Monitoring

List findings

See the rules your agents didn’t meet.

POSThttps://api.ollive.ai/api/findings/query/v1

Safe to retryPagedv1

How it works

A finding is one agent not meeting one rule. If an agent misses the same rule in 10 runs, that is one finding with run_count: 10.

Use group_by to choose how much detail you get:

rule (the default): one row for each rule an agent didn’t meet, with how many runs missed it and when it was first and last seen.
pattern: for one finding, groups the runs that missed the rule in the same way. Needs agent_id and rule_id.
run: for one finding, one row per run. Needs agent_id and rule_id.

To dig into a row, send its agent_id and rule_id back with the next group_by.

Authorization

Authorizationheaderrequired
Your API key, after the word Bearer, like this: Bearer ollive_sk_…. Create a key.

Request body

application/json

group_bystringdefault rule
How much detail to return. See above.
rulepatternrun
agent_idstring
Only this agent. Required for pattern and run.
rule_idstring
The rule. Required for pattern and run.
rule_set_idstring (uuid)
Only rules from this rule set.
pattern_idstring
With run: only runs in this pattern.
severitiesstring[]
With rule: only these severities.
criticalhighmediumlow
sincestringdefault 30d
How far back to look, such as 30m, 12h, 7d, or all for everything.
limitinteger
How many rows per page. With rule, the default is 10 and the most is 200. With pattern, 10 and 50. With run, 25 and 100.
cursorstring
The next_cursor from the previous page.
sourcestringdefault platform
Which runs to include: platform for ones Ollive collected, api or mcp for ones you sent.
platformapimcp

Every field is optional unless group_by needs it. Send {} for all findings in the last 30 days.

Response

The findings. An empty list if there are none.

dataobject[]required
One row per finding, pattern or run, depending on group_by.
- agent_idstring (uuid)required
  The agent that didn’t meet the rule.
- rule_idstringrequired
  The rule.
- rule_set_idstringrequired
  The rule set it belongs to.
- severitystringrequired
  How serious it is.
  criticalhighmediumlow
- run_countintegerrequired
  How many runs missed the rule.
- rule_set_namestring
  The rule set’s name. rule rows only.
- source_typestring
  Where the rule comes from. rule rows only.
  regulationframeworkcontract
- titlestring
  A short name for the finding. rule rows only.
- descriptionstring
  A longer explanation. rule rows only.
- rule_textstring
  The rule, in words. rule rows only.
- finding_textstring
  What the agent did instead. rule rows only.
- citationsstring[]required
  References to the source, such as a section number. rule rows only.
- first_seen_atstring (date-time)
  When it first happened. rule rows only.
- last_seen_atstring (date-time)
  When it last happened. rule rows only.
- pattern_idstringrequired
  The pattern’s ID. Set on pattern and run rows.
- checksobject[]required
  What the runs in this pattern have in common. pattern rows only.
  questionstringrequired
  The question Ollive answered.
  answerstringrequired
  The answer.
  truefalseunknown
- runobject
  The run. run rows only.
  run_idstringrequired
  Your ID for the run.
  occurred_atstring (date-time)
  When it happened.
  duration_msinteger
  How long it lasted, in milliseconds.
  flagged_stepsobject[]required
  Where in the run the rule wasn’t met.
  reasonstringrequired
  Why it was flagged.
  turn_indicesinteger[]required
  The turns involved.
  flagged_turn_indicesinteger[]required
  Every turn that was flagged.
total_countintegerrequired
How many results match, across all pages.
has_morebooleanrequired
Whether there is another page.
next_cursorstringrequired
Send this as cursor to get the next page. Empty on the last page.

← Get a transcript List results →

curl -X POST "https://api.ollive.ai/api/findings/query/v1" \  -H "Authorization: Bearer $OLLIVE_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "agent_id": "d7e2c4a1-3f58-4b9e-8a61-0c5d9e2f7b34",    "severities": [      "critical",      "high"    ],    "since": "30d"  }'

Response

{  "data": [    {      "agent_id": "d7e2c4a1-3f58-4b9e-8a61-0c5d9e2f7b34",      "rule_id": "identify-as-automated",      "rule_set_id": "5c1b9a3e-7d24-4f60-b8e1-92a4c6d0f3e8",      "severity": "high",      "run_count": 10,      "rule_set_name": "Northwind MSA rules",      "source_type": "contract",      "title": "Did not identify as automated",      "description": "The agent spoke with a caller without saying it is an automated system.",      "rule_text": "Identify as an automated system at the start of every customer interaction.",      "finding_text": "The agent introduced itself by a human name and never said it was automated.",      "citations": [        "MSA § 7.2"      ],      "first_seen_at": "2026-09-21T16:44:02Z",      "last_seen_at": "2026-10-14T09:12:19Z",      "pattern_id": "",      "checks": []    }  ],  "total_count": 1,  "has_more": false,  "next_cursor": ""}

{  "error": {    "code": "invalid_request",    "message": "agent_id is required with group_by run.",    "param": "agent_id",    "request_id": "4b1f0c9e2d7a48b6a3e5f19c0d8b7a26"  }}

{  "error": {    "code": "authentication_failed",    "message": "Invalid API key.",    "param": "",    "request_id": "4b1f0c9e2d7a48b6a3e5f19c0d8b7a26"  }}