← UserTold: AI User ResearchCONTENT HISTORY

Update to UserTold: AI User Research

Snapshot Oct 24, 2026 · 13:11 UTC · version 2.0.0

WHAT CHANGED

Product listing or positioning changed

Full description — Now says: AI-led voice interviews with your users inside your website, combining screen recordings, navigation context, and conversation in the same session....

Observed in the public listing; claims come from the publisher.

Save UserTold: AI User Research and check future changes in Following.

Up to 10 plugins free · no card required.

All fields and original values.

Full description

Before

Sep 30, 2026 · 23:02 UTC

consented interviews inside a product and lets ChatGPT inspect source-linked Evidence, design and manage Studies, turn findings into reviewed Work, and explicitly hand ready Work to GitHub or Linear.

After

Oct 24, 2026 · 13:11 UTC

AI-led voice interviews with your users inside your website, combining screen recordings, navigation context, and conversation in the same session. Understand what people are trying to do, where they struggle, and what they expected to h...

Long description

Before

Sep 30, 2026 · 23:02 UTC

consented interviews inside a product and lets ChatGPT inspect source-linked Evidence, design and manage Studies, turn findings into reviewed Work, and explicitly hand ready Work to GitHub or Linear.

After

Oct 24, 2026 · 13:11 UTC

AI-led voice interviews with your users inside your website, combining screen recordings, navigation context, and conversation in the same session. Understand what people are trying to do, where they struggle, and what they expected to h...

Short description

Before

Sep 30, 2026 · 23:02 UTC

Research from real users

After

Oct 24, 2026 · 13:11 UTC

User interviews & UX testing

Declared skills

Before

Sep 30, 2026 · 23:02 UTC

[{"description":"Set up UserTold projects and in-product interview studies, inspect consented research, and turn source-linked findings into verified product work through UserTold MCP or CLI. Use when an agent needs to learn a product be...

After

Oct 24, 2026 · 13:11 UTC

[{"description":"Set up UserTold projects and in-product interview studies, inspect consented research, and turn source-linked findings into verified product work through UserTold MCP or CLI. Use when an agent needs to learn a product be...

Compare saved observations

Download comparison JSON
Full technical diff · 9 changed fields

added /is_template_instance

BEFORE
Field was absent
AFTER
false

changed /release/description

BEFORE
"UserTold runs consented interviews inside a product and lets ChatGPT inspect source-linked Evidence, design and manage Studies, turn findings into reviewed Work, and explicitly hand ready Work to GitHub or Linear."
AFTER
"UserTold runs AI-led voice interviews with your users inside your website, combining screen recordings, navigation context, and conversation in the same session. Understand what people are trying to do, where they struggle, and what they expected to happen.\n\nFor usability research, let participants try a task or continue their ordinary work. With consent, UserTold observes without interrupting or offering hints, then asks about specific moments while the experience is fresh. Their explanation stays connected to the screen recording and page activity that prompted the question. Screen recording is available on supported desktop browsers; mobile interviews capture voice and in-page events.\n\nStart in ChatGPT or Codex with a question such as \"Why do trial users stop before creating their first report?\" UserTold helps prepare the study goal, participant task, and interview questions. Review the draft before going live, then invite users through your website widget or share an interview link with customers you can already reach.\n\nRun usability tests, observe everyday workflows, or conduct customer discovery, switching, and concept interviews. Give the interviewer product context and research goals so it can ask relevant follow-up questions and explore concrete examples.\n\nReview transcripts, available recordings, and evidence linked to specific moments. Compare interviews to identify recurring problems while keeping participant statements, observed behavior, and AI interpretation distinct.\n\nTurn supporting evidence into product findings. Check the sources, review the finding, and choose whether to send it to GitHub or Linear with quotes and interview references attached.\n\nUserTold is for teams and coding agents that want to interview real users, capture their product experience, and make decisions with the original context close at hand. Participants come from your own users and customers.\n\nUserTold saves AI research-guidance requests and responses to improve the service. Avoid including personal data or secrets in those requests."

