Get Your First Proof in 5 Minutes
From zero to cryptographic behavioral attestation. All you need is an API key and curl.
Get Your API Key
Request a free API key. Free tier gives you 100 proofs per month — no credit card required. We'll email your key within 24 hours.
Once you have it, set it as an environment variable:
export SENTINEL_API_KEY="your_api_key_here"
Check the API Is Up
Verify the SENTINEL API is healthy (no authentication required):
curl https://api.starksentinel.com/health
You should see:
{
"status": "healthy",
"version": "1.1.0",
"timestamp": "2026-04-02T12:00:00.000Z"
}
Generate a Proof
Send behavioral observations to the /v1/prove endpoint. In this example, we're attesting that an AI agent's quality scores stay within control limits:
curl -X POST https://api.starksentinel.com/v1/prove \ -H "X-API-Key: $SENTINEL_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "observations": [95, 98, 92, 97, 100, 94, 96, 99], "baseline_mean": 96, "ucl": 110, "lcl": 80 }'
The response arrives in ~9ms:
{
"public_inputs": {
"num_observations": 8,
"baseline_mean": 96,
"final_ewma": 95,
"ucl": 110,
"lcl": 80,
"within_limits": true
},
"proof_bytes": "base64-encoded-stark-proof...",
"metadata": {
"generation_time_ms": 9,
"proof_size_bytes": 6761,
"security_level": 96
}
}
Notice: the response contains no raw observation values. The proof attests to the statistical result (EWMA within limits) without revealing the underlying data. This is the Prove-Don't-Share architecture.
Verify the Proof
Pass the proof_bytes and public_inputs from the prove response to /v1/verify. Verification is always free and unlimited.
curl -X POST https://api.starksentinel.com/v1/verify \ -H "X-API-Key: $SENTINEL_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "proof_bytes": "PASTE_PROOF_BYTES_HERE", "public_inputs": { "num_observations": 8, "baseline_mean": 96, "final_ewma": 95, "ucl": 110, "lcl": 80, "within_limits": true } }'
A valid proof returns:
{
"valid": true,
"public_inputs": {
"num_observations": 8,
"baseline_mean": 96,
"final_ewma": 95,
"ucl": 110,
"lcl": 80,
"within_limits": true
},
"metadata": {
"verification_time_ms": 2
}
}
Read the Public Inputs
The public_inputs object tells the story in plain integers — no cryptography PhD required:
| Field | Value | Meaning |
|---|---|---|
num_observations | 8 | 8 behavioral samples were attested |
baseline_mean | 96 | The expected baseline for the EWMA |
final_ewma | 95 | The smoothed average after all observations |
ucl | 110 | Upper bound of acceptable behavior |
lcl | 80 | Lower bound of acceptable behavior |
within_limits | true | Agent behavior stayed within bounds |
This is what you share with auditors, clients, and regulators. The cryptographic proof guarantees these numbers are authentic — but the numbers themselves are human-readable.
Next Steps
MCP Integration
Drop SENTINEL into any MCP-compatible AI agent framework. Three tools — prove, verify, health — with a five-minute setup. Install the SENTINEL MCP server and your agents can generate proofs natively.
WASM Verifier
Ship the open-source WASM verifier to your clients. They verify proofs entirely client-side in ~158ms — no network calls, no trust in SENTINEL required. True zero-trust verification.
Compliance Reports
Generate professional PDF attestation reports from any proof. File them with auditors for SOC 2, attach to contracts, or share with partners. Available on Pro and Enterprise plans.
Full API Reference
Dive deeper into request schemas, error codes, rate limits, and authentication. The API Docs cover everything you need for production integration.