💬Chat with your webpage cookbook is out! 💬 It uses ScrapeGraphAI to extract the webpage content, LanceDB to vector store it and retrieve the most relevant chunks and DAGWorks Inc. (YC W23) Apache Burr (incubating) to orchestrate everything 🚀 Try it out: colab.research.google.com/drive/1pbDpLKW…

🤔 2025 prediction. "memory" will have it's RAG/Agent moment - i.e. overhyped where people realize that: 1. Using a framework that hides the internal prompts & logic because its "memory" impedes everyone serious who wants to get to production reliability. Why? You need to

📣 New blog post! Chat with your webpage with ScrapeGraphAI, Apache Burr (incubating) and LanceDB blog.dagworks.io/p/chat-with-yo… TL;DR: a great post showing the use of lightweight tools that are "orchestrated" and "observed" with Burr.

Check out the latest article in my newsletter: February Updates linkedin.com/pulse/february… via LinkedIn Apache Hamilton (incubating): - crosses 2K⭐️ - installs in Pyodide envs - mutlithreaded parallel DAG execution Apache Burr (incubating): - crosses 1.5K ⭐️ - async persister implementations - tag

While some frameworks have all the mindshare, their solutions are still off the mark. Excited to find organic posts like this on Apache Hamilton (incubating)

Jeremy Howard 🤷, 😊

Friday Demo time: Just recorded a walkthrough of APX's onboarding flow See how quickly our AI agents connect to GitHub, Datadog, Sentry and Postgres to auto-fix production issues. From signup to automated PRs & recommendations in minutes. What should we demo next?

🛠️ Best Free Resources for Building AI Agents I put together this handpicked list of free resources to help folks ramp up for my course Building LLM Apps for Data Scientists and Software Engineers (which I teach with Stefan Krawczyk). But I realized it might be useful to a

📚 A hand-picked list of free resources for building reliable LLM applications—covering Python, deep learning, evaluation, MLOps, and prompt engineering. Everything here is open and accessible—no paywalls, no subscriptions, just great content to dive into (even the books!).

My colleague Stefan Krawczyk gave an incredible workshop in our last Maven cohort on observability and debugging for LLM-powered apps—highlighting the two iteration loops every serious AI team should master: ✅ One for development ✅ One for production He’ll be running a free

Now offering $100 in Mistral AI credits to the first 50 students in our course with Stefan Krawczyk. Mistral is becoming one of the most compelling platforms for working with open-weight LLMs — efficient models, fast inference, and clean APIs. Their recent releases include: •

Data pipelines have been around but they’re becoming increasingly crucial as organizations look to deploy AI agents. We spoke with DAGWorks Inc. (YC W23) co-founder Stefan Krawczyk to understand what teams should consider when standing up their first data pipeline. hubs.ly/Q03hSzVn0

🚀 Building your first data pipeline? Start small, but plan for growth. 🛠️ Data evolves—build for change. 🚮 Standardize early to reduce tech debt. 🔭 Prioritize observability and quality checks. In this article, DAGWorks Inc. (YC W23) co-founder Stefan Krawczyk breaks it down for you.

Oh hey 👋 how's them agents? Repo update: github.com/apache/burr (hint: the apache part ) Some user ❤️:

Earlier this week, our Building with LLMs course broke into the Top 100 on Maven 🏛 . Now it’s jumped into the Top 10! It’s currently #7 in AI and #3 in Data & Engineering. If you want to learn how to build production-grade LLM and AI applications, join Stefan Krawczyk and me in

To celebrate our course kicking off next week, Stefan Krawczyk and I are hosting 5 free events this week with top builders in the space. 🗓 All event details: hugobowne.substack.com/p/stop-buildin… 📚 Course info: bit.ly/build-with-llms Hope to see you there... and feel free to share with

Struggling to move beyond toy LLM demos? 😕 I’ve taken Hugo Bowne-Anderson & Stefan Krawczyk's “Building LLM Apps” course twice—as a student, then as a Builder in Residence—and I’m going back a THIRD time because it’s that good. (1/5)

Yesterday I posted about “Stop Building AI Agents” being on the front page… turns out it actually hit #1 on Hacker News 🤖 Thanks RavinKumar for letting me know! And thanks Decoding ML for the great collab. That was wild to see. Over 100 comments, plenty of thoughtful

Listen, watch, or read: Apple → podcasts.apple.com/us/podcast/epi… Spotify → open.spotify.com/episode/1ajEdi… YouTube → youtu.be/3r_Hsjy85nk?si… Full notes → vanishinggradients.fireside.fm/57 This conversation was adapted from a guest session in Hugo and Stefan Krawczyk's Building LLM-powered

Things I hear in private circles: "even the CEOs of LangChain and LlamaIndex 🦙 say there is little value in abstracting over LLM API calls". If you haven't been following Apache Apache Hamilton (incubating) or Apache Apache Burr (incubating) that's exactly what we've been saying for years -- you need