Autonomy you can audit.
Run correctly, or stop.
Every lending leader we talk to carries the same fear, whether they say it out loud or not: the system will make a decision no one watched, it will go wrong, and it will be their name on the failure, not the vendor’s and not the model’s.
That fear is why “let AI run the book” lands as a threat rather than an offer. The pitch is autonomy. The thing you actually hold is accountability, to a regulator, to a board, to borrowers. Autonomy handed over without accountability is exposure.
So here is the promise we’re building Lokta to keep, and the whole of it: the book can run itself, but it never runs unsupervised. AI operates your loan book at machine speed. Every decision that moves money stays deterministic, policy-bounded, and on the record. We don’t remove the risk. We put you in command of it.
These principles guide how we build and evaluate Lokta. Ask us to demonstrate the controls on the workflows your team will run.
Most AI lending pitches ask you to trust a model you can’t inspect. We think that’s backwards, so we hold ourselves to a single governing rule: zero-magic AI. Every AI claim ships with its guardrail. If we can’t show the guardrail, we don’t make the claim.
Deterministic before clever.
Governed before fast.
On the record, always.
The order, spelled out.
Deterministic core, governed edge
AI operates at the edge and proposes. The deterministic core decides.
A deterministic core is the part of the system whose math is fixed and reproducible: the same inputs always produce the same result, and you can read exactly why. The ledger, the loan accounting, the balance you owe: none of that is ever guessed by a model. Around that core, AI works at the edge (it reads the borrower, drafts the next collections action, prices a settlement offer) then hands that proposal to the core, which resolves it through logic you can inspect.
The guardrailEvery money-moving decision passes deterministic checks that a lender can inspect and reproduce.
Policy-bounded agents, run correctly, or stop
Agents act only inside an explicitly declared, versioned policy envelope. An agent that would step outside its bounds stops rather than guesses.
A policy-bounded agent is one whose room to act is written down in advance: the products it can touch, the settlement bands it can propose within and the servicing actions it may request. That envelope is versioned. You know which rules were live, and when. A case outside those limits stops and goes to a person for review.
The proofYour team can inspect the policy document, review its version history and approve changes to the limits.
Nothing changes silently
Every change to a live policy, price, or borrower state carries maker-checker, and leaves the record of why.
Maker-checker is the control where one party proposes a change and a different party approves it before it takes effect. We apply it to the things that matter: a policy going live, a price moving, a borrower’s state changing. And we capture the actor, the evidence, and the before-and-after as the change happens. The change completes only when its evidence has been recorded. That is what audit-by-design requires.
The guardrailThe evidence is built into the state change, not written afterward. That’s how you prove (to a board, to the RBI, to yourself) that you were in command, on the day it mattered.
One canonical model, no reconciliation
Servicing, collections and accounting use the same definitions of the loan.
An ontology, here, is the single agreed definition of what a loan, a borrower, a payment, and a policy are: used identically everywhere in the system. Servicing, collections and the AI edge use the same canonical model after the approved loan arrives from your LOS. Most stacks don’t work this way: they stitch separate systems together and spend forever reconciling them, and reconciliation is where drift, disputes, and quiet errors live.
A shared recordA shared loan model lets each team trace its figures to the same events and audit history.
The book learns inside the guardrails
Outcomes feed variant generation: policy, pricing, offers. Winners are promoted only after evaluation, and only inside the envelopes above.
This is the part people mean when they say a loan book can sharpen itself the more it lends. Real repayment and recovery outcomes feed the generation of candidate policies. Those candidates are evaluated. The ones that hold up are promoted. But the loop is not free-running: a promoted policy is version-pinned, evidence-backed, and human-approved before it goes live. It moves within the same policy envelope as everything else, and it changes under the same maker-checker as everything else.
The guardrailSelf-improving, never self-unsupervised. This is where “the book sharpens itself the more it lends” earns the right to be said, because it happens on the record, inside bounds a human signed off on. No policy rewrites itself in the dark.
What that looks like when it works.
Example: an agent proposes more frequent borrower contact, and the core checks it against the permitted contact policy.
Agentproposes
An agent watches the early-warning signals on a borrower segment: first-EMI bounces and broken promises-to-pay creeping up at day 5, not day 90. It drafts a proposal: pull outreach forward to the first missed debit, tighten the follow-up cadence, and route the riskiest accounts to field visits. On the numbers in front of it, the proposal looks good.
The corebounds it, and stops the rest
The core checks the proposal against the live, versioned policy envelope, and the tightened cadence crosses a borrower-contact ceiling the compliance team set. It limits the cadence to the permitted ceiling and routes the exception to a named human approver.
The head of collectionssigns off
She sees the full picture: what the agent proposed, why, what the core allowed, what it refused, and the rule that drew the line. She approves the bounded version. She declines the part that crossed the ceiling.
One immutable recordproves it
Every step (the proposal, the core’s decision, the boundary that held, her sign-off) is written to one immutable record, as it happens. Months later, if anyone asks who decided to tighten that outreach cadence and on what basis, the record shows the decision and its basis.
AI proposes. The core decides. The record proves it.
Why the discipline is also the economics.
A servicing policy needs to account for risk as well as yield. Test candidates against both, keep the evidence and require approval before a change goes live. The goal is to improve profit per loan disbursed without taking on risks the lender has not accepted.
As agents take on more servicing work, you need to see which actions they proposed, which rules applied and who approved each change.
That is autonomy you can audit: work carried out within limits you set, with a record you can answer for.
We don’t remove the risk. We put you in command of it: and on the record for it.
In lending, the autonomy you can audit is the only autonomy that scales.
We’re working with a small set of co-design partners in 2026: lenders, fintechs, and LSPs who want to shape an agent-native loan book with the team behind Apache Fineract, the open-source lending core the industry runs on. If that’s the book you want to run, we’d like to hear how you’d stress-test these five principles.