← raksa.oneSign in
Raksa Guardrails

Careful AI for compliance teams, with guardrails you can prove.

Every Raksa agent runs under a Mandate, passes the Human Gate, is watched by Rex & Kira, and leaves its tracks in the Evidence Ledger, all inside your Data Boundary. Not promises in a policy document. A part of the product you can open and check.

Guardrail 1 of 5

Mandates

Every agent has a defined job.

A Mandate sets what an agent may work on and which of your policies it must follow. Asked to go beyond it, the agent declines and records the attempt.

Guardrail 2 of 5

The Human Gate

Nothing is final without a person.

Everything an agent produces is a draft until someone on your team approves it. Every approval records who, what and when, in the app or in Slack alike.

Guardrail 3 of 5

The Watchdogs

Rex and Kira review the other agents.

Two agents whose only job is oversight. They check the others' work against your policies and flag anything that looks wrong. People stay above both.

Guardrail 4 of 5

The Evidence Ledger

Every agent action is on the record.

An exportable, tamper-evident record of everything the agents did. Ready for an audit, a regulator, or your own board asking what the AI did last quarter.

Guardrail 5 of 5

The Data Boundary

Your data stays yours.

Your data is never used to train any AI model. It is hosted in the EU and UK, kept separate from every other customer, and can stay entirely inside your own cloud with the Sovereign edition.

One compliance engine, every surface

Anything the app can do, the API and agents can do, with the same guardrails attached. Wherever the work happens, the same approvals apply and the same record is kept. This is how it fits together:

Mandates, the Human Gate, the Watchdogs and the Evidence Ledger. Built into every layer, not bolted on.

  1. Where you work. The Raksa app, the API, Slack, and AI assistants. Same engine, same rules, wherever the work happens.
  2. The agents. Six agents do the groundwork. Two more, Rex and Kira, watch over them.
  3. The compliance engine. Assessments, data maps, RegWatch and posture. One engine, one record, everything connected.
  4. Knowledge. The laws, regulators, vendor profiles and country facts the agents draw on, kept current.
  5. The guardrails. Mandates, the Human Gate, the Watchdogs and the Evidence Ledger. Built into every layer, not bolted on.
  6. Your data boundary. Hosted in the EU and UK, never used to train AI. Or entirely inside your own cloud with Sovereign.

Two postures, two editions

Same product, same guardrails. The difference is where it runs.

Raksa Cloud

For most teams

  • Runs in our EU and UK cloud
  • Your data is never used to train AI
  • Data stays in the EU and UK
  • Published prices, start today

Raksa Sovereign

For regulated industries and strict data rules

  • Runs in your own cloud, in your own country
  • AI runs on your own keys
  • Your data never leaves your boundary
  • Priced per deployment, agreed with you

See the guardrails in action

Run a free assessment with no login, or book a walkthrough on your own scenario.