Prompt Paul- AI Insights at the click of a mouse

A Chrome extension for processing selected text using an LLM endpoint

Context-aware AI in your browser. Select text, get quick answers, skip the ceremony. +++Prompt Paul — Context-aware AI in the browser+++ Short loops from selected text to answer. That's the whole idea. Prompt Paul keeps AI close to the page you're already on. Select some text, load the page as context, right-click media, or open the side panel and just start talking about what's in front of you. Bring your own model endpoint. OpenAI-compatible cloud providers, routing services, local setups — configure the endpoint, key, and model that match how you work. +++Features+++ ++Selected text actions++ Select something, then analyze, explain, proofread, summarize, or run your own instruction on it — from the context menu or the side panel. ++Page-aware chat++ Load the current page into the side panel and ask follow-ups. The page stays attached to the conversation, so questions like "what did this say about X" just work. ++Media-aware prompts++ If your model handles images, video, or audio, right-click and ask about it directly. On YouTube, prompts can pull in transcript context and visual moments when available. ++Custom instructions++ Save the workflows you repeat — emails, meeting notes, captions, research summaries, code explanations, product descriptions, support replies — and run them in one click. ++Tools and Agent Skills++ When plain chat isn't enough, use configured tools and OpenClaw-compatible Agent Skills. ++Optional web search++ Turn on grounding when the answer needs current or verifiable information. Responses that searched include their Sources. +++What's new (version 6.2.0)+++ Chat is now composer-led, with your context attachments shown up front. Quick actions adapt to what you're working on, Stop/Retry/Edit/Continue controls sit right in the response, and setup plus Options got a cleanup pass. API credentials are masked, web search grounding is optional, and media, voice input, custom instructions, tools, and Agent Skills all still work as before.