Letters from Andrew Ng

AI-assisted agentic coding reinforces iterative software development. These three loops can guide development and help you decide what to build.

If you haven’t already, I encourage you to experiment with using AI agents not just to chat but to actually do work for you on your desktop.

Coding agents are accelerating different types of software work to different degrees.

AI-native software engineering teams operate very differently than traditional teams.

Should there be a Stack Overflow for AI coding agents to share their learnings with each other?

I’m thrilled to announce Context Hub, a new tool to give to your coding agents the API documentation they need to write correct code.

Happy 2026! Will this be the year we finally achieve AGI? I’d like to propose a new version of the Turing Test, which I’ll call the Turing-AGI Test, to see if we’ve achieved this.

As amazing as LLMs are, improving their knowledge today involves a more piecemeal process than is widely appreciated.

If you have not yet built an agentic workflow, I encourage you to try doing so, using the simple recipe I’ll share here!

AI agents are getting better at looking at different types of data in businesses to spot patterns and create value. This is making data silos increasingly painful.

In last week’s letter, I explained how effective agentic AI development needs a disciplined evals and error analysis process, and described an approach to performing evals.

Readers responded with both surprise and agreement last week when I wrote that the single biggest predictor of how rapidly a team makes progress building an AI agent lay in their ability to drive a disciplined process for evals...

Automated software testing is growing in importance in the era of AI-assisted coding.

There is significant unmet demand for developers who understand AI.

Parallel agents are emerging as an important new direction for scaling up AI. AI capabilities have scaled with more training data, training-time compute, and test-time compute.