INVOICE PROCESSING

Outlook Invoice Intake with PO Matching and ClickUp Exception Routing

Watches an Outlook accounts-payable mailbox for vendor invoices, extracts line items with AI, matches each PO number against your purchase-order table.

CategoryInvoice Processing
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew email in AP Outlook mailboxOutlook
  • ActionExtract invoice fields and line items with AIOpenAI
  • ActionLook up purchase order in PostgresPostgreSQLPostgres
  • LogicBranch: PO match and total within tolerance?
  • ActionInsert approved invoice into PostgresPostgreSQLPostgres
  • OutputCreate ClickUp exception task for mismatchesClickUpClickUp

What it does

Monitors a shared Outlook mailbox for incoming vendor invoices, pulls the PDF or body text, and uses an LLM to extract the vendor, invoice number, totals, and line items. It looks up the referenced purchase-order number in your Postgres PO table and compares amounts and line quantities. Clean matches are written to the invoices table as approved; anything that fails to match — wrong PO, amount over tolerance, or no PO at all — becomes a ClickUp exception task.

When to use it

Use this when invoices arrive by email and your team manually keys them and cross-checks POs in a spreadsheet. It removes the data entry and the eyeballing, while still keeping a human in the loop for the cases that actually need judgment.

How it works

  1. 1A new email lands in the watched Outlook mailbox and triggers the run.
  2. 2The flow extracts the invoice fields and line items with OpenAI.
  3. 3It queries Postgres for the matching purchase order.
  4. 4A branch checks whether the PO exists and the total is within tolerance.
  5. 5Matches are inserted into the invoices table as approved.
  6. 6Mismatches are routed to ClickUp as a tagged exception task with the parsed data attached.

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 PostgresAny Postgres URL — query, write, migrate.
  4. 4
    Connect ClickUpDocs + tasks + chats in one workspace.
  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.