Introducing Exa Agent: frontier web research at less than half the cost of GPT 5.5 and Opus.
/agent orchestrates a mixture of cost-effective models to complete any web research task, from simple data enrichments to building gigantic lists.
Introducing Exa Monitors - your agentβs radar for the web
Exa is a search engine built from scratch, and today we're exposing our "update" layer. Simply define what to find and how often - Monitors will return any new information, via webhook.
Exa powers most of the popular coding agents. We wrote about how we build and evaluate coding-related web search.
Blog and open evals: https://t.co/dwnVmYCJO3
We're excited to be powering search in Browserbase!
Exa can now be used inside of @browserbase sessions, increasing speed and quality of browser agent tasks.
Introducing Exa Deep: putting an agent inside every search
For each query, an agent runs in a loop until it gathers all information, then returns structured output.
Evals show Deep is Pareto optimal at 4-60s latency, ideal for quick, cost-efficient research!
Introducing Perpetual
An AI agent that automates biology experiments
Describe your protocol in natural language - our agent interprets, validates, and executes on real lab hardware
Let scientists focus on discovery, not execution
ππ» demo v0
i wanna start using AI in my IDE (i currently just copy-paste to ChatGPT)
how do Cursor, Windsurf, and Copilot compare?
if it matters: i'm mostly working on systems code (compiler, and runtime) mostly in C++, and scripting in Python