Information technology / Business software and AI

Anthropic: A research service with cooperating AI agents

Company
Anthropic
Country
United States
Adoption stage
In operation
Source published
Date basis
The date the source was published. It can differ from the date adoption started.
How the source was checked
Read the full source text

The work problem

Complex research changes direction as new evidence appears. A single search or fixed workflow cannot adequately explore multiple independent topics, and a single agent has limited context capacity. Anthropic needed both breadth and reliability in its live Research service.

Technology and data

The lead Research agent analyzes the user's question, saves a plan and creates specialized subagents in parallel. Each subagent searches the web and connected material and returns condensed findings. The lead decides whether further research is needed and synthesizes the results, after which a citation agent links claims to specific evidence locations. Checkpoints and retries allow recovery without restarting from scratch. Human testers also check errors and source-selection biases missed by automated evaluation.

Results

Anthropic said Claude Opus 4 leading Claude Sonnet 4 subagents outperformed a single Claude Opus 4 by 90.2 percent on its internal research evaluation. It said parallel subagents and tool calls cut research time by up to 90 percent for complex queries. The source reports that the service is in production and that users apply it to finding business opportunities and resolving technical problems.

Limits and open questions

The 90.2 percent figure is relative performance on an internal evaluation, not an accuracy rate. The company said multi-agent systems use about fifteen times as many tokens as ordinary chats and did not provide average customer time savings.

Sources

Compiled from public sources. These are not results from ATF Works customers.

Read original (opens in a new tab)