Teams

Enterprise agent + majority voting — claimed #1 on GAIA, Dec 2