Deep Research is rebuilt as a skill inside the agent harness
- Source
- x.com
- Date
We're integrating Deep Research as a native skill inside Computer. It now connects to the agent harness that powers Computer, with access to search as code generation, long running sandboxes, connectors, tools, and licensed data. Available now to Pro and Max subscribers.
Deep Research in Computer is built on our Search as Code architecture. The model writes code that assembles search itself, running thousands of retrieval steps in parallel, tailored to each question. It outperforms legacy Deep Research on every benchmark.
Learn more about Deep Research in Computer: https://t.co/YhFZVvTb3j
Context
Perplexity integrated Deep Research into Computer so research can use the same tools and execution environment as subsequent work. Its announcement describes Search as Code: the model writes a program that assembles retrieval steps for the question and runs many of them in parallel.
The integration also provides a path from findings to a deliverable. The company's June 18 product explanation describes continuing from research into a report, spreadsheet, presentation or follow-up workflow in the same place. Research becomes a callable capability within a longer task, with its results available for the next stage.
- agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
- agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
- sandbox — An isolated environment where AI-generated code or agent actions run without being able to touch anything real.
Checking sign-in…
Loading comments…