Paytm Build for India AI Hackathon · Track 3

Kriyaby EthicCode

Chatbots answer tickets.
Kriya closes them.

An autonomous AI teammate for customer support. It investigates cases across systems, acts under written policy, verifies its own work and resolves the customer's issue. Anything risky goes to a person, with the whole case file.

Built and demonstrated on payment support workflows

Or talk to it, in Hindi or English. Voice by Sarvam AI.

How a case moves

Code runs the loop. The model is only asked for small, checked answers along the way.

  1. 01

    Understand

    Reads the complaint in plain words, Hindi or English.

  2. 02

    Investigate

    Pulls the customer's records with read-only tools.

  3. 03

    Decide

    Proposes a fix under a written, versioned policy.

  4. 04

    Act

    Runs the action only if the policy engine authorizes it.

  5. 05

    Verify

    Reads the systems back to prove it actually happened.

  6. 06

    Resolve

    Tells the customer what was done, with references.

Or escalate: when the policy says a person must decide (fraud, big amounts, a failed check), Kriya prepares the handoff, and carries out whatever the person approves.

Why a support lead can trust it

The model proposes. Policy decides.

Every action is checked against a written policy using data re-read from the source systems, not what the model said. Refunds, blocks and disputes need a single-use approval tied to the exact amount.

Nothing is claimed until it is verified.

After acting, Kriya reads the ledger back. If a refund fails, it does not tell the customer it worked. It hands the case to a person instead.

Every step is on the record.

The live trace shows each tool call, rule and check. The audit log is append-only and hash-chained, so any tampering shows.