clip.qa is a mobile app that turns screen recordings into structured bug reports. Record a bug on your phone, and clip.qa's AI drafts a report with steps to reproduce and device context for you to review. Reports export as markdown for AI coding tools like Claude Code and Cursor, or to paste into any tracker. Jira, Linear, Slack, GitHub Issues and Notion integrations are coming soon. No SDK required in the app you test.

What is Vibe QA — and why does it matter?

Vibe QA is quality assurance for apps built with AI coding tools — a practice that emerged alongside vibe coding (using AI assistants like Claude Code, Cursor, and Copilot to build apps rapidly). Because vibe-coded apps ship faster than traditional QA can keep up, Vibe QA uses AI-native tools to close the loop: capture bugs visually, generate LLM-ready reports automatically, and feed them back to the same AI tools that built the app. clip.qa is built for Vibe QA.

Does clip.qa work with OpenClaw projects?

Yes. clip.qa produces a structured report your agent, including OpenClaw, can read through MCP or a pasted prompt.

How is clip.qa different from Jam?

Jam has a Chrome extension, a Mac app and an iOS app, plus AI summaries and an MCP server. No Android app is documented. clip.qa records on iOS, Android and in Chrome (beta, request access), with no SDK in the app you test. clip.qa's MCP also records each fix attempt (pending, succeeded, failed) with its commit or PR, and can diff reports.

Do I need to install an SDK or add code to my app?

No. clip.qa works without any SDK integration. It uses your phone's native screen recording, so it works on any app — including competitor apps you're testing, OpenClaw projects, and apps you don't have source access to (subject to OS limits such as FLAG_SECURE).

How much does clip.qa cost?

Free: 30 bug reports and 30 AI-assisted reports a month. Team ($12.99/mo or $129/yr, billed per creator seat, viewers free): unlimited bug reports, 200 AI-assisted reports and 50 share links a month. Enterprise pricing is custom; confirm current quotas and features with sales. Audit logs and priority support are listed; SAML/SSO is coming soon.

What platforms does clip.qa support?

The clip.qa web dashboard is available now; the iOS app, Android app and Chrome extension are in beta (request access at hello@clip.qa). Bug reports can be copied as markdown into any tracker (Jira, Linear, GitHub Issues; native integrations coming soon) or used directly as prompts for Claude, Cursor, and other AI coding tools.

ChatGPT Dots

clip.qa / Use cases / ChatGPT Dots

clip.qa for ChatGPT Dots: send bug reports your agent can fix

A dot works on projects with its own computer and your connected tools. clip.qa gives it the part it cannot see: a recording of the bug on a real device, turned into steps, logs and video context.

The clip.qa iOS app, Android app and Chrome extension are in beta. Request access on the apps page.

Request beta access See all integrations

The agent

About ChatGPT Dots from OpenAI

OpenAI describes ChatGPT dots as always-on agents that use their own computer, Codex and connected tools to work on projects. Owners choose which apps they authorize and when a dot can act without approval. OpenAI's documentation describes personal dots using the owner's authorized plugin connections and ChatGPT Work delegating tasks through Codex. Its examples include gathering customer feedback, then scoping, building and testing improvements.

How it works

From a bug on your phone to a fix attempt in ChatGPT Dots

1. Record the bug on your own device

Use the clip.qa iOS or Android app (beta, request access), or the Chrome extension (beta, request access), to screen-record the bug. No SDK goes into the app you test.

2. Review the AI draft

clip.qa turns the recording into a report: title, severity, kind, suspected root cause, steps to reproduce, and expected vs actual behavior when the recording shows a defect, plus key-moment screenshots and device context (OS, device, memory, thermal). It is a draft, so check it before you hand it to your dot.

3. Give your dot a report it can access

ChatGPT Work supports custom MCP servers as plugins. OpenAI does not list clip.qa, so verify authenticated report retrieval before relying on this connection. Otherwise, paste the report as Markdown or give it to Codex in a session with tested access.

4. Review and approve

Your dot gets the steps, logs and video context it needs to scope and test a fix. You decide when it acts on its own and when it needs your approval, then you review the result.

Connect your dot

Two ways to give a dot a clip.qa report

OpenAI documents custom MCP servers as plugins for ChatGPT Work and explains how to connect authorized plugins to a dot. OpenAI does not list clip.qa, so test authenticated retrieval of a real clip.qa report before relying on this workflow.

clip.qa connection details

Remote MCP server:  https://mcp.clip.qa/mcp
Local MCP server:   npm @clip-qa/mcp-server
CLI:                npm @clip-qa/cli

1In ChatGPT Work, open Plugins → + → Add custom MCP server. Enter a name, set the HTTPS endpoint to https://mcp.clip.qa/mcp, and complete authentication if prompted; then choose Create as a plugin.

2Install the plugin and test its clip.qa tools in Work. Confirm that it can retrieve a real report.

3Open or create a dot, connect the installed plugin to it, and verify that the dot retrieves the same report.

4If retrieval is not confirmed, paste the Markdown report into the dot conversation or give it to Codex through a separately tested connection.

Honest fit

Choose a dot on its own if

The work starts from feedback you already have in written form.
The bug reproduces from code or a failing test, with no device in the loop.
You want an always-on agent for projects in general, not for bug intake.

A dot can scope, build and test. clip.qa does not. clip.qa is for the moment before that: you hit a bug on your phone in an AI-built app, and typing the steps from memory loses half of them. The recording becomes the report your dot works from.

clip.qa and ChatGPT Dots FAQ

How do I give a ChatGPT dot a clip.qa report?

OpenAI documents adding custom MCP servers as plugins in ChatGPT Work, but clip.qa is not listed and authenticated report retrieval has not been verified. Configure https://mcp.clip.qa/mcp, install and test the plugin in Work, and confirm it retrieves a real report. Otherwise, paste the Markdown report or give it to Codex through a tested connection.

Will a dot fix the bug on its own?

OpenAI describes dots taking on tasks and gives an example of scoping, building and testing improvements from customer feedback. For a clip.qa report, first confirm the dot can retrieve that report. Review any proposed changes and keep approval settings appropriate to the work.

Is this an OpenAI integration?

No. clip.qa is an independent product with no partnership with OpenAI. The connection uses the standard MCP protocol, and you add the clip.qa server yourself.

Your dot scopes and tests. clip.qa captures the bug.

Record the bug, review the AI draft, then send it to your agent. Free plan available.

Request beta access See all integrations