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.
A three-agent pipeline that drafts weekly posts from commit history and publishes to Notion and DEV.
A three-agent pipeline that drafts weekly posts from commit history and publishes to Notion and DEV.
The author built DevNotion on Mastra, run by a Sunday GitHub Actions cron. A GraphQL call pulls the week's commits, PRs, issues, reviews and language stats with no LLM. Gemini then writes a first-person post, with a deterministic fallback if it fails. The publisher creates a DEV.to draft and a Notion planner page with tables.
It reliably produces a draft each week, which the author edits before publishing. The source gives no engagement figures. Gemini gave the best output among the models tried, including Ollama and Groq ones.
Asking Gemini for native structured output added 20-40 seconds per call. Plain text with YAML frontmatter parsing was 3-4x faster, and Notion needs rate limiting.
Build a weekly workflow that pulls my commits and pull requests from [GitHub repo or username] for the past 7 days, has one step summarize the changes, a second draft a blog post in [tone], and a third format it for [Notion and DEV]. Save the output as a draft in Notion. Finished means I can review a draft each week, and the workflow must pause for my approval before publishing anything publicly.
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.