGoogle BigQueryBigQuery
  • LogicSelect approver tier by amount and escalation rules
  • ActionLog routing decision and approver to BigQueryGoogle BigQueryBigQuery
  • OutputSend approval request to manager in Microsoft TeamsMicrosoft Teams

What it does

Turns an emailed invoice into an addressed approval request. It identifies which cost center the spend belongs to, finds the responsible approver, and applies your approval matrix so small invoices go to a line manager while large ones escalate to finance leadership.

When to use it

Use it when invoices are emailed in but approvals happen informally over chat or get stuck because nobody knows whose budget it hits. It enforces your delegation-of-authority rules automatically.

How it works

  1. 1A vendor invoice lands in the Outlook AP inbox.
  2. 2OpenAI extracts the amount, vendor, and any cost center or project code on the document.
  3. 3BigQuery resolves the cost center to its owner and the applicable approval threshold.
  4. 4Logic selects the approver tier based on the invoice amount and escalation rules.
  5. 5A Microsoft Teams approval request is sent to the chosen manager with the invoice summary and a link.
  6. 6The routing decision and assigned approver are logged back to BigQuery for audit.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect OutlookMail, calendar, contacts.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect BigQueryDatasets, queries, schemas.
  4. 4
    Connect Microsoft TeamsChannels, chats, 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.