Use case · Drift investigation
Behavior feels different. Where did it drift?
Drift is the change no code review catches — same code, different outputs. Ask your coding agent to read traces you have already exported, turn them into checks, and compare against your expected behavior. EvalGlass makes drift a delta you can read.
Inspect recent traces and tell me where behavior drifted from our expected checks.
What it checks
trace-derived cases vs. your expected behavior · tone · grounding · tool-call patterns. It uses traces you have already exported (OpenTelemetry / OpenInference / local JSON) — no SDK on the evaluation path (a live pull is a separate, experimental opt-in lane). It is a comparison you run, not continuous monitoring — and evalglass watch next lets you schedule it: one run against a baseline, a typed drift.json, then exit (built for cron or CI, not a resident daemon). It flags a regression only when the runs are comparable and the paired interval clears zero — otherwise the delta is within_noise; not_comparable or a missing baseline is reported as exactly that. The watcher adds no exit class and never promotes the baseline.
The scorecard
Verdict informational — a comparison on exported traces, not a live monitor. Illustrative example, not a measured result.
What it will not claim
EvalGlass does not watch your traffic. It reads traces you export and compares them to your checks — a deliberate run, not an always-on monitor. evalglass watch next can schedule that comparison as a one-shot on cron or CI, but it never watches live traffic — and a no-comparable-regression result never means quality is fine. No false green →
Core compares exported traces to your checks and reports where behavior drifted. It measures drift against the checks you already have.
When the drift is real but its cause is unclear — behavior moved and the checks cannot say why —
EvalGlass Intelligence private preview diagnoses why behavior changed — reconstructing the path and validating the cause through controlled replay — and returns a Core-runnable regression. Discuss consequential failures →
Core remains usable on its own.
Ask your coding agent.
Evaluate my agentic app using EvalGlass.
Related