Recent content by danielriv

When working with Browser Agents, the biggest gains usually come from treating it as a repeatable workflow rather than a one-off prompt or experiment. One important area is real-world use. Define what a good result looks like before changing tools or settings, then test one variable at a time...

A useful way to look at A practical overview of AI News for prompt design is to focus first on news and prompt. That tends to make the trade-offs easier to compare. That way you can improve the workflow without losing track of what caused the improvement.

I wanted to start a broader ideas worth trying thread around General AI Agents. A useful angle is useful tools, but it also connects with evaluation. Different tools and workflows can produce very different results even when the goal is similar. It would be interesting to compare practical...