Reliability regression
create_database_view failures increased
20.0% now vs 16.7% previously across 5 calls; InvalidArguments is the leading code.
Inspect recent failures, then check the tool handler and upstream dependency logs.
InvestigateBidlo Status Frontend
Chat tool telemetry
Find slow, failing, and repetitive agent tools without exposing prompts, arguments, or outputs.
Detailed production timing active
6101 of 6166 saved tool calls include execution duration.
Tool calls
5
-17% vs previous 7d4 saved production turns
p50 latency
490 ms
+17% vs previous 7d5 timed calls
p95 latency
599 ms
-6% vs previous 7d5 timed calls
Tool failures
20.0%
+3.3 pts vs previous 7d1 excluding NoResults
No result
0.0%
No change vs previous 7d0 product outcomes
Calls / turn
1.3
+4% vs previous 7d75.0% of turns at 5+ calls
What changed
Material regressions ranked by severity and affected call volume.
Agent loop pressure
More turns are using five or more tools
75.0% now vs 60.0% previously (3 turns).
Inspect the affected turn sequences for repeated or avoidable tool selection.
InvestigateRegression checks require at least 3 calls in both windows. Latency is flagged at +20%; failure and no-result rates are flagged at +1 and +3 points respectively.
Execution volume
Successful calls, no-results, and failures combined.
Calls
Oct 1Oct 4Oct 7
Payload pressure
How often results exceed the 20 KB inline cap.
5.0%
handle rows / all calls
309 stored handles in this period. This is a payload-size proxy, not a one-to-one call classification.
Tool comparison
Each change is measured against the previous equal window; latency appears only where detailed timing exists.
| Tool | Calls | p50 | p95 | Failures | No result |
|---|---|---|---|---|---|
| create_database_view | 5-17% vs prior | 490 ms+17% vs prior | 599 ms-6% vs prior | 20.0%+3.3 pts vs prior | 0.0%No change vs prior |
Failure codes
Operational failures only; NoResults is excluded.
InvalidArguments1
Interpretation notes
The data has known edges that change what a chart means.
- Blocked loops are invisible
- Rate-limited and identical-argument calls are rejected before telemetry fires.
- NoResults is not downtime
- It remains a failed tool outcome, but is separated from runtime reliability here.
- Preview volume lives elsewhere
- Preview and threadless chats reach PostHog but are intentionally absent from Postgres.
- Latency is partially instrumented
- Saved tool parts provide production outcomes and volume; duration appears only on calls with detailed telemetry.
- Partial turns are retained
- They remain in volume counts but are excluded from failures and latency percentiles.
- Comparisons use equal windows
- Every delta compares the selected period with the immediately preceding period under the same tool and team filters.
Recent sanitized calls
Arguments, outputs, user IDs, and message content are never rendered.
create_database_viewHJC490 msOct 6, 7:14 PM UTC
Outcome
Success
Thread
3d7ad6cb…
Tool call
chatcmpl…
Turn sequence
8 of 9
Turn state
Completed
create_database_viewHJC554 msOct 6, 7:02 PM UTC
Outcome
Success
Thread
033cbc16…
Tool call
chatcmpl…
Turn sequence
5 of 5
Turn state
Completed
create_database_viewHJC430 msOct 6, 6:56 PM UTC
Outcome
Success
Thread
50ac87df…
Tool call
call_io2…
Turn sequence
1 of 1
Turn state
Completed
create_database_viewHJC211 msOct 4, 4:23 PM UTC
Outcome
InvalidArguments
Thread
e1179f50…
Tool call
chatcmpl…
Turn sequence
10 of 12
Turn state
Completed
create_database_viewHJC599 msOct 4, 4:23 PM UTC
Outcome
Success
Thread
e1179f50…
Tool call
chatcmpl…
Turn sequence
11 of 12
Turn state
Completed