Update to UserTold: AI User Research

Changed files

Choose a file to see its text changes. Binary or large files show metadata only.

.codex-plugin/plugin.json →

.codex-plugin/plugin.json

− removed · + added

--- before
+++ after
@@ -3,25 +3,25 @@
   "author": {
     "name": "UserTold.ai"
   },
-  "description": "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.",
+  "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.",
   "interface": {
     "capabilities": [],
     "category": "Productivity",
     "defaultPrompt": [
       "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."
+      "review completed UserTold interviews and Evidence, triage Findings, and create tracker issues only after I approve fixes."
     ],
     "developerName": "UserTold.ai",
-    "displayName": "UserTold",
-    "longDescription": "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.",
+    "displayName": "UserTold: AI User Research",
+    "longDescription": "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.",
     "privacyPolicyURL": "https://usertold.ai/privacy",
-    "shortDescription": "Research from real users",
+    "shortDescription": "User interviews & UX testing",
     "supportURL": "https://usertold.ai/support",
     "termsOfServiceURL": "https://usertold.ai/terms",
     "websiteURL": "https://usertold.ai"
   },
   "name": "app-6a8759c2dba48191b391f3915cc0ee5f",
   "skills": "./skills",
-  "version": "1.0.0"
+  "version": "2.0.0"
 }
\ No newline at end of file