Prompt Paul- AI Insights at the click of a mouse
Featuredjuanmackie.com · Tools
Media
5 items
Description
A Chrome extension for processing selected text using an LLM endpoint Prompt Paul - AI that works on the page you have open Select text, ask about it, and get an answer without leaving the page. Prompt Paul works on what you already have open. Select text, load the page into the side panel, right-click supported media, or open the panel yourself and ask about what you see. Use your own model endpoint: an OpenAI-compatible cloud provider, a routing service, or a local setup. You set the endpoint, key, and model. 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-up questions. The page stays attached to the conversation, so "What did this say about X?" still has the text to answer from. Media-aware prompts -If your provider and model support images, video, or audio, right-click supported media and ask about it. On YouTube, prompts can use transcript context when captions exist, and the current video frame can be captured in chat for reference. Custom instructions -Save the workflows you repeat, such as emails, meeting notes, captions, research summaries, code explanations, product descriptions, and support replies, then run them in one click. Tools and Agent Skills -When chat alone is not enough, use your configured tools and OpenClaw-compatible Agent Skills. Optional web search - Turn on grounding when an answer needs current or verifiable information. Responses that use search include a Sources section. What's new in 6.2.1 -Chat now starts from the composer, with context attachments shown up front. Quick actions change with what you are working on, and Stop,Retry, Edit, and Continue controls sit in the response itself. -Options and setup got a cleanup pass: API credentials are masked, web search grounding is optional, and media, voice input, custom instructions, tools, and Agent Skills are still there.