Big news for developers! We’re launching two new products to bring code execution & dev environments to AI apps: 📦 Together Code Sandbox ⚡ Together Code Interpreter Now you can run LLM-generated code in secure, scalable, fully managed environments. Details below 👇

Announcing our latest example app to show off how to do structured OCR on Together AI! An app that lets you easily split your restaurant bill – powered by llama 4 vision w/ JSON mode on Together. Try it today -> usebillsplit​.com

Introducing the Open Deep Research CLI! Generate research reports directly from your terminal with `npx open-deep-research`.

Introducing the Open Deep Research CLI! Generate research reports directly from your terminal with "npx open-deep-research".

Data Science Agent – implemented from scratch in code! In this notebook, we share our Data Science Agent implementation & go over how it works step-by-step. We use an iterative ReAct workflow capable of reasoning, code execution, and self-correction. Link below!🔽

Fully open source and capable Data Science Agent that you can run in CoLab! Great job by Federico Bianchi Zain Shang Zhu 👏 github.com/togethercomput…

1/ We built an open-source AI agent that can reason like a data scientist. It loads data, writes Python code, retrains when models fail, and solves real Kaggle + DABStep tasks. Here’s how we did it (and how you can too): 👇

Excited to introduce Open Data Scientist: ✅outperforms Gemini data science agent ✅solves real Kaggle tasks ✅fully open source, easy to adapt ✅sandbox for safe exec Step-by-step tutorial on building our agent together.ai/blog/building-… Great job Federico Bianchi Shang Zhu

Introducing the Open Deep Research app! Generate detailed reports on any topic with open source LLMs. Free & fully open source. We’re releasing everything: evaluation dataset, code, app, and blog.🔥

Our Open Data Scientist agent is now ranked on the DABStep data analysis leaderboard! We released everything - so you can try it yourself!🔥: • Full codebase • Detailed workflow recipe • Benchmarks See how we created it. 🧵

📢New conference where AI is the primary author and reviewer! agents4science.stanford.edu Current venues don't allow AI-written papers, so it's hard to assess the +/- of such works🤔 #Agents4Science solicits papers where AI is the main author w/ human advisors. 💡Initial reviews by

Can LLMs predict the future? In FutureBench, friends from Together AI create new questions from evolving news & markets: As time passes, we'll see which agents are the best at predicting events that have yet to happen! 🔮 Also cool: by design, dynamic & uncontaminated eval

Most AI benchmarks test the past. But real intelligence is about predicting the future. Introducing FutureBench — a new benchmark for evaluating agents on real forecasting tasks that we developed with Hugging Face 🔍 Reasoning > memorization 📊 Real-world events 🧠 Dynamic,

🔮Exciting new benchmark testing how well AI predicts the future! Each week, we curate news + prediction markets for questions about next week. Then we have agents make forecasts. Requires advanced research + reasoning Together AI Hugging Face 📜together.ai/blog/futureben… 🌐

📢New policy brief: Does labeling AI content affect its persuasiveness? Scholars evaluate the impact of authorship labels on how people perceive AI-written policy messages. hai.stanford.edu/policy/labelin…

🚨 Together AI is proud to sponsor the Best Paper Awards at #Agents4Science - the world's first conference where AI agents author AND review papers! 🤖 💰 3 winners get $10K in compute credits 📅 Submission deadline: Sept 5 ⏰ Only 15 days left!

Building AI agents for complex engineering tasks ≠ building chatbots 🧵 Most AI agents today excel at short, simple tasks. But automating multi-day engineering workflows? That’s a whole different game. At Together AI, we learned this the hard way while optimizing LLM