Turn AI newsletters into a daily podcast
An agent runs overnight, collects the author's AI newsletter subscriptions and produces a daily podcast to listen to on walks.
Hassan's agent parses source documents, plans lesson structure via tool calls, picks interactive components, and a Lesson Reviewer agent checks the final course.
Hassan's agent parses source documents, plans lesson structure via tool calls, picks interactive components, and a Lesson Reviewer agent checks the final course.
The agent receives a PDF or textbook and parses it, keeping small files in context or embedding larger ones. It plans lesson structure using provided examples, then uses tool calls to select and populate pre-built components such as Q&A or flowcharts with generated content and parameters. The output passes to a separate Lesson Reviewer agent for verification against the source before final creation.
A working demo generated one course in 2 minutes at 10 cents on Together Compute open-source models; the full free open-source app is now live.
Generation cost 10 cents and took 2 minutes in the reported demo.
Read the PDF or textbook at [file path] and turn it into an interactive course for [audience]. Plan the lesson structure, then for each lesson write the content and add quizzes, flashcards or exercises. Review the full course for accuracy against the source and consistency. Finish with the course as [format, e.g. HTML files] in [folder].
An agent runs overnight, collects the author's AI newsletter subscriptions and produces a daily podcast to listen to on walks.
Reviewers use Make workflows with Gemini to generate ideas, create and title a daily YouTube video, and route Google Form responses into a CRM with follow-ups.
A Zapier agent watches an RSS feed and posts content summaries to Bluesky, helping manage blogging across Medium, Buy Me a Coffee and Bluesky.