Playbooks: ready-made finance proceduresTransform your finance work, beyond automation
Playbooks are finance jobs your AI runs for you, end to end: the month-end close, expense review, budget control, supplier clean-up.
 1.svg){kind=small}
A prompt does a task. A playbook does the job
Month-end close, budget forecasting, multi-entity reporting - recurring jobs that took days to complete are now a conversation away.
You describe the outcome, then review the run. The playbook works the whole thing end to end, then brings it back for you to review.
The procedure comes with the playbook: what to check, in what order. Anyone with the permissions can run it.
Chase the receipt, merge the duplicate supplier, change the card limit - each ready to run on your approval.
Instead of chasing, checking and building reports, your team spends that time on decisions and strategic work.
“The MCP integration between Payhawk and Claude has proven to be a highly effective enhancement to our operational setup. It enables substantial time efficiencies, provides dynamic reporting capabilities, and simplifies data access and organization.”
Run playbooks where you already work
Connect your account once, then ask for any playbook straight from Claude and ChatGPT.
Ask for any playbook in the Payhawk web or mobile app. Nothing to connect and nothing for IT to set up.
Choose from a variety of pre-build playbooks
Whoever owns the job, there's a playbook for it: the controller closing the month, the CFO checking the budget, the admin clearing up after a leaver.
Month-end close
Close the month: everything coded, documented, reviewed and export-ready, then the export run under your confirmation, its outcome read back per expense from the accounting system, and a shareable close summary.
Expense review
Review a batch of expenses for correct coding, policy and documentation before approval.
Multi-entity (group) rollup
Assemble a consolidated view across the entities the user can access. A few tools consolidate across accounts in one call; for the rest the assistant pulls each entity and combines the results itself.
Spend report
Produce the spend report for any period the user names, as one answer carrying the narrative, the key figures, the period-on-period comparison and the charts.
Cash runway and top-up timing
Estimate when the available balance will run low, per currency and entity, so funds arrive in time. It forecasts when money needs to be there; it never moves money.
Payment run coverage
Answer whether the money will be there to pay the bills falling due by a deadline, per currency, and if not how much to load and by when. It checks funding; it never pays anything.
Cash position overview
Show the current cash position per balance type, currency and entity, with recent movements and, where history is available, the balance trend.
Finance benchmarking (peers and entities)
Answer whether the account's spend mix, expense process, card programme and product adoption are normal for a company like theirs, and which of their own entities is lagging.
Your permissions travel with the job
A playbook runs as you, inside Payhawk's own controls. It cannot reach data your role cannot see, nor take an action your role cannot take.
Runs with your own Payhawk permissions, never wider
Previews every change, writing nothing until you confirm
Names the actions it can take before it starts
Records every action in your normal audit trail
Never starts a payment or a transfer
FAQ
A playbook is a finance job written down as a set of steps. Ask for one of Payhawk's official playbooks by name, and your AI Assistant works through those steps in order, the same way every time.
A plain question gets you data back. A playbook carries Payhawk's procedure for the job: which checks to run, in what order, what finished looks like. That procedural knowledge is what separates a playbook from a general connection to your finance data.
Yes, in the parts that need judgement. The sequence of steps is declared up front rather than improvised, and the steps that analyse, such as budget burn or benchmarking, call Payhawk Insights for the reasoning. Every step that would change your data still waits for your confirmation.
No change happens without your confirmation. Each playbook names the actions its steps can take before it runs, works only within your own Payhawk permissions, and records everything it does in your normal audit trail.
You are offered the playbooks your own permissions allow, resolved role by role and account by account. A colleague with different permissions, or working in a different entity, sees a different list.
Yes. Describe the job in your own words and Payhawk drafts the complete playbook for you, built only from actions you can already take. Nothing is saved until you review it and confirm.
No. An ordinary question, such as how many expenses are pending your review, gets an ordinary answer. A playbook runs only when you ask for the job itself, on request, never on a schedule.
In the Payhawk Web Portal, the Payhawk Mobile App, or the AI Assistant your company already uses. There is nothing for IT to configure first.