Muse hides the code until you need it
Muse is a product that displays AI agent activity with progressive disclosure of technical details. It shows status updates for non-technical users (like "working" and high-level task descriptions) while allowing engineers to drill down into detailed logs, curl commands, and code for auditing purposes.
Summary
The speaker describes Muse as a highly useful product that addresses different user needs through layered information architecture. For casual users, the interface displays simple status indicators at the top (e.g., "Jolly Bot is working") and provides basic context about current tasks through emoji-based descriptions like "researching pumpkin patches." As users engage more deeply with the interface by tapping through layers, they gain access to increasingly technical information. Engineers and auditors can eventually reach detailed logs showing curl commands and actual code, which the speaker emphasizes is important for verification and auditing purposes. The key design philosophy is that technical details remain available when needed but remain hidden by default, preventing information overload for users unfamiliar with technical concepts. This progressive disclosure approach makes the product accessible to both technical and non-technical audiences without requiring either group to navigate unnecessary complexity.
Key Insights
- Muse displays simple status indicators like 'working' for non-technical users at the top level, preventing them from being overwhelmed by technical details they may not understand
- The product uses emoji-based task descriptions as a middle layer of information disclosure, allowing users to understand what the agent is doing without seeing underlying code
- Technical users and engineers can access detailed curl commands and code by drilling down through multiple layers of the interface, enabling thorough auditing
- The speaker considers code visibility and audit trails 'really important from like an auditing perspective,' indicating security and verification are key product features
- Muse's design philosophy is to hide complexity by default rather than overwhelming users with technical information upfront, making it accessible to diverse user expertise levels
Topics
Transcript
[0:00] This product, I found it to be one of the most helpful thing. If you are a engineer, you may want to know exactly what your agent has done, and you can find that in Muse. But, if you're a normal person, you maybe just want to know like, is it doing something? So, at the top, it'll tell you, it's working. Jolly Bot is working. And then, your next question might be, what's it working on? You know, and so, it will tell you that with the little emoji, like researching pumpkin patches. But, then if you want to go a little bit further, you tap on it. And then, you have a list of everything that it's…
Full transcript available for MurmurCast members
Sign Up to AccessMore from How I AI
A perfect TikTok cut from a one sentence prompt
Claude code automatically transforms a single sentence prompt into a polished, TikTok-ready short-form video with captions, jump cuts, and zooms in approximately 4 seconds with no manual editing required. The tool demonstrates AI's capability to understand and execute high-quality short-form video production autonomously.
I made my website photo follow you (and wink)
The creator made an interactive photo of themselves that follows viewers around their website and winks when clicked. They accomplished this by converting a photo into a black-and-white dither pattern, using Claude to generate six directional versions of the image, and writing code to make it interactive.
Claude Code turned one long video take into a 15-second ad
A creator demonstrates an AI-powered video editing workflow that automatically transformed a single 5-minute phone recording into a polished 15-second vertical ad. The system used silence detection, speech recognition, facial tracking, and automated shot composition to generate cuts, captions, and graphics without manual timeline editing.
I Turned a $50 Photo Frame Into an AI Family Dashboard
A creator transformed a $50 Amazon photo frame running Android into a customized AI-powered family dashboard using OpenAI's Codeex and web technologies. The dashboard displays family schedules, photos, NASA images, news, and individual checklists for each family member, with updates automatically posted via an API connected to a grabbot that monitors calendars and emails.
Claude Code edited my TikTok
A creator describes using Claude Code to automatically edit their TikTok videos by analyzing raw footage and verbal instructions. The AI tool uses existing computer tools like FFmpeg, Whisper, and Python to process local files, intelligently cutting segments based on spoken cues and selecting the best takes.