Deep Research, Now in Computer - Perplexity

2026-07-10 · Source: perplexity.ai via Google News · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Intermediate, medium

Summary

Perplexity has launched Deep Research in Computer, an AI-driven tool designed to tackle complex questions by breaking them into subtasks and routing them across over 20 frontier models. Built on Perplexity's Agent Search SDK and Search as Code architecture, this system generates thousands of parallel retrieval steps, allowing models to dynamically assemble search queries. It synthesizes information from both user-provided files and live web sources, citing every claim to primary sources. Deep Research transforms a single complex query into structured deliverables like reports, slide decks, spreadsheets, or dashboards. Benchmarks indicate significant improvements in accuracy, depth of analysis, and citation quality, with Computer DR achieving 83.8% on BrowseComp compared to Legacy DR's 40.7%.

Key takeaway

For research scientists or consultants needing to produce comprehensive, cited reports from complex inquiries, Perplexity's Deep Research offers a significant efficiency gain. You can streamline your workflow by inputting a single query and receiving structured deliverables like decks or spreadsheets, complete with verified claims and primary source citations. This tool allows you to integrate internal data with real-time web information, reducing manual synthesis and improving the reliability of your findings.

Key insights

Perplexity's Deep Research uses AI agents and multi-model routing to deliver structured, cited research from complex queries.

Principles

• Complex questions benefit from decomposition.
• Specialized models improve task accuracy.
• Verifiable claims require primary citations.

Method

Deep Research builds a plan, routes subtasks to 20+ frontier models, cross-references user files with the live web, and cites every claim.

In practice

• Generate financial valuations.
• Compare legal data privacy laws.

Topics

• Deep Research
• AI Agents
• Multi-model AI
• Automated Information Retrieval
• Structured Data Generation
• Research Automation

Best for: AI Product Manager, Product Manager, Entrepreneur, Consultant, Research Scientist, Data Scientist

Related on AIssential

• Perplexity upgrades Deep Research tool with Claude Opus 4.5 integration — Perplexity's Deep Research tool, powered by Claude Opus 4.5, leads in a new open-source benchmark for comprehensive research agents.
• - Perplexity — Perplexity AI combines real-time search with LLMs to deliver direct, cited answers.
• How AI Agents Reshape Knowledge Work - Perplexity — AI agents like Perplexity Computer autonomously execute complex workflows, significantly reducing human effort and cost while expanding the scope and cognitive complexity of tasks.
• Best ai for research purposes? — Combining specialized AI tools and strategic prompting mitigates hallucination and improves accuracy for deep, niche research.
• DeepSurvey: Enhancing Analytical Depth and Citation Reliability in Automated Survey Generation — DeepSurvey improves automated survey generation through deep analysis and reliable citation validation.
• Google’s new Deep Research and Deep Research Max agents can search the web and your private data — Google's new Deep Research agents fuse web and private data, generating visual reports for enterprise workflows.

See Counsel's argued verdicts on the open AI decisions leaders are weighing →

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by perplexity.ai via Google News.