changed /release/display_name

BEFORE
"UserTold"
AFTER
"UserTold: AI User Research"

changed /release/id

BEFORE
"pluginrel_e16777dd9ed0819190a795ca74b2babb"
AFTER
"pluginrel_3ce8c6916ce4819181ce381cc42edc29"

changed /release/interface/default_prompts

BEFORE
[
  "learn this product, create its UserTold project, and propose interviews for its landing page and core product workflow.",
  "create and activate UserTold studies for new visitors on / and experienced users on core product pages; install the widget.",
  "review completed UserTold interviews and Evidence, triage Work, and create tracker issues only after I approve fixes."
]
AFTER
[
  "learn this product, create its UserTold project, and propose interviews for its landing page and core product workflow.",
  "create and activate UserTold studies for new visitors on / and experienced users on core product pages; install the widget.",
  "review completed UserTold interviews and Evidence, triage Findings, and create tracker issues only after I approve fixes."
]

changed /release/interface/long_description

BEFORE
"UserTold runs consented interviews inside a product and lets ChatGPT inspect source-linked Evidence, design and manage Studies, turn findings into reviewed Work, and explicitly hand ready Work to GitHub or Linear."
AFTER
"UserTold runs AI-led voice interviews with your users inside your website, combining screen recordings, navigation context, and conversation in the same session. Understand what people are trying to do, where they struggle, and what they expected to happen.\n\nFor usability research, let participants try a task or continue their ordinary work. With consent, UserTold observes without interrupting or offering hints, then asks about specific moments while the experience is fresh. Their explanation stays connected to the screen recording and page activity that prompted the question. Screen recording is available on supported desktop browsers; mobile interviews capture voice and in-page events.\n\nStart in ChatGPT or Codex with a question such as \"Why do trial users stop before creating their first report?\" UserTold helps prepare the study goal, participant task, and interview questions. Review the draft before going live, then invite users through your website widget or share an interview link with customers you can already reach.\n\nRun usability tests, observe everyday workflows, or conduct customer discovery, switching, and concept interviews. Give the interviewer product context and research goals so it can ask relevant follow-up questions and explore concrete examples.\n\nReview transcripts, available recordings, and evidence linked to specific moments. Compare interviews to identify recurring problems while keeping participant statements, observed behavior, and AI interpretation distinct.\n\nTurn supporting evidence into product findings. Check the sources, review the finding, and choose whether to send it to GitHub or Linear with quotes and interview references attached.\n\nUserTold is for teams and coding agents that want to interview real users, capture their product experience, and make decisions with the original context close at hand. Participants come from your own users and customers.\n\nUserTold saves AI research-guidance requests and responses to improve the service. Avoid including personal data or secrets in those requests."

changed /release/interface/short_description

BEFORE
"Research from real users"
AFTER
"User interviews & UX testing"

changed /release/skills

BEFORE
[
  {
    "description": "Set up UserTold projects and in-product interview studies, inspect consented research, and turn source-linked findings into verified product work through UserTold MCP or CLI. Use when an agent needs to learn a product before planning interviews, install route-targeted interview capture, inspect voice transcripts, supported desktop screen recordings, observed behavior or page context, triage draft Work with its Evidence, create approved tracker issues, or export a portable research handoff. Do not use for participant recruitment or for claims not grounded in the captured record.",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $usertold to learn this product, create its project, and propose landing-page and core-workflow interviews.",
      "display_name": "UserTold",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "default",
      "short_description": "Capture and analyze interviews"
    },
    "name": "usertold",
    "plugin_release_skill_id": "pluginrsk_6a879e2c692c81918fdcba34fedb9b76"
  },
  {
    "description": "Plan participant recruitment for a UserTold Study and produce participant-readable recruitment copy plus canonical Invitation, Visibility, and neutral Intake inputs. Use when choosing whom to invite, comparing outreach channels, setting an honest reward, drafting an in-product launcher or direct-link invitation, screening without revealing qualifying answers, or translating an existing recruitment plan into UserTold configuration. Do not use to send outreach, source a participant panel, fulfill rewards, claim representative sampling, or provide legal advice.",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $usertold-recruit-participants to configure focused invitations for users I can already reach.",
      "display_name": "Recruit UserTold Participants",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "default",
      "short_description": "Plan truthful participant recruitment"
    },
    "name": "usertold-recruit-participants",
    "plugin_release_skill_id": "pluginrsk_6a879e2ca1e88191840007105d7fc459"
  }
]
AFTER
[
  {
    "description": "Set up UserTold projects and in-product interview studies, inspect consented research, and turn source-linked findings into verified product work through UserTold MCP or CLI. Use when an agent needs to learn a product before planning interviews, install route-targeted interview capture, inspect voice transcripts, supported desktop screen recordings, observed behavior or page context, triage draft Work with its Evidence, create approved tracker issues, or export a portable research handoff. Do not use for participant recruitment or for claims not grounded in the captured record.",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $usertold to learn this product, create its project, and propose landing-page and core-workflow interviews.",
      "display_name": "UserTold",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "default",
      "short_description": "Capture and analyze interviews"
    },
    "name": "usertold",
    "plugin_release_skill_id": "pluginrsk_6a98a9d58cec8191a8e88b50f7e6b114"
  },
  {
    "description": "Plan participant recruitment for a UserTold Study and produce participant-readable recruitment copy plus canonical Invitation, Visibility, and neutral Intake inputs. Use when choosing whom to invite, comparing outreach channels, setting an honest reward, drafting an in-product launcher or direct-link invitation, screening without revealing qualifying answers, or translating an existing recruitment plan into UserTold configuration. Do not use to send outreach, source a participant panel, fulfill rewards, claim representative sampling, or provide legal advice.",
    "interface": {
      "brand_color": null,
      "default_prompt": "Use $usertold-recruit-participants to configure focused invitations for users I can already reach.",
      "display_name": "Recruit UserTold Participants",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "default",
      "short_description": "Plan truthful participant recruitment"
    },
    "name": "usertold-recruit-participants",
    "plugin_release_skill_id": "pluginrsk_6a98a9d5cd188191b3b73d558db1c747"
  }
]

