Bidlo Status Frontend

Chat tool telemetry

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

Detailed production timing active

6035 of 6100 saved tool calls include execution duration.

98.9% timing coverage

Tool calls

16

+60% vs previous 7d16 saved production turns

p50 latency

1 ms

No change vs previous 7d16 timed calls

p95 latency

264 ms

+37% vs previous 7d16 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

1.0

No change vs previous 7d93.8% 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

Latency regression

get_team_collections p95 slowed 37%

264 ms now vs 193 ms previously across 16 calls.

Open the tool view and inspect the slowest recent calls for a repeatable bottleneck.

Investigate

Agent loop pressure

More turns are using five or more tools

93.8% now vs 90.0% previously (15 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 2026-10-011 calls on 2026-10-022 calls on 2026-10-032 calls on 2026-10-043 calls on 2026-10-053 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

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.

Sorted by current p95 latency
ToolCallsp50p95FailuresNo result
get_team_collections16+60% vs prior1 msNo change vs prior264 ms+37% 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_team_collectionsHJC264 msOct 6, 8:04 PM UTC

Outcome

Success

Thread

ed7becf5…

Tool call

call_wuO…

Turn sequence

2 of 29

Turn state

Completed

get_team_collectionsBidlo1 msOct 6, 4:11 PM UTC

Outcome

Success

Thread

20a1bcaf…

Tool call

call_z3y…

Turn sequence

13 of 23

Turn state

Completed

get_team_collectionsTRP 20 msOct 6, 12:22 PM UTC

Outcome

Success

Thread

d7e232c7…

Tool call

call_Zaf…

Turn sequence

14 of 70

Turn state

Completed

get_team_collectionsHJC1 msOct 5, 7:51 PM UTC

Outcome

Success

Thread

8baa70ed…

Tool call

call_yWm…

Turn sequence

16 of 32

Turn state

Completed

get_team_collectionsHJC1 msOct 5, 7:36 PM UTC

Outcome

Success

Thread

10f9fa7b…

Tool call

call_lDc…

Turn sequence

2 of 3

Turn state

Completed

get_team_collectionsHJC0 msOct 5, 7:29 PM UTC

Outcome

Success

Thread

8baa70ed…

Tool call

call_fhk…

Turn sequence

2 of 48

Turn state

Completed

get_team_collectionsHJC1 msOct 4, 6:36 PM UTC

Outcome

Success

Thread

913d4f54…

Tool call

chatcmpl…

Turn sequence

2 of 10

Turn state

Completed

get_team_collectionsHJC1 msOct 4, 4:34 PM UTC

Outcome

Success

Thread

e1179f50…

Tool call

call_oXc…

Turn sequence

30 of 54

Turn state

Completed

get_team_collectionsHJC1 msOct 3, 8:13 PM UTC

Outcome

Success

Thread

312f49c4…

Tool call

chatcmpl…

Turn sequence

3 of 7

Turn state

Completed

get_team_collectionsHJC1 msOct 3, 4:54 PM UTC

Outcome

Success

Thread

fd14dc19…

Tool call

chatcmpl…

Turn sequence

4 of 6

Turn state

Completed

get_team_collectionsHJC1 msOct 2, 7:47 PM UTC

Outcome

Success

Thread

c1a79eab…

Tool call

chatcmpl…

Turn sequence

1 of 24

Turn state

Completed

get_team_collectionsHJC1 msOct 1, 1:11 PM UTC

Outcome

Success

Thread

ee519c74…

Tool call

chatcmpl…

Turn sequence

1 of 19

Turn state

Completed

get_team_collectionsRagle1 msSep 30, 8:06 PM UTC

Outcome

Success

Thread

3613dd75…

Tool call

call_UYC…

Turn sequence

16 of 19

Turn state

Completed

get_team_collectionsHJC0 msSep 30, 7:10 PM UTC

Outcome

Success

Thread

4cf27f28…

Tool call

chatcmpl…

Turn sequence

16 of 27

Turn state

Completed

get_team_collectionsHJC0 msSep 30, 6:19 PM UTC

Outcome

Success

Thread

6719d8ef…

Tool call

chatcmpl…

Turn sequence

3 of 5

Turn state

Completed

get_team_collectionsTRP 21 msSep 30, 2:44 PM UTC

Outcome

Success

Thread

a7197a7d…

Tool call

call_X8z…

Turn sequence

8 of 14

Turn state

Completed

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