appraisal is in the schema's top-level required list, but none of the seven conformance modules checks it. The only coverage today is the JSON Schema enum (exercised in the pytest suite) and a ...
trace-tests/src/trace_tests/modules/tr_rte.py at 46c9c0e2e9216d66e1ae10b1a78324f7ca08a1ed · agentrust-io/trace-tests
TRACE compliance test suite. Conformance tests for TRACE Certification. - agentrust-io/trace-tests
trace-tests/src/trace_tests/report.py at 46c9c0e2e9216d66e1ae10b1a78324f7ca08a1ed · agentrust-io/trace-tests
TRACE compliance test suite. Conformance tests for TRACE Certification. - agentrust-io/trace-tests
trace-tests/src/trace_tests/modules/tr_sig.py at 46c9c0e2e9216d66e1ae10b1a78324f7ca08a1ed · agentrust-io/trace-tests
TRACE compliance test suite. Conformance tests for TRACE Certification. - agentrust-io/trace-tests
trace-tests/src/trace_tests/runner.py at 46c9c0e2e9216d66e1ae10b1a78324f7ca08a1ed · agentrust-io/trace-tests
TRACE compliance test suite. Conformance tests for TRACE Certification. - agentrust-io/trace-tests
trace-tests/docs/levels.md at 46c9c0e2e9216d66e1ae10b1a78324f7ca08a1ed · agentrust-io/trace-tests
TRACE compliance test suite. Conformance tests for TRACE Certification. - agentrust-io/trace-tests
trace-spec/schema/trace-claim.json at 738358dfac58047eaf689ca824f9e15008aabf36 · agentrust-io/trace-spec
TRACE: Trust Runtime Attestation and Compliance Evidence. Open attestation standard for agentic AI governance. - agentrust-io/trace-spec
trace-spec/LIMITATIONS.md at 738358dfac58047eaf689ca824f9e15008aabf36 · agentrust-io/trace-spec
TRACE: Trust Runtime Attestation and Compliance Evidence. Open attestation standard for agentic AI governance. - agentrust-io/trace-spec
trace-spec/ROADMAP.md at 738358dfac58047eaf689ca824f9e15008aabf36 · agentrust-io/trace-spec
TRACE: Trust Runtime Attestation and Compliance Evidence. Open attestation standard for agentic AI governance. - agentrust-io/trace-spec
On evaluating agents – aunhumano
No amount of evals will replace the need to look at the data, once you have a evals good coverage you’ll be able to decrease the time but it’ll be always a must to just look at the agent traces to identify possible issues or things to improve.
[Proposal] Adding OpenTelemetry Trace Support to MCP · modelcontextprotocol modelcontextprotocol · Discussion #269
Pre-submission Checklist I have verified this would not be more appropriate as a feature request in a specific repository I have searched existing discussions to avoid duplicates Your Idea Abstract...
🚨 AI News | TestingCatalog on Twitter / X
OPENAI 🚨: Early look at an upcoming Agent Studio for building and hosting configurable, always-on 24/7 agents on ChatGPT. The "Hermes" feature is tightly coupled with the existing Workflows builder on the OpenAI Platform, and you will also be able to open your Agents in the… https://t.co/7U4m2vNS3z pic.twitter.com/tfPIGdXRAs— 🚨 AI News | TestingCatalog (@testingcatalog) April 21, 2026
Josh Clemm on Twitter / X
The agent trace is one of the most important new pieces of data in AIIt creates a flywheel.By combining the trace and the original context, you create new data that feeds directly into the next agent run. https://t.co/uylQQ4wiLd— Josh Clemm (@joshclemm) January 11, 2026
Agentic manual testing - Agentic Engineering Patterns
Agentic manual testing - Agentic Engineering Patterns
AT Protocol status pages
Status pages for ATProto apps and services
Arabica Social status
Graze Social Status
Blacksky Status
Eurosky Status
Bluesky down? Current problems and outages - US
Bluesky
