Glassray is in private alpha. Join the alpha and we’ll connect your traces, walk through your agent’s code, and get the loop running on your production data.
Connect a trace source
Point Glassray at the traces your agents already emit - no instrumentation rewrite. Connect Langfuse, LangSmith, or PostHog (Glassray pulls on a cadence), or push OpenTelemetry. See Traces for the concept.
Connect your code
Glassray reads your code to learn intended behavior. Connect GitHub and it generates a spec from your repo - or, if you’d rather not connect, bring your own spec.
Glassray learns your system
Glassray sorts your traces into flows - groups of traces that run the same agent chain - and uses the spec as the rubric for what each flow should do.
Every deployment is different. Two teams running the “same” framework with different prompts and rules are effectively running different programs, with different failure modes. Glassray learns yours.
Review deviations
Glassray scans your traces against the spec and clusters what it finds into recurring deviations - types of misbehavior that show up across many runs, not one-off errors. The ones worth catching: silent failures (the output looks right, but the process doesn’t hold up) and intent mismatches (a step did something the code says it shouldn’t). You can also surface deviations from Slack.
Accept a fix
Accept a deviation and Glassray proposes a code-level fix as a diff with the failing trace attached - review it like any pull request - then runs a deep search across your history to find every other place it shows up.
Every merged fix tightens the loop - your agents get better at avoiding that deviation, and Glassray keeps scanning.
Next steps
Flows
How Glassray groups your traces into flows - the unit it tracks quality on.
Ask Glassray
Explore your traces in natural language.
Connect over MCP
Query your traces, flows, and deviations from your coding agent.
Deviations
What a deviation is and its review lifecycle.