Chat tool telemetry

Find slow, failing, and repetitive agent tools without exposing prompts, arguments, or outputs.

PeriodToolTeam

Detailed production timing active

495 of 570 saved tool calls include execution duration.

86.8% timing coverage

Tool calls

+73% vs previous 7d8 saved production turns

p50 latency

328 ms

Timing not instrumented17 timed calls

p95 latency

1.1 s

Timing not instrumented17 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

2.4

-14% vs previous 7d100.0% 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

Stable against baseline

No material tool regressions detected

Tools with enough activity were checked for higher failure rates, available p95 latency regressions, more no-results, and increased loop pressure.

Review the tool comparison for absolute hotspots that may still need a product threshold.

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

Aug 1Aug 4Aug 7

Payload pressure

How often results exceed the 20 KB inline cap.

Unavailable

handle rows / all calls

The handle store could not be read with the current credentials.

Tool comparison

Each change is measured against the previous equal window; latency appears only where detailed timing exists.

Sorted by current p95 latency

Tool	Calls	p50	p95	Failures	No result
app_write_file	19+73% vs prior	328 msNo prior timing	1.1 sNo prior timing	0.0%No change 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.

Privacy safe

app_write_fileHJC136 msAug 7, 3:55 PM UTC

Outcome

Success

Thread

28ab5468…

Tool call

call_dYc…

Turn sequence

8 of 11

Turn state

Completed

app_write_fileHJC353 msAug 7, 3:55 PM UTC

Outcome

Success

Thread

28ab5468…

Tool call

call_eR0…

Turn sequence

9 of 11

Turn state

Completed

app_write_fileBidlo206 msAug 6, 9:16 PM UTC

Outcome

Success

Thread

1ab2ebd7…

Tool call

call_lEY…

Turn sequence

15 of 19

Turn state

Completed

app_write_fileBidlo294 msAug 6, 9:16 PM UTC

Outcome

Success

Thread

1ab2ebd7…

Tool call

call_6rv…

Turn sequence

16 of 19

Turn state

Completed

app_write_fileBidlo390 msAug 6, 9:16 PM UTC

Outcome

Success

Thread

1ab2ebd7…

Tool call

call_5ow…

Turn sequence

17 of 19

Turn state

Completed

app_write_fileHJCNot timedAug 6, 5:59 PM UTC

Outcome

Success

Thread

cca85bae…

Tool call

call_LdZ…

Turn sequence

10 of 14

Turn state

Completed

app_write_fileHJCNot timedAug 6, 5:59 PM UTC

Outcome

Success

Thread

cca85bae…

Tool call

call_lOx…

Turn sequence

11 of 14

Turn state

Completed

app_write_fileHJC203 msAug 6, 5:45 PM UTC

Outcome

Success

Thread

1c6b6c3e…

Tool call

call_ShV…

Turn sequence

22 of 39

Turn state

Completed

app_write_fileHJC401 msAug 6, 5:45 PM UTC

Outcome

Success

Thread

1c6b6c3e…

Tool call

call_LsO…

Turn sequence

24 of 39

Turn state

Completed

app_write_fileHJC182 msAug 6, 5:40 PM UTC

Outcome

Success

Thread

2d1997bc…

Tool call

call_REQ…

Turn sequence

3 of 6

Turn state

Completed

app_write_fileHJC1.1 sAug 6, 5:40 PM UTC

Outcome

Success

Thread

2d1997bc…

Tool call

call_nDP…

Turn sequence

4 of 6

Turn state

Completed

app_write_fileHJC206 msAug 6, 5:37 PM UTC

Outcome

Success

Thread

2d1997bc…

Tool call

call_ut7…

Turn sequence

24 of 27

Turn state

Completed

app_write_fileHJC364 msAug 6, 5:37 PM UTC

Outcome

Success

Thread

2d1997bc…

Tool call

call_84w…

Turn sequence

25 of 27

Turn state

Completed

app_write_fileBidlo155 msAug 6, 1:05 PM UTC

Outcome

Success

Thread

66970855…

Tool call

call_ujO…

Turn sequence

11 of 15

Turn state

Completed

app_write_fileBidlo351 msAug 6, 1:05 PM UTC

Outcome

Success

Thread

66970855…

Tool call

call_CWZ…

Turn sequence

12 of 15

Turn state

Completed

app_write_fileBidlo442 msAug 6, 1:05 PM UTC

Outcome

Success

Thread

66970855…

Tool call

call_p5Q…

Turn sequence

13 of 15

Turn state

Completed

app_write_fileBidlo175 msAug 3, 2:20 PM UTC

Outcome

Success

Thread

fb5e59c8…

Tool call

call_BTQ…

Turn sequence

7 of 11

Turn state

Completed

app_write_fileBidlo337 msAug 3, 2:21 PM UTC

Outcome

Success

Thread

fb5e59c8…

Tool call

call_Jt6…

Turn sequence

8 of 11

Turn state

Completed

app_write_fileBidlo328 msAug 3, 2:21 PM UTC

Outcome

Success

Thread

fb5e59c8…

Tool call

call_1ZN…

Turn sequence

9 of 11

Turn state

Completed