The decision layer,one endpoint away.
Lumi exposes the full Kauzio platform as one clean API. Plain JSON in, plain JSON out. Send any choice your users are about to make and get back a verdict, the case for and against, a reversibility score and a signed receipt your users can verify. 50 calls free every month, no card required. Paid plans unlock higher limits and 99.9% SLA.
50 calls free · 99.9% SLA on paid plans · No card to start
Kauzio LumiWhat teams build on Lumi
One API. Any product that decides for its users.
Lumi is not tied to a sector. If your product makes a choice on a user's behalf, the decision layer drops straight in.
Not on this list? If your product makes a call a user has to live with, Lumi fits.
/v1/decide{ verdict: "…" }Kauzio Lumi
Decision intelligence.
Drop signed verdicts and risk scores into your own product. Six engines behind one endpoint.
/v1/decide{ verdict: "…" }Simple by design
One API call.
Full decision analysis.
Send any decision as plain text. Get back structured analysis, bias flags, a recommended action and a confidence score, all in a single response.
Get your API keycurl -X POST \
https://api.kauzio.com/public/v1/brain/query \
-H "Authorization: Bearer kz_live_..." \
-H "Content-Type: application/json" \
-d '{
"question": "Should we expand to the US market in Q3?"
}'{
"question": "Should we expand to the US market in Q3?",
"answer": "Not yet. Two of your top three markets are still under-penetrated. Recommend a Q4 pilot with a 90-day proof window.",
"confidence": 0.74,
"data_context_loaded": true,
"source": "kauzio_brain",
"latency_ms": 312
}API Reference
Key endpoints
A selection of the most powerful endpoints in the Kauzio API.
/public/v1/brain/query/public/v1/consequence/simulate/public/v1/opposition/challenge/public/v1/witness/public/v1/verify/{id}Platform features
Built for production
API Keys & Rate Limiting
Generate multiple API keys per project, set rate limits, and monitor usage per key — all from the Lumi developer dashboard.
Webhooks
Subscribe to decision events, simulation completions, and certificate issuance. Every payload is HMAC-signed so you can verify it came from Kauzio.
Usage Analytics
Track API calls, latency, and error rates. Full audit log of every request made against your keys, retained for 90 days.
Signed Certificates
Every API response includes a verifiable certificate — a SHA-256 cryptographic proof of the decision. Anyone can verify any call, forever, without calling your servers.
Low Latency
Brain query in under 800 ms. Consequence simulation in under 2 s. Hosted on European infrastructure with a 99.9% SLA on paid plans.
Outcome Tracking
Send the outcome back when a decision plays out. The engines recalibrate. Every result makes the next call sharper — for you and every developer on the platform.
Works with any stack
Plain JSON in, plain JSON out. REST API works with any language or framework today. Python, Node.js, and Go SDKs are on the roadmap.
Witness any AI output
Not just Kauzio. POST any question + answer from ChatGPT, Claude, or your own model. Lumi timestamps and signs it — a verifiable record of what your AI said and when.
In the terminal
One API key. A whole Decision OS behind it.
Stripe gave developers payments. Twilio gave them communication. Kauzio gives them the Decision OS. One key, three signed endpoints, eight webhook events. Drop a verdict, a risk score and a tamper-proof certificate into anything you build.
One API. Every product you build.
Your code. One verdict away.
Lumi sits behind one REST endpoint. Drop a verdict, a risk score and a signed certificate into anything you ship: web, mobile, server, SaaS, AI agent, e-commerce, you name it.
Web app
browser → API
Mobile · iOS · Android
on-device call
Backend service
server-side decision
CLI · ops scripts
curl or SDK
AI agent
tool-call from LLM
E-commerce store
checkout, returns
SaaS product
embedded inside
Slack · Discord bot
chat-driven calls
Analytics pipeline
real-time scoring
API · /v1/decide
Web app
browser → API
Mobile · iOS · Android
on-device call
Backend service
server-side decision
CLI · ops scripts
curl or SDK
AI agent
tool-call from LLM
E-commerce store
checkout, returns
SaaS product
embedded inside
Slack · Discord bot
chat-driven calls
Analytics pipeline
real-time scoring
One API key. Pay per call, free to start. Every response ships a tamper-proof signed receipt you can verify with /v1/verify.
How the API flows
Seven stages. One signed response.
Every public endpoint runs the same seven-stage loop server-side and returns a verdict, a risk score and a verifiable certificate id.
Step 01
Suggested
A POST hits /brain/query with a decision
Step 02
Reviewed
Engines run, for / against compiled
Step 03
Approved
API returns verdict + risk + cert id
Step 04
Executed
Your app executes the decision downstream
Step 05
Measured
You PATCH outcome back to /decisions/:id
Step 06
Learned
Webhook delivered · models recalibrate
Step 07
Closed & fed back in
usage.recorded · loop closed for the call
Inside the Developer API
Production decision intelligence at API-call scale.
Three endpoints, eight webhook events, signed certificates. Drop the entire Decision OS into anything you ship.
API Keys
kz_live_* keys, scopes, rate limits
8 Webhook Events
HMAC-signed, retried, logged
Certificate Verify
Public verify endpoint, no auth
/brain/query
Grounded AI Q&A over user data
/consequence/simulate
Full cascade in one API call
/opposition/challenge
Get an honest second opinion’s reply
Usage Meter
Daily + monthly limits, real-time
Delivery Logs
Every webhook attempt, status, retries
99.9% SLA
On paid plans, status.kauzio.com
Pricing
Pay per call. Free to start.
Free · Indie · Studio · Enterprise.
50 calls free
See API pricing14-day free trial · No credit card · Cancel any time