Expensify Report Review Agent with Claude Code

Each line is checked against two things at once: the policy you wrote in plain English and the Expensify policy the report was submitted under. Claude Code reads context thoroughly before concluding anything, which is what a per item, per category, receipt status pass over eleven lines actually takes. The verdict at the end is four words or a short list.
Loading preview…
Free to start · guided setup · switch agents any time.

Live demo

Watch it work before it's live

Run a staged conversation — no account needed. The agent handles it for real while a simulated world answers its tool calls; nothing touches real accounts, and nothing is actually sent.

Berlin Sales Trip, 4 to 7 May

Marta KowalczykSales Travel Policy (EU)

Eleven line items totalling 1,842.60 EUR. Flights Warsaw to Berlin at 312.40 EUR, hotel for four nights at 688.00 EUR, seven meals between 14.20 and 61.90 EUR, and airport taxis at 74.00 EUR. Every item has a receipt attached and each dinner sits under the 75.00 EUR limit.

What you'll need

Set up in minutes

Using this template drops you into a guided setup. It asks exactly this, nothing else:

  1. Connect Expensify

    One sign-in. The agent acts through your account, scoped to what this template uses.

  2. Connect Slack

    One sign-in. The agent acts through your account, scoped to what this template uses.

  3. Expense policy

    The spending rules a report has to satisfy - per item and per category limits, what always needs a receipt attached, categories you never reimburse, how far back a submission can be dated, and what makes a report worth a proper read rather than a rubber stamp.

  4. Runs on Claude Code

    Preselected for this page — connect your Claude Code account during setup, or switch to NoClick's built-in models with one click.

  5. Watch it handle a test run

    A staged conversation against a simulated world — then it’s live.

A considered pairing

Why Claude Code for this agent

Two policies, one pass

Your written rules cover the judgement calls a rule engine cannot and the Expensify policy covers the mechanical ones. Both have to be in view while a single line is judged.

Both numbers, side by side

A flag names the item, the merchant, the date and the amount next to the limit it crosses. Over budget with no figures gives the approver nothing to act on.

Good to know

Before you fork

What if my written policy contradicts the Expensify policy?

It flags the line and says what it could not settle rather than picking a winner, which is the right outcome. Contradictions surface as NOT SURE lines naming what a person has to check. A few of those in the first fortnight is usually how a team discovers their written policy had drifted from the configured one.

Other editions

Run it with a different agent

OpenAICodexopencodeopenclawhermesMore Claude Code agents

Make it yours

Put Expensify Report Review Agent to work on Claude Code.

Free to start. Guided setup, a staged test run, and a workflow you can change at every step.