Workflow · saas · workflow
Anthropic's multi-agent research system: lessons from prototype to production
Research tasks are inherently open-ended and path-dependent, making them impossible to solve with fixed, linear pipelines; the unpredictability requires AI agents that can dynamically adapt their approach based on intermediate findings.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User submits research query
When a user submits a query, it initiates the multi-agent research process.
Tools used
Claude Opus 4Claude Sonnet 4
Outcome
The multi-agent system with Claude Opus 4 as lead agent and Claude Sonnet 4 subagents outperformed single-agent Claude Opus 4 by 90.2% on internal research evaluations, and users report saving up to days of work on complex research tasks.
What failed first
Early agents in the system made coordination errors such as spawning excessive subagents, searching endlessly for nonexistent sources, and showing consistent bias toward SEO-optimized content farms over authoritative sources.
Results
Time savedup to days of work
Volume90.2%
Grounding & classification
Source type: technical build writeup
25 fields verified against source quotes.
agentic workflowai agentknowledge searchmulti agent workflowsummarizationknowledge basefailure mode describedmetric backedproduction runtime claimedtools describedvendor confirmedworkflow describedsoftwareaccuracy improvementthroughput increasetime savedtechnical build writeupagentic task execution