Oneprofile · Schema

AgentLearningReadSchema

One learning: a one-line rule the agent follows on every output.

Sales OutreachAI ResearchEmail AutomationLinkedIn OutreachCRM Integration

Properties

Name Type Description
all_sequences boolean Whether every sequence's writer follows it, rather than one agent.
batch_id object The release that wrote it, for a learning split from a long prompt (`simplified`) or carried over from old feedback (`carried`): undoing that event (POST /agent-learnings/thumbs-downs/{event_id}/rever
created_at string
created_by_user_id object Who taught it, or null for a release.
id string
last_event_id object The latest thumbs down that wrote it, for Undo (POST /agent-learnings/thumbs-downs/{event_id}/revert/); null when none did or the learning was only read.
note object What the person said in the thumbs down that last wrote it (`last_event_id`), every note of a refined one joined, one per line; null when no thumbs down did, and once its feedback session closed: a sa
note_surface object Where the thumbs down that last wrote it (`last_event_id`) was given, which `note` and `source_text` come from; it can differ from `source` once a later thumbs down on another surface changed it. Null
noted_at object When that thumbs down was given; null when no thumbs down wrote it.
notes array The same notes one by one, oldest first, each whole: the thumbs down's own, then each further note in its session. Empty when no thumbs down wrote it, and once its feedback session closed.
repeats integer How often a later Needs work asked for it again, as it stood, once saved; 0 when none did.
source object Where it was taught: the surface whose thumbs down added it, `simplified` when a long prompt was split into a goal and learnings, `carried` when old feedback was carried over.
source_text object The message that thumbs down was given on, as it read then; null when none was kept (a table agent's, or a learning a release wrote).
step_key object The one step of the sequence it holds for, by the step's agent prompt slot; null when it holds for every message the agent writes.
step_label object That step as the sequence names it now, e.g. "Step 2 · Follow up"; null when it holds for every message, or the step is gone.
text string The rule, one line.
updated_at string
View JSON Schema on GitHub

JSON Schema

getoneprofile-ai-agent-learning-read-schema-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/getoneprofile-ai/json-schema/getoneprofile-ai-agent-learning-read-schema-schema.json",
  "title": "AgentLearningReadSchema",
  "description": "One learning: a one-line rule the agent follows on every output.",
  "x-generated": "2026-11-10",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/getoneprofile-ai-agent-learnings-api-openapi.yml#/components/schemas/AgentLearningReadSchema",
  "properties": {
    "all_sequences": {
      "default": false,
      "description": "Whether every sequence's writer follows it, rather than one agent.",
      "title": "All Sequences",
      "type": "boolean"
    },
    "batch_id": {
      "anyOf": [
        {
          "format": "uuid",
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "The release that wrote it, for a learning split from a long prompt (`simplified`) or carried over from old feedback (`carried`): undoing that event (POST /agent-learnings/thumbs-downs/{event_id}/revert/ with this id) is Put back the original prompt. Null for a learning a thumbs down taught.",
      "title": "Batch Id"
    },
    "created_at": {
      "format": "date-time",
      "title": "Created At",
      "type": "string"
    },
    "created_by_user_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "Who taught it, or null for a release.",
      "title": "Created By User Id"
    },
    "id": {
      "format": "uuid",
      "title": "Id",
      "type": "string"
    },
    "last_event_id": {
      "anyOf": [
        {
          "format": "uuid",
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "The latest thumbs down that wrote it, for Undo (POST /agent-learnings/thumbs-downs/{event_id}/revert/); null when none did or the learning was only read.",
      "title": "Last Event Id"
    },
    "note": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "What the person said in the thumbs down that last wrote it (`last_event_id`), every note of a refined one joined, one per line; null when no thumbs down did, and once its feedback session closed: a saved, discarded or undone session keeps none of the person's notes.",
      "title": "Note"
    },
    "note_surface": {
      "anyOf": [
        {
          "$ref": "#/$defs/LearningSource"
        },
        {
          "type": "null"
        }
      ],
      "description": "Where the thumbs down that last wrote it (`last_event_id`) was given, which `note` and `source_text` come from; it can differ from `source` once a later thumbs down on another surface changed it. Null when no thumbs down did."
    },
    "noted_at": {
      "anyOf": [
        {
          "format": "date-time",
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "When that thumbs down was given; null when no thumbs down wrote it.",
      "title": "Noted At"
    },
    "notes": {
      "description": "The same notes one by one, oldest first, each whole: the thumbs down's own, then each further note in its session. Empty when no thumbs down wrote it, and once its feedback session closed.",
      "items": {
        "type": "string"
      },
      "title": "Notes",
      "type": "array"
    },
    "repeats": {
      "default": 0,
      "description": "How often a later Needs work asked for it again, as it stood, once saved; 0 when none did.",
      "title": "Repeats",
      "type": "integer"
    },
    "source": {
      "$ref": "#/$defs/LearningSource",
      "description": "Where it was taught: the surface whose thumbs down added it, `simplified` when a long prompt was split into a goal and learnings, `carried` when old feedback was carried over."
    },
    "source_text": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "The message that thumbs down was given on, as it read then; null when none was kept (a table agent's, or a learning a release wrote).",
      "title": "Source Text"
    },
    "step_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "The one step of the sequence it holds for, by the step's agent prompt slot; null when it holds for every message the agent writes.",
      "title": "Step Key"
    },
    "step_label": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "That step as the sequence names it now, e.g. \"Step 2 · Follow up\"; null when it holds for every message, or the step is gone.",
      "title": "Step Label"
    },
    "text": {
      "description": "The rule, one line.",
      "title": "Text",
      "type": "string"
    },
    "updated_at": {
      "format": "date-time",
      "title": "Updated At",
      "type": "string"
    }
  },
  "required": [
    "id",
    "text",
    "source",
    "created_at",
    "updated_at",
    "created_by_user_id",
    "last_event_id",
    "batch_id"
  ],
  "type": "object",
  "$defs": {
    "LearningSource": {
      "description": "Where a learning came from: the surface a thumbs down was given on, or a release pass.\n\nAlso the ``surface`` of the event that wrote it.",
      "enum": [
        "table_cells",
        "agent_preview",
        "task",
        "writing_preview",
        "reply_draft",
        "sent_message",
        "hand_edit",
        "simplified",
        "carried",
        "template",
        "hand"
      ],
      "title": "LearningSource",
      "type": "string"
    }
  }
}

Work with this as data

Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for schemas

4 MCP tools reach this
  • find_json_schemasBrowse and filter every JSON Schema in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/getoneprofile-ai-agent-learning-read-schema"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.