Hi guys, I built a tool www.lovespreadsheets.com earlier this year and a huge problem we kept running into is processing messy, real-world, complex spreadsheets for AI agents. Even a "medium" sized spreadsheet converts to about 1m+ tokens if read fully, which immediately blows up the current context windows of most models. So I noticed most agents sample data from spreadsheets in chunks instead. So I (& Claude) built this library Sheetgraph, https://github.com/asharma327/sheetgraph
Hey HN, We build financial AI agents, and Apgar is the tool we wrote to see whether a harness change made an agent better or worse in production. Our offline evals can't cover every kind of question or session real users bring, and the LLM judge we run in Langfuse is too expensive to use on more than a small slice of traffic, so some failures get through. Apgar is a small release health checker that sits on top of our Langfuse data. It picks up the release from the production traces, and for the
How I Built the Most AI-Pilled Company in the World Don't be put off by the clickbait headline, this piece by Jacob Sansbury describing how they are building Spawn is a fascinating exploration of the bleeding edge of what's possible with agentic engineering against frontier models. Spawn is a massively multiplayer gaming environment where players can use prompts (to the in-game agent, Savi) to modify the game world. I fired it up on my phone for a few minutes and was able to prompt a castle into
A top executive of a Singapore AI cloud company that was accused of illegally selling Nvidia chips to China could also have been a Chinese spy, sources have told the New York Times.
Dream is grounded in real physics and construction standards. Just as LLMs learn from text, Dream's world model is trained on more than 100 million square feet of building data gathered from permit archives across the United States.
SuperMe is a network of AI profiles built from the knowledge of real-life experts. When you ask a question, the platform determines which experts are best suited to answer and creates a group chat with their AI profiles.
Hi HN, today we're launching the biggest update to Tella ever ( https://tella.com/ ). Tella is all-in-one video creation. You can record, edit and publish with one tool. Today we're shipping: 1. Tella Agent: An in-app video editing agent 2. Tella Motion: Rich motion graphics support 3. Auto Capture: Agentic screen recording Our in-app agent uses the same tools as our MCP. All year we've been exposing more of our editor to the MCP. So when we started working on the in-app agent a few weeks ago, a
Hi HN, we're Ahnaf and Seungmin from Simantic ( https://simantic.com ). We are building the simulation layer that lets engineers and AI agents test and validate firmware without hardware. Before Simantic, we were ex-firmware engineers at companies like Neuralink and Tesla. We’ve worked on some of the coolest projects, like the Cybertruck and Roadster, back when they were still early prototypes. We started working on firmware back when ChatGPT didn’t exist yet, but over the years, we saw how much
During the dark ages of AI, when Opus 5 was incomprehensible and Codex Ultra was burning all tokens within a day, I decided to give open-source agents and models a try. What I saw was that a lot of the tools I tried were terminal-first, and desktop apps were less common. Additionally, I felt that lately a lot of the agents apps are slowly trying to become “superapps”. They keep adding more and more features that imo are not always useful and make the UI quite heavy and complex. This motivated me