Banking, NBFCs and insurance

Can we show the regulator who did what?

Loan checks, claims and collections now run with agents beside your people. LeafCraft records every step by every agent and every person, and keeps it in your environment.

One teamYour rulesYour memoryYour budget
Product screen · example dataLeafCraft console
Trusted by
MiVi
mediamint
Bhashini
Neurasix
Wyra

What's changing in banking, NBFCs and insurance

01

The regulator asks who did what

Loan decisions, claim settlements and collections now involve agents. The trail must show the person and the agent.

02

Fairness is a record, not a promise

If an agent decided about a customer, you must show the rule it followed and who checked it.

03

Model risk management applies to agents

A model change inside an agent is a change your model risk team must see and approve.

Two risks the layer removes

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

Agents you don't know about

In banking, NBFCs and insurance, 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 banking, NBFCs and insurance, the agents arrived before the rules did.

In banking, NBFCs and insurance, the question is never whether an agent can decide. It is whether you can show the regulator the rule it followed, the limit it stayed inside, the person who checked it, and the reason both gave. The layer keeps that record in your environment, unchanged, for as long as your retention policy says.

What the record answers hereEvery decision about a customer: the rule, the limit, the checker and both reasons.
How the layer works

AI and people, one team

Your banking, NBFCs and insurance 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
A log of what the agent did
A record of how it decided, who checked it, and why
Agents decide with shared service logins
Every agent has its own login and only its role's access
Model changes inside agents go unnoticed
Every model switch is a recorded change, tested on your own history
Regulator requests take weeks to assemble
Export the full trail in open formats, on demand
Silence is never a yesEstimated before it runsNothing erased after it's written
Product screen · example dataLeafCraft console
LeafCraft sells no agents, no models and no compute.
NeutralGains nothing from your choice of agent or modelYoursRuns in your cloud, VPC or on-premOpenAny model, any cloud, MCP and A2AEqualBought, built and people, same rules
Why that matters

Questions teams ask

Who signs off when the claim is large?

The adjuster you name. Routine claims run on their own within the agent's limit. Large or unusual ones go to that person, and if they do not reply in time, to the backup you named.

Can the data stay in our environment?

Yes. LeafCraft runs in your cloud account, your VPC or on-prem. Run records sit in your own Redis or Postgres, and keys stay in your vault.

Can an outside vendor's agent be tricked into breaking our rules?

Replies from outside agents and tools are read as data, not orders. That guardrail is always on and cannot be switched off. Outside agents also reach only the addresses you allow and get only the fields you choose.

Bring one banking, NBFCs and insurance process.

We'll map it with you: which roles are AI and which are people, who decides, who checks, what it costs and what gets recorded.