changed /release/version

BEFORE
"1.0.0"
AFTER
"2.0.0"
Full snapshot data
{
  "canonical_app_id": "asdk_app_6a8759c2dba48191b391f3915cc0ee5f",
  "connector_id": "asdk_app_6a8759c2dba48191b391f3915cc0ee5f",
  "created_at": "2026-08-20T19:47:15.190424Z",
  "discoverability": "LISTED",
  "id": "plugin_asdk_app_6a8759c2dba48191b391f3915cc0ee5f",
  "is_template": false,
  "is_template_instance": false,
  "name": "app-6a8759c2dba48191b391f3915cc0ee5f",
  "release": {
    "app_ids": [
      "asdk_app_6a8759c2dba48191b391f3915cc0ee5f"
    ],
    "app_manifest": {
      "apps": {
        "app-6a8759c2dba48191b391f3915cc0ee5f": {
          "id": "asdk_app_6a8759c2dba48191b391f3915cc0ee5f",
          "required": true
        }
      }
    },
    "app_templates": [],
    "description": "UserTold runs AI-led voice interviews with your users inside your website, combining screen recordings, navigation context, and conversation in the same session. Understand what people are trying to do, where they struggle, and what they expected to happen.\n\nFor usability research, let participants try a task or continue their ordinary work. With consent, UserTold observes without interrupting or offering hints, then asks about specific moments while the experience is fresh. Their explanation stays connected to the screen recording and page activity that prompted the question. Screen recording is available on supported desktop browsers; mobile interviews capture voice and in-page events.\n\nStart in ChatGPT or Codex with a question such as \"Why do trial users stop before creating their first report?\" UserTold helps prepare the study goal, participant task, and interview questions. Review the draft before going live, then invite users through your website widget or share an interview link with customers you can already reach.\n\nRun usability tests, observe everyday workflows, or conduct customer discovery, switching, and concept interviews. Give the interviewer product context and research goals so it can ask relevant follow-up questions and explore concrete examples.\n\nReview transcripts, available recordings, and evidence linked to specific moments. Compare interviews to identify recurring problems while keeping participant statements, observed behavior, and AI interpretation distinct.\n\nTurn supporting evidence into product findings. Check the sources, review the finding, and choose whether to send it to GitHub or Linear with quotes and interview references attached.\n\nUserTold is for teams and coding agents that want to interview real users, capture their product experience, and make decisions with the original context close at hand. Participants come from your own users and customers.\n\nUserTold saves AI research-guidance requests and responses to improve the service. Avoid including personal data or secrets in those requests.",
    "display_name": "UserTold: AI User Research",
    "id": "pluginrel_3ce8c6916ce4819181ce381cc42edc29",
    "interface": {
      "brand_color": null,
      "capabilities": [],
      "category": "Productivity",
      "composer_icon_dark_url": "https://files.openai.com/content?id=file_00000000664c824396c2b05cb57845ea",
      "composer_icon_url": "https://files.openai.com/content?id=file_00000000664c824396c2b05cb57845ea",
      "default_prompt": "learn this product, create its UserTold project, and propose interviews for its landing page and core product workflow.",
      "default_prompts": [
        "learn this product, create its UserTold project, and propose interviews for its landing page and core product workflow.",
        "create and activate UserTold studies for new visitors on / and experienced users on core product pages; install the widget.",
        "review completed UserTold interviews and Evidence, triage Findings, and create tracker issues only after I approve fixes."
      ],
      "developer_name": "UserTold.ai",
      "logo_url": "https://files.openai.com/content?id=file_00000000d80c820a9cc1da9eb3cab591",
      "logo_url_dark": "https://files.openai.com/content?id=file_00000000d80c820a9cc1da9eb3cab591",
      "long_description": "UserTold runs AI-led voice interviews with your users inside your website, combining screen recordings, navigation context, and conversation in the same session. Understand what people are trying to do, where they struggle, and what they expected to happen.\n\nFor usability research, let participants try a task or continue their ordinary work. With consent, UserTold observes without interrupting or offering hints, then asks about specific moments while the experience is fresh. Their explanation stays connected to the screen recording and page activity that prompted the question. Screen recording is available on supported desktop browsers; mobile interviews capture voice and in-page events.\n\nStart in ChatGPT or Codex with a question such as \"Why do trial users stop before creating their first report?\" UserTold helps prepare the study goal, participant task, and interview questions. Review the draft before going live, then invite users through your website widget or share an interview link with customers you can already reach.\n\nRun usability tests, observe everyday workflows, or conduct customer discovery, switching, and concept interviews. Give the interviewer product context and research goals so it can ask relevant follow-up questions and explore concrete examples.\n\nReview transcripts, available recordings, and evidence linked to specific moments. Compare interviews to identify recurring problems while keeping participant statements, observed behavior, and AI interpretation distinct.\n\nTurn supporting evidence into product findings. Check the sources, review the finding, and choose whether to send it to GitHub or Linear with quotes and interview references attached.\n\nUserTold is for teams and coding agents that want to interview real users, capture their product experience, and make decisions with the original context close at hand. Participants come from your own users and customers.\n\nUserTold saves AI research-guidance requests and responses to improve the service. Avoid including personal data or secrets in those requests.",
      "plugin_category_id": "productivity",
      "privacy_policy_url": "https://usertold.ai/privacy",
      "screenshot_urls": [],
      "short_description": "User interviews & UX testing",
      "terms_of_service_url": "https://usertold.ai/terms",
      "website_url": "https://usertold.ai"
    },
    "keywords": [],
    "mcp_servers": [],
    "onboarding_skill_name": null,
    "requires_local_executor": false,
    "skills": [
      {
        "description": "Set up UserTold projects and in-product interview studies, inspect consented research, and turn source-linked findings into verified product work through UserTold MCP or CLI. Use when an agent needs to learn a product before planning interviews, install route-targeted interview capture, inspect voice transcripts, supported desktop screen recordings, observed behavior or page context, triage draft Work with its Evidence, create approved tracker issues, or export a portable research handoff. Do not use for participant recruitment or for claims not grounded in the captured record.",
        "interface": {
          "brand_color": null,
          "default_prompt": "Use $usertold to learn this product, create its project, and propose landing-page and core-workflow interviews.",
          "display_name": "UserTold",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "default",
          "short_description": "Capture and analyze interviews"
        },
        "name": "usertold",
        "plugin_release_skill_id": "pluginrsk_6a98a9d58cec8191a8e88b50f7e6b114"
      },
      {
        "description": "Plan participant recruitment for a UserTold Study and produce participant-readable recruitment copy plus canonical Invitation, Visibility, and neutral Intake inputs. Use when choosing whom to invite, comparing outreach channels, setting an honest reward, drafting an in-product launcher or direct-link invitation, screening without revealing qualifying answers, or translating an existing recruitment plan into UserTold configuration. Do not use to send outreach, source a participant panel, fulfill rewards, claim representative sampling, or provide legal advice.",
        "interface": {
          "brand_color": null,
          "default_prompt": "Use $usertold-recruit-participants to configure focused invitations for users I can already reach.",
          "display_name": "Recruit UserTold Participants",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "default",
          "short_description": "Plan truthful participant recruitment"
        },
        "name": "usertold-recruit-participants",
        "plugin_release_skill_id": "pluginrsk_6a98a9d5cd188191b3b73d558db1c747"
      }
    ],
    "version": "2.0.0"
  },
  "scope": "GLOBAL",
  "share_url": "https://chatgpt.com/plugins/plugin_asdk_app_6a8759c2dba48191b391f3915cc0ee5f?open_in_app",
  "status": "ENABLED"
}

SHA-256 of public snapshot: bce54d820b1d40893e3970ca442f7746151b5a02b3fbeb504aad6bc15a24a83a