Bidlo 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.

98.9% timing coverage

Tool calls

20

+33% vs previous 7d13 saved production turns

p50 latency

169 ms

+1% vs previous 7d19 timed calls

p95 latency

211 ms

+7% vs previous 7d19 timed calls

Tool failures

0.0%

No change vs previous 7d0 excluding NoResults

No result

0.0%

No change vs previous 7d0 product outcomes

Calls / turn

1.5

+33% vs previous 7d69.2% of turns at 5+ calls

What changed

Material regressions ranked by severity and affected call volume.

Current 7 days compared with the previous equal window

Agent loop pressure

More turns are using five or more tools

69.2% now vs 53.8% previously (9 turns).

Inspect the affected turn sequences for repeated or avoidable tool selection.

Investigate

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
1 calls on 2026-10-015 calls on 2026-10-021 calls on 2026-10-046 calls on 2026-10-055 calls on 2026-10-06
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.

Sorted by current p95 latency
ToolCallsp50p95FailuresNo result
get_document_notes20+33% vs prior169 ms+1% vs prior211 ms+7% vs prior0.0%No change vs prior0.0%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.

Privacy safe
get_document_notesHJC181 msOct 6, 7:01 PM UTC

Outcome

Success

Thread

50ac87df…

Tool call

call_GZT…

Turn sequence

1 of 1

Turn state

Completed

get_document_notesHJC108 msOct 6, 6:53 PM UTC

Outcome

Success

Thread

50ac87df…

Tool call

call_nqD…

Turn sequence

1 of 4

Turn state

Completed

get_document_notesHJC177 msOct 6, 6:53 PM UTC

Outcome

Success

Thread

50ac87df…

Tool call

call_7n1…

Turn sequence

3 of 4

Turn state

Completed

get_document_notesHJC162 msOct 6, 6:53 PM UTC

Outcome

Success

Thread

50ac87df…

Tool call

call_Bl7…

Turn sequence

4 of 4

Turn state

Completed

get_document_notesHJC179 msOct 6, 5:39 PM UTC

Outcome

Success

Thread

eac20ce4…

Tool call

chatcmpl…

Turn sequence

11 of 17

Turn state

Completed

get_document_notesHJC169 msOct 5, 8:38 PM UTC

Outcome

Success

Thread

bf677805…

Tool call

chatcmpl…

Turn sequence

6 of 20

Turn state

Completed

get_document_notesHJC174 msOct 5, 7:29 PM UTC

Outcome

Success

Thread

22e6d03b…

Tool call

call_TzS…

Turn sequence

8 of 8

Turn state

Completed

get_document_notesHJC171 msOct 5, 7:27 PM UTC

Outcome

Success

Thread

05b735d6…

Tool call

call_qLW…

Turn sequence

2 of 8

Turn state

Completed

get_document_notesHJC101 msOct 5, 7:27 PM UTC

Outcome

Success

Thread

05b735d6…

Tool call

call_hTM…

Turn sequence

3 of 8

Turn state

Completed

get_document_notesHJC165 msOct 5, 5:50 PM UTC

Outcome

Success

Thread

d85df539…

Tool call

chatcmpl…

Turn sequence

12 of 12

Turn state

Completed

get_document_notesHJC174 msOct 5, 1:53 PM UTC

Outcome

Incomplete

Thread

921b777f…

Tool call

chatcmpl…

Turn sequence

4 of 11

Turn state

Incomplete

get_document_notesHJC169 msOct 4, 2:55 PM UTC

Outcome

Success

Thread

94d1ea5b…

Tool call

chatcmpl…

Turn sequence

2 of 3

Turn state

Completed

get_document_notesHJC211 msOct 2, 8:01 PM UTC

Outcome

Success

Thread

8d6df445…

Tool call

chatcmpl…

Turn sequence

1 of 19

Turn state

Completed

get_document_notesHJC114 msOct 2, 8:02 PM UTC

Outcome

Success

Thread

8d6df445…

Tool call

chatcmpl…

Turn sequence

5 of 19

Turn state

Completed

get_document_notesHJC175 msOct 2, 8:02 PM UTC

Outcome

Success

Thread

8d6df445…

Tool call

chatcmpl…

Turn sequence

9 of 19

Turn state

Completed

get_document_notesHJC114 msOct 2, 8:02 PM UTC

Outcome

Success

Thread

8d6df445…

Tool call

chatcmpl…

Turn sequence

11 of 19

Turn state

Completed

get_document_notesHJC185 msOct 2, 7:56 PM UTC

Outcome

Success

Thread

c1a79eab…

Tool call

chatcmpl…

Turn sequence

11 of 28

Turn state

Completed

get_document_notesRagle111 msOct 1, 4:50 PM UTC

Outcome

Success

Thread

75cd10c7…

Tool call

call_8va…

Turn sequence

1 of 2

Turn state

Completed

get_document_notesHJC119 msSep 30, 7:09 PM UTC

Outcome

Success

Thread

4cf27f28…

Tool call

chatcmpl…

Turn sequence

2 of 27

Turn state

Completed

get_document_notesHJC103 msSep 30, 7:09 PM UTC

Outcome

Success

Thread

4cf27f28…

Tool call

chatcmpl…

Turn sequence

3 of 27

Turn state

Completed

Source: Production chat_messages.tool_results (saved tool parts and detailed telemetry) Tool execution time starts after approval gates.