Replay every agent failure
Walk a failed production session turn by turn. Find where the decision chain went wrong and connect it to the change that caused it: a code deploy, a prompt edit, a tool that started returning different data, or a model update that never touched your diff.
Agents fail silently in production
Standard monitoring reports normal latency, normal error rates, and normal throughput while an agent works through a session incorrectly. A tool call at turn 3 feeds context that shapes the decision at turn 7, which reaches turn 9 as a confident wrong answer. No exception fires. No alert triggers.
Errors are not the failure signal
Datadog measured errors across LLM call spans in February 2026. The errors that do fire are mostly infrastructure noise. The failures that cost you, wrong decisions carried confidently to the final turn, produce no error at all.
- 5%
of all LLM call spans reported an error in February 2026
Datadog, State of AI Engineering 2026
- 60%
of those errors were exceeded rate limits, not reasoning or decision failures
Datadog, State of AI Engineering 2026
Dashboards tell you a score moved. Replay shows why.
Trace viewers and score dashboards
What you have today
- Show every span and every score, once you know where to look
- Tell you a score moved, not which change moved it
- The walk from moved score to causing change is manual
- No lineage connecting a session to the change that was live when it ran
Tessary session replay
Navigate session → turn → trace
- Traces the failing quality dimension back through the session to the suspect turn
- Each turn shows the full context, tool calls, and returned values the agent had
- Ties the failure to the change behind it, whether or not it shipped through your repo
- Works with existing Langfuse or Braintrust instrumentation
The Session-to-Turn-to-Trace model
Graders score every production session and watch the trend, so a degrading pattern surfaces the sessions worth replaying before a customer reports one. From there, Tessary makes the first pass and you verify.
Open the session timeline
The session timeline shows all turns in order. Tessary gives every production run a navigable structure: a session holds the full sequence of turns, each with its typed observations and tool calls.
Land on the suspect turn
Tessary traces the failing quality dimension back through the session and opens the turn where it first broke. You review the context the agent had at that point, retrieved documents, prior tool outputs, and accumulated state, rather than hunting for it turn by turn.
Verify the deviation
Replay is the verification pass. Confirm whether retrieved context went stale, a tool returned an unexpected schema, or accumulated state led to a wrong decision, with every tool call and the value it returned in front of you.
Trace to the change
Commit-SHA lineage tags every session to the code version running when it occurred, which covers the code-change case with the diff already attached. When no deploy lines up, Tessary correlates the causes that never touch your repo: a tool that started returning different data, an upstream agent's shift, or a model provider update.
The inputs to each decision
Standard error logs record whether each step completed. Replay records why each decision was made.
Full context at each turn
The retrieved documents, prior tool outputs, and accumulated state the agent had at that turn: the exact inputs to the decision, not just the output.
Tool calls and returned values
Every tool call made at each turn, with the parameters it received and the output that propagated forward to the next decision.
The deviation point
The specific turn where behavior first diverged from expected, visible as a gap between the context available and the output produced.
The change that was live
The commit SHA running when the session occurred covers the deploy case. Tool output shifts and model provider updates are correlated alongside it, so the trail does not end at your repo.
If you are running agents in production without span-level tracing, you are operating a black box. You can detect that something failed. You cannot reliably explain why.
Answered, plainly.
Related pages
Agent monitoring and alerting setup
Route grader trend breaks to Slack or PagerDuty, so a degrading pattern reaches the person who can fix it.
Multi-turn agent evaluation
A session can look fine one reply at a time and still fail the user's goal. Grade the whole conversation.
Regression detection
Catch a regression as a trend break in production, then trace it back to its cause.
Replay your first incident today
Connect Langfuse, Braintrust, or OTLP and read the session that failed before the next one fires. The trail ends at what changed, not at a moved score, and no credit card is needed to start.