Finance

Can I show my auditor who approved each payment, and why?

Agents already match invoices, chase payments and prepare the close. LeafCraft makes sure no one checks their own work, and every decision keeps both reasons.

One teamYour rulesYour memoryYour budget
Decision request in Microsoft Teams · example dataLeafCraft console

What's changing in finance

01

Agents now post, match and pay

Vendor updates put agents inside AP, AR and the close. They act under the vendor's defaults.

02

Auditors ask about the agent

Who approved this payment, and why, now includes the agent's reasoning.

03

The AI bill is a new line nobody owns

Finance is asked to budget for AI work without knowing the cost per task.

Two risks the layer removes

The agents you can't see, and the model that gets retired.

Agents you don't know about

In finance, agents arrive through vendor updates and team pilots. LeafCraft finds all of them, gives each an owner, and brings it under your rules or removes it.

How discovery works

A model that gets retired

An agent built straight on one model has to be rebuilt and re-approved when that model is retired or repriced. On LeafCraft you switch the model for that agent in config and keep everything else. Months and a budget, saved.

Agent tied to one model
  • The model is retired or repriced
  • Prompts, tests and sign-offs rebuilt
  • Months of work, a new approval cycle
  • The history stays with the old tool
MonthsA rebuild budget
Agent on LeafCraft
  • Pick another model for that agent
  • Switching is a config change
  • Test it against your own record first
  • Rules, limits, owner and memory stay
HoursNo rebuild
TimeHours to switch, not months to rebuild
CostNo rebuild budget, no new approval cycle
MemoryThe record carries over to the new model
Your choice of model

Why it matters now

In finance, the agents arrived before the rules did.

Finance is where the rules were always strict: maker and checker, limits by amount, a trail for every payment. Agents arrived without those rules. The layer brings them back for every agent, bought or built: a named owner, a limit set before the run, a separate checker and a record your auditor accepts.

How the layer works

AI and people, one team

Your finance team, with AI on the org chart.

Does the work
Decides
Checks
AI drafts. A person decides. Another agent checks.

The agent prepares the case. Your person makes the call and writes why. A separate audit agent checks the decision against your rules.

Same rules for every seatNo one checks their own workOne named ownerCost set before it runsBoth reasons recorded
No one checks their own workAgent or person. Maker and checker are never the same.
One named owner per decisionNever "the system".
Authority earned from the recordWidens with clean work. Narrows after mistakes.
People stay where they workSlack, Teams, WhatsApp (coming) or email. Their reply moves the work on.

What changes for you

Today
With LeafCraft
An agent matches and approves the same invoice
Maker and checker are never the same
Approvals above policy caught at audit
Limits per agent, widened only by the record
Audit trail assembled from five systems
One record with both reasons, exportable
AI cost seen on the invoice
Cost per task, per agent and per type, set before the close
Silence is never a yesEstimated before it runsNothing erased after it's written
Product screen · example dataLeafCraft console

Questions teams ask

Can an agent approve payments?

Only up to the limit its record has earned. Above that, the agent recommends and a person decides, and both reasons are kept.

Does this replace our ERP?

No. Agents read and write to the ERP you already run. LeafCraft adds the rules, the limits and the record.

Can our auditors read the record?

Yes. It is kept on your side, unchanged, and exports in open formats on demand.

Bring one finance process.

We'll map who does the work, who decides and who checks, set the cost limits and show you the record.