Turn a PDF into an interactive course
An agent read textbooks and PDFs, built lesson sections, filled in interactive blocks, and sent the course to a second agent for review.
- What they did
- Hassan used a custom agent that takes a PDF or textbook as input. For smaller files, it keeps the text in context; for larger ones, it stores embeddings. It first outlines the lesson flow from examples, then uses tool calls to fill prebuilt pieces like Q&A sections or flowcharts with generated text and settings. A separate Lesson Reviewer agent then checks the draft against the source before the course is finalized.
- How it went
- In a demo, the system produced one course in 2 minutes for 10 cents on Together Compute using open-source models. The free open-source app is now available live.
- Tips
- Use a review step before publishing anything that needs to stay faithful to the source. For longer documents, expect embedding and retrieval to matter more than keeping everything in context.
Try it yourself with Claude Cowork
I’m going to give you a [PDF/textbook file path] and a target audience: [audience]. First, inspect the source and outline a lesson plan with sections in a logical teaching order. Then, for each section, create the lesson text and choose suitable interactive elements such as quizzes, flashcards, Q&A, matching, or a flowchart, filling each template with content from the source. Before finalizing, pause and ask me to confirm the course structure and any interactive elements that will be submitted or exported. After I approve, run a separate accuracy check against the source, fix any mismatches, and then export the finished course as [format] into [folder].
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Let an agent package one idea for multiple channels
A creator delegated script writing, thread drafting, and post repurposing to a CreaoAI agent.
Turn raw footage into a first edit from a description
Cardboard can assemble an editable cut from footage and a plain-language brief, then let you fine-tune the result in chat or on the timeline.
Set up a node-based video editing workflow
A mosaic-style canvas can automate video edits, generate variations, and then hand off to a timeline for manual tweaks.
Automate repeated site content updates
A developer used an agent to turn one podcast-page update into a repeatable workflow for their Nuxt site.
Make a 3D Blender model from an image
A developer used a coding agent with a local Blender skill to turn a generated image into a Blender file.
Build a tiny agent for one app task
A developer makes small purpose-built agents, including one inside a music player, because the useful core can be very short.