Agent loop pressure
More turns are using five or more tools
100.0% now vs 0.0% previously (1 turns).
Inspect the affected turn sequences for repeated or avoidable tool selection.
InvestigateBidlo Status Frontend
Chat tool telemetry
Find slow, failing, and repetitive agent tools without exposing prompts, arguments, or outputs.
Detailed production timing active
6058 of 6123 saved tool calls include execution duration.
Tool calls
1
-80% vs previous 7d1 saved production turns
p50 latency
625 ms
+63% vs previous 7d1 timed calls
p95 latency
625 ms
-52% vs previous 7d1 timed calls
Tool failures
0.0%
-20.0 pts vs previous 7d0 excluding NoResults
No result
0.0%
No change vs previous 7d0 product outcomes
Calls / turn
1.0
-20% vs previous 7d100.0% of turns at 5+ calls
What changed
Material regressions ranked by severity and affected call volume.
Regression 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
307 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 |
|---|---|---|---|---|---|
| manage_sharing | 1-80% vs prior | 625 ms+63% vs prior | 625 ms-52% vs prior | 0.0%-20.0 pts vs prior | 0.0%No change vs prior |
Failure codes
Operational failures only; NoResults is excluded.
No operational failures
in the selected view
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.
manage_sharingBidlo625 msOct 4, 5:29 AM UTC
Outcome
Success
Thread
3ed32d55…
Tool call
call_62y…
Turn sequence
6 of 29
Turn state
Completed