10 years ago, Parag Agrawal and I were working together to introduce ranking to Twitter’s timeline for hundreds of millions of consumers. Now he’s started Parallel Web Systems to build infrastructure for a very different kind of user: AI agents. And in a full circle moment, we’re able to work together

we've been building

Added the parallel search api to the chart for completeness.

Aravind Srinivas fixed the table for you

We shipped the Parallel Search API today. For use by agents, our API meaningfully outperforms products and technologies built over years and decades with substantial resources by very talented teams. Why?

When we first built the Monitor API, we made the classic mistake of thinking we knew what it was for. We opened up access to the team, left for lunch, and came back to see that our colleagues had begun testing it out for all kinds of needs:

Today, we’re introducing updates to the Task API that deliver 3-5x improvements to latency. Here’s Aman Kansal , one of our engineering leads on the Task API, to explain: parallel.ai/blog/task-api-…

Parallel's Task API is designed for highly extensible asynchronous web search tasks like deep research, enrichments, competitive intelligence, and the like. Our Processor architecture delivers the best option across the Pareto frontier of cost and accuracy, and now, latency.