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

-87% vs previous 7d4 saved production turns

p50 latency

234 ms

Timing not instrumented5 timed calls

p95 latency

413 ms

Timing not instrumented5 timed calls

Tool failures

20.0%

-41.5 pts vs previous 7d1 excluding NoResults

No result

0.0%

No change vs previous 7d0 product outcomes

Calls / turn

1.3

-84% vs previous 7d50.0% 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
get_database_view	5-87% vs prior	234 msNo prior timing	413 msNo prior timing	20.0%-41.5 pts vs prior	0.0%No change vs prior

Failure codes

Operational failures only; NoResults is excluded.

Unknown1

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_database_viewTexas Materials413 msAug 3, 6:42 PM UTC

Outcome

Success

Thread

6ef49cff…

Tool call

call_nhN…

Turn sequence

5 of 6

Turn state

Completed

get_database_viewTexas Materials208 msAug 3, 5:33 PM UTC

Outcome

Success

Thread

1765bb64…

Tool call

call_j9m…

Turn sequence

10 of 20

Turn state

Completed

get_database_viewTexas Materials86 msAug 3, 5:35 PM UTC

Outcome

Unknown

Thread

1765bb64…

Tool call

call_xQz…

Turn sequence

19 of 20

Turn state

Completed

get_database_viewBidlo374 msAug 3, 2:29 PM UTC

Outcome

Success

Thread

3ecd1f11…

Tool call

call_WuN…

Turn sequence

1 of 3

Turn state

Completed

get_database_viewBidlo234 msAug 3, 2:19 PM UTC

Outcome

Success

Thread

839363e5…

Tool call

call_v7w…

Turn sequence

1 of 3

Turn state

Completed