Continuous behavioral coverage for AI agents
Discover what your agent actually does in production, identify what you're not testing, turn real behavior into golden tests, and prevent regressions before they ship.
The problem
Traditional software has unit tests. But when you tweak a system prompt to fix a login bug, you risk silently breaking ten other capabilities. Maintaining a golden dataset by hand takes hundreds of hours engineering teams don't have.
The solution
AgentLasso.dev turns your production logs into a continuous testing suite — with zero machine learning knowledge required. We map your agent's code, capture real-world edge cases from live users, and auto-generate comprehensive testing rubrics.
Sign up and create a project. Your project's API key is in Settings.
export AGENTLASSO_API_KEY="<your-api-key>"Quickstart
One JSON object per request your agent handles. No SDK needed, or point your OpenTelemetry exporter at the same endpoint.
curl -X POST https://agentlasso.dev/api/v1/telemetry \
-H "x-api-key: $AGENTLASSO_API_KEY" \
-H "Content-Type: application/json" \
-d '{"user_input": "Refund order 44182",
"agent_output": "Refund issued.",
"tool_calls": [{"name": "stripe.refund"}]}'Send traces Run your golden tests on every pull request and fail the build when your agent regresses.
- name: Run AgentLasso golden tests
env:
AGENTLASSO_API_KEY: ${{ secrets.AGENTLASSO_API_KEY }}
AGENTLASSO_CAPABILITIES: process_refund # optional; empty = every test
run: node scripts/run-eval.mjsCI guide $0
Free forever
Perfect for developers building side projects.
$79
per month
For small engineering teams with an agent in production.
$299
per month
For scaling AI startups demanding deep regression testing.
Custom
talk to us
For organizations with strict security and massive telemetry scale.
Agent data is highly sensitive. AgentLasso.dev runs on a secure PostgreSQL architecture with row-level security, strict data isolation, and comprehensive PII scrubbing so user logs stay private.
Start evaluating for free