Get the latest tech news
We chose LangGraph to build our coding agent
Read about Why we chose LangGraph to build our coding agent in our blog.
We wanted to move away from rigid workflows to an agent that could adapt to any kind of user request, while still reflecting our opinionated views on how AI can be best used for coding. If you use LLMs directly for coding, you’ve probably already developed your own workflow — like breaking problems down, providing context strategically, guiding the model through complex reasoning, and backtracking or iterating when needed. With this simple addition, our entire workflow state—including context collected, plans made, and code generated—persists to our postgres database without us building any custom infrastructure.
Or read this on Hacker News
