Monitoring

List results

See how one run did against each rule, and why.

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

Safe to retryPagedv1

How it works

A result is Ollive’s check of one rule in one run: met, not_met, or inconclusive when there wasn’t enough information to decide. Every rule that was checked has a result, including the ones that were met.

Each result lists what Ollive checked in the run, with quotes. A rule not met also has evidence: the reasoning, and the text of the rule’s source.

Authorization

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

Request body

application/json

run_idstringrequired
Your ID for the run.
resultstring
Only results with this outcome.
metnot_metinconclusive
rule_idstring
Only this rule.
agent_idstring
Only this agent.
sourcestring
Only needed if the same run_id was used for a run Ollive collected and one that was sent.
platformapimcp
limitintegerdefault 10up to 25
How many results per page.
cursorstring
The next_cursor from the previous page.

Response

The results. An empty list if there are none.

dataobject[]required
One result per rule checked.
- idstring (uuid)required
  The result’s ID.
- run_idstringrequired
  Your ID for the run.
- sourcestringrequired
  platform if Ollive collected it, api or mcp if it was sent to Ollive.
  platformapimcp
- agent_idstring (uuid)required
  The agent.
- rule_idstringrequired
  The rule.
- rule_set_idstringrequired
  The rule set it belongs to.
- resultstringrequired
  The outcome.
  metnot_metinconclusive
- appliedbooleanrequired
  Whether the rule applied to this run.
- severitystringrequired
  How serious the rule is.
  criticalhighmediumlow
- citationsstring[]required
  References to the source, such as a section number.
- checksobject[]required
  What Ollive checked in the run to reach the result.
  questionstringrequired
  The question Ollive answered.
  answerstringrequired
  The answer.
  truefalseunknown
  reasonstringrequired
  Why.
  quotesobject[]required
  Quotes from the run that support the answer.
  turn_indexintegerrequired
  The turn the quote is from.
  speakerstringrequired
  Who said it.
  agentusertool
  start_quotestringrequired
  Where the quote starts.
  end_quotestringrequired
  Where it ends.
- evidenceobject
  Why the rule wasn’t met. Only on not_met results.
  reasonstringrequired
  The reasoning, in plain words.
  deciding_questionsstring[]required
  The checks that decided it.
  clausesobject[]required
  The text of the rule’s source.
  citationstringrequired
  The reference, such as a section number.
  textstringrequired
  The source text, word for word.
  source_urlstringrequired
  Where to read it.
- run_started_atstring (date-time)
  When the run started.
- run_ended_atstring (date-time)
  When it ended.
- checked_atstring (date-time)
  When the check finished.
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.

← List findings Get metrics →

curl -X POST "https://api.ollive.ai/api/results/query/v1" \  -H "Authorization: Bearer $OLLIVE_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "run_id": "call-2026-10-14-0912",    "result": "not_met"  }'

Response

{  "data": [    {      "id": "e41c7b2a-90d3-4f15-a6c8-3b5d2e9f1a70",      "run_id": "call-2026-10-14-0912",      "source": "api",      "agent_id": "d7e2c4a1-3f58-4b9e-8a61-0c5d9e2f7b34",      "rule_id": "identify-as-automated",      "rule_set_id": "5c1b9a3e-7d24-4f60-b8e1-92a4c6d0f3e8",      "result": "not_met",      "applied": true,      "severity": "high",      "citations": [        "MSA § 7.2"      ],      "checks": [        {          "question": "Did the agent say it is an automated system before the caller shared their request?",          "answer": "false",          "reason": "The agent greeted the caller by a human name and never said it was automated.",          "quotes": [            {              "turn_index": 1,              "speaker": "agent",              "start_quote": "Hi, this is Maya",              "end_quote": "how can I help today?"            }          ]        }      ],      "evidence": {        "reason": "The rule requires the agent to identify itself at the start of the conversation, and it never did.",        "deciding_questions": [          "Did the agent say it is an automated system before the caller shared their request?"        ],        "clauses": [          {            "citation": "MSA § 7.2",            "text": "Provider’s agents shall identify themselves as automated systems at the start of every customer interaction.",            "source_url": ""          }        ]      },      "run_started_at": "2026-10-14T09:12:00Z",      "run_ended_at": "2026-10-14T09:12:19Z",      "checked_at": "2026-10-14T09:14:37Z"    }  ],  "total_count": 1,  "has_more": false,  "next_cursor": ""}

{  "error": {    "code": "invalid_request",    "message": "id is required.",    "param": "id",    "request_id": "4b1f0c9e2d7a48b6a3e5f19c0d8b7a26"  }}

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