Our Python documentation just got a huge boost thanks to RunLLM! Our new "Ask AI" widget in the bottom-right of every docs page launches a truly magically accurate agentic RAG system that writes accurate, up-to-date code in answer to your questions. Try it out today!

If you're not implementing this for your library's docs, I don't know what you're doing. runllm.com

.Joey Gonzalez and I have a pre-holiday hot take. 🔥 Your AI strategy is a waste of time. You'll be much better served by using more AI tools (and accepting that it won't work out sometimes). By the time you invent a strategy, it'll be outdated anyway! open.substack.com/pub/frontierai…

Everyone's been hand-wringing about the end of scaling laws, but does it matter? Better models aren't necessary for adoption, and better models aren't going to create adoption. Joey Gonzalez and I on what the real priorities are: open.substack.com/pub/frontierai…

The end of the year snuck up on Joey Gonzalez and me, so we reviewed our predictions for 2024 and shared some lessons learned. Predictions for next after the holidays! 👀

We're launching a public beta of RunLLM in a few weeks! There's a bunch of new features that we're excited to share — a new streamlined welcome flow, a significantly upgraded chat experience, and new insights about what your users are focused on. Super proud of what the team's

The RunLLM Public Beta is Live! 🚀 After almost two years of work, we’re launching RunLLM — the first AI Support Engineer. Built for advanced technical support, RunLLM: ✅ Saves support engineering time ✅ Accelerates customer adoption ✅ Generates customer and product insights

Great AI is built by great teams. Joey Gonzalez,  Joe Hellerstein, Vikram Sreekanti, & Chenggang Wu have spent years at UC Berkeley pushing the frontier of AI research — Now they’re applying it to one of the most challenging problems in tech: scaling advanced technical support.

An AI Support Engineer's most important job is, of course, supporting your customers. Doing that well requires a lot more than providing a simple question-answer interface. With yesterday's public beta launch, we've released a revamped support experience that's singularly

Something that's surprised us over the past year is that a user base with access to a trustworthy AI Support Engineer asks up to 10x as many questions as they did before. Why? A variety of reasons — avoiding embarrassment for "silly" questions, having to wait for a person to

For the last few days, we've been talking about the features that make RunLLM the best AI Support Engineer on the market. All these features have been guided by our experiences using other apps and building RunLLM. To close out the week, we wanted to share how we think about

Despite all the hype about AI, very few companies are really on the cutting edge of AI — but Arize AI is one of them. RunLLM's been working with them for 6 months now, and we've learned a lot about how they approach technical support. We've been able to cut resolution times in

LLMs do everything they can to be helpful, which is generally great... until it goes horribly wrong. That failure mode becomes painful when you're building high-quality applications: You can't trust LLMs to solve a complex problem directly. What we've found in building RunLLM

.Joey Gonzalez and I have said many times that there needs to be more focus on the UX of AI applications... but what does that mean? We've done a very poor job of defining that so far! But we've finally gotten around to it. It comes down to two things: visibility into what

Would you be surprised if we told you we'd already achieved AGI? Well, we have. 🙂 It's just that achieving AGI doesn't mean what you think. Current state of the art models demonstrate general intelligence, but they haven't solved all our problems. Why? Because generality is

🎬 Catch up on Episodes 4–9 of LLMs on the Run, our rapid-fire Q&A video series with UC Berkeley Professor and RunLLM cofounder Joey Gonzalez. Each episode tackles a real question in AI clearly, quickly, and without the hype. 📽️ Episode 4: Is Post-Training the New Pre-Training?

AI is progressing exceedingly fast. It's hard for startups and builders to keep up. Learn how in this mini-documentary by RunLLM w/ top AI researchers, enterprise builders, and system designers. dj patil, Joey Gonzalez, Omar Khattab, Shirshanka Das, Vikram Sreekanti, Chenggang Wu 📽️

We’re excited to introduce RunLLM v2 today! 🎉 RunLLM v2 is rebuild of the product from the ground up focused on delivering the most powerful and flexible platform for enterprise support teams. Read the RunLLM v2 launch blog post: 👉 tinyurl.com/49st5ns2 Today’s launch

Excited to share that we’ve launched RunLLM v2! 🎉 We rebuilt the product from the ground up to create the most powerful, flexible platform for enterprise support teams. Check us out on Product Hunt and let us know what you think: producthunt.com/products/runll…

📢 Agent Infra Demo Night in #SF on Aug 19 📢 Cohosted w/ @georgian_io & Datadog, Inc., meet the founders building the infra powering the agentic future🛠️ Featuring: Letta Flox RunLLM & more RSVP: lu.ma/9uifuoqp #AgentInfra #AIInfra #DeveloperTools #AI