Jeremiah Lowin

Thrilled to share four milestones we hit in July: 🚀 Record‑breaking quarter: we just posted the strongest in company history. 🏁 Profitable: we’ll affirm this milestone in the next few weeks. 🤩 Customer momentum: +70 % net growth in just six months. 📈 Exploding usage:…

Git worktrees are the recommended way to run Claude Code in parallel, but managing them is kind of tedious... so I built claude-wt! A simple utility to spin up and manage Claude in isolated worktrees. No install needed: uvx claude-wt new

2018 AI demo: book a reservation 2019 AI demo: book a reservation 2020 AI demo: book a reservation 2021 AI demo: book a reservation 2022 AI demo: book a reservation 2023 AI demo: book a reservation 2024 AI demo: book a reservation 2025 AI demo: book a reservation with agents

Every Claude Code session is a race to ship before the auto-compact feature helpfully performs a total lobotomy.

I was honored to open @PayPal's first-ever AI Summit! Watching a company at this scale commit to radical transformation is astounding and inspiring, and I got to see this not only from the keynote stage but in hours of conversations with the AI, LLM, and MCP teams after.…

Data orchestration you can trust.

I almost didn’t make cyclopts a fastmcp dependency because it didn’t have a lot of downloads. Problem solved, I guess?

At NN.07 we've been using @PrefectIO for workflow orchestration for over 4 years with no downtime and almost zero maintenance. Over 50 deployments with more than 800 weekly runs! They continue to be our reliable partner.

2024: No wifi on the flight? Guess I'll do some coding 2025: No wifi on the flight? Guess I can't do any coding.

There is a profound difference in how to build an optimal API for agents end users vs humans. If you are not thinking deeply about how to build infrastructure for agents as your main users in the next 2-5 years you are NGMI. Shoutout to @jlowin for this great piece! Definitely…

🛑 Stop converting your REST APIs to MCP. I know that slick OpenAPI-to-MCP converter feels like magic, but it's poisoning your agent. I'm telling you this as the person who built the most popular one. Here’s why we need to rethink agent-first API design, from first principles:…

“Two months ago we launched self-serve pricing at @PrefectIO . Today is Tuesday and it's already our 3rd largest week of sign-ups ever 📈” linkedin.com/posts/whitecdw…

It's all fun and games until an AI vibe-codes a 42,000 line PR and another AI vibe-reviews it as "impressive and substantial." This is the way the world ends, not with a bang but a "LGTM!" github.com/google-gemini/…

Sure, I could use AI video to sell something... or I could just sit here and watch the virtual starling murmurations fly by

"Cyclopts is what you thought Typer was." Just refactored the FastMCP CLI and I have to say I agree with this line from the Cyclopts docs.

We released today the @tinybirdco Remote MCP Server. It is built with the amazing fastmcp from @jlowin. One of the cool things of our mcp server is that we expose tools dynamically depending on your token scopes.

When I launched MLIP Arena (github.com/atomind-ai/mli…), I chose @PrefectIO for HPC orchestration. Glad I did. Now with FastMCP (github.com/jlowin/fastmcp) by its very best CEO @jlowin, enabling LLM to use SOTA MLIP to run atomistic simulation in same ecosystem would be very easy.

I'm excited to see this new hands-on course that showcases @pixeltablehq to build production-ready multimodal agents. Miguel from The Neural Maze and Alex from Neural Bits just launched Kubrick: a course on building multimodal video agents using the Model Context Protocol (MCP).…

TIL every senior dev dedicates part of Claude.md to ensuring that Claude doesn't write really weird long PR messages. Here's mine. It'll be probably be longer by the time you read this: ### PR Messages - REQUIRED Structure - 1-2 paragraphs: problem/tension +…

A common question I hear when teams start building for AI is, “Why can’t agents just use our REST API instead of MCP?” My response is usually the same: “Why can’t you just use your REST API instead of a UI?” jlowin.dev/blog/curation-…