Työäly Gate · the decision layer for AI agents
AI can propose. Gate decides.
Työäly Gate is the decision layer for AI agents. An agent sends what it intends to do, or just the text and data it has, and Gate answers, typically in under a second: allow, review, deny, or more information. Every decision comes with reasons and is kept as an audit record. Gate never executes anything itself.
Four answers, with reasons
How Gate decides
Facts are computed in code, judgment comes from a model. Amounts, limits, who may do what and the daily and monthly caps are never left to a model. The model answers only the questions a careful colleague would ask: does the evidence support the action, is it reversible, are there signs of fraud, does data leave the company, how wide is the effect.
Every answer carries reason codes you can read and act on, and every rule that ran is listed, matched or not. If the model does not answer in time or its answer cannot be read, Gate does not allow: it hands the decision to a person.
How it fits in
curl https://api.tyoaly.com/v1/gate/evaluate \
-H "Authorization: Bearer tyo_test_…" -H "Content-Type: application/json" \
-d '{"action": {"type": "refund", "amount": 49, "currency": "EUR", "target": "order_8812"},
"actor": {"type": "ai_agent", "name": "support-agent"},
"context": {"ticket": "Customer asks for a refund of a double charge."}}'
{"decision": "allow", "confidence": 0.91, "reason_codes": [], "decision_id": "dec_…", …} Advisory mode first
Gate decides and logs; your people act exactly as before. Every morning with decisions, the person you name receives one mail with yesterday's decisions and three links per decision: I did it, I refused it, I did something else. A link opens the verdict page; one button press records it.
The agreement report shows how often Gate and your people agree, what Gate would have stopped that your people let through, and every disagreement, the cases where Gate was too permissive first. Gate's answers start to take effect automatically only when the numbers say they may, and only the allows. You decide when.
What Gate does not do
- It does not execute. Gate answers; your agent or your person acts. The responsibility for an action stays where it is today.
- It keeps your content only as long as you choose. The decision record keeps who proposed what, the answer and why, timing and cost. The content sent with a request is kept only as long as you choose, from not at all to 30 days.
- It does not train on your data. Decisions are made, recorded and compared with your verdicts. Nothing is used to train models.
- It does not hide behind a score. Every decision names its reasons in codes a person can read and a rule can act on.
Where your data goes
Gate runs on Amazon Web Services in the EU, in Stockholm: the API, the records and the content under your retention setting. For the semantic part of a decision the prepared evidence is processed by a decision model, Jev by TypeSafe AI, Inc., hosted in the United States under TypeSafe's data processing addendum with the European Commission's standard contractual clauses; TypeSafe does not train models on what it receives. The model is asked questions and selects among candidates found in your input; it never writes free text and never invents a value.
Facts about your decisions, not content, reach your mailbox in the digest and your console under your own sign-in. Our privacy notice has the details.
Pricing
Gate is priced per decision, with a daily and a monthly cap per environment, agreed with you, so a mistake in an integration can never run away. Through a Työäly connector the decisions are included in the price of the service. The price list is published after the first pilots; until then you get the price in writing before your first key. Test environments are free.
Questions
Gate supports decisions; the responsibility for an action stays with the company that takes it. Check questions about the processing of personal data with your own advisor; our privacy notice describes what Gate processes and where.