Skip to content
All tool news

Tool desk · Updated daily

Tool news·Perplexity·

Perplexity Integrates Deep Research Into Computer With Search as Code Architecture.

Perplexity brings Deep Research to Computer using Search as Code, running thousands of parallel retrieval steps for Pro and Max subscribers.

CW

Create With tool desk

1 source checked · 2 min read · 3 sections

ShareLinkedIn

Perplexity has integrated its Deep Research feature directly into Computer, the company's AI agent environment, connecting it to the underlying infrastructure that powers code generation, sandboxes, and data access.

The update, announced on LinkedIn, makes Deep Research available as a native skill within Computer rather than a separate tool. It now taps into Computer's agent harness, gaining access to search as code generation, long-running sandboxes, connectors, tools, and licensed data.

Search as Code at Scale

Deep Research in Computer is built on what Perplexity calls its Search as Code architecture. Instead of executing searches sequentially, the model writes code that assembles search operations dynamically, running thousands of retrieval steps in parallel.

Each query gets its own tailored retrieval strategy. The system determines which sources to query, how to parse results, and which follow-up searches to spawn, all generated programmatically based on the specific question.

Perplexity claims the new implementation outperforms the legacy Deep Research system on every internal benchmark, though specific metrics were not disclosed.

Computer Gets Deeper Context

Computer, which recently became available inside Microsoft Office apps, is Perplexity's environment for running AI agents that can execute code, maintain state across sessions, and connect to external tools. By embedding Deep Research as a native capability, users can now trigger comprehensive research operations without leaving the agent workflow.

The integration gives Computer access to Perplexity's licensed data sources alongside the ability to write and execute search code on the fly. Long-running sandboxes mean research tasks can continue processing in the background while users work on other tasks.

This follows a pattern of infrastructure investments at Perplexity. The company recently shipped query-aware compression to cut retrieval tokens by 70% and open-sourced a unigram tokenizer with 5x CPU performance improvements.

Availability

Deep Research in Computer is available now to Pro and Max subscribers. Max users also recently gained access to Claude Opus 4.8, giving them multiple frontier model options within the same interface.

The company has not announced pricing changes or plans to bring the feature to free-tier users.

Sources

1 checked

How we cover tool news: Create With's tool desk drafts these reports with AI from the sources listed above and checks them against those sources before publishing.

Worth passing on?

ShareLinkedIn

Go deeper on Perplexity

Related reading, watching and going.

Everything on Perplexity →

The briefing

16 Jun 2026

How Claude Code Lets One Person Replace SEO Teams Fast

Discover how Claude Code lets one non-technical user automate SEO — from keyword discovery to publishing — replacing SEO teams easily without writing code.

Read →

The briefing

31 Mar 2026

Vibe Marketing Review: Can AI Agents Really Automate Marketing?

An honest review of vibe marketing with AI agents. Learn if automated marketing actually works for solo founders and small teams. Plus: Claude Code leak, Factory Missions.

Read →

The briefing

3 Mar 2026

Perplexity Computer Platform & Notion AI Agents Review 2025

Perplexity's 19-model AI platform, Claude Code mobile control, iPhone offline AI with Qwen 3.5, and Notion's custom agents are transforming AI automation.

Read →
31 min

Conference

How to Get Your Product Recommended by Google and ChatGPT

Tanya Van Gastel presents the APEX framework for making products discoverable in AI-powered search engines like ChatGPT and Google's AI Overviews. She explains how AI is fundamentally changing product discovery and buyer behavior, then breaks down five critical components: Authority (being cited as a solution), Presence (visibility across search platforms), Expertise (creating high-quality money pages), Endorsements (off-site validation), and Extractability (making content easy for AI to process). The talk emphasizes quality over quantity, with data showing 50% of SaaS SEO revenue comes from fewer than 10 high-performing pages.

Watch now ↗

Latest tool news

What else changed this week.

All tool news
VercelDigest

What Vercel Shipped in Late October

Vercel shipped quicker static deployments, four AI Gateway models, more free domain choices and new CLI controls in late October. The changes cover developers testing sites…

Vercel

Vercel Adds Submit_feedback to Its MCP

submitfeedback is a new Vercel MCP tool that lets agents and harnesses send bug reports, friction reports and feature requests directly to the Vercel team. Feedback can include…

The Create With Briefing

Don't watch forty changelogs. Read one email.

Every Tuesday: the tool changes worth knowing, real business use cases, and what's on near you. Free, unsubscribe any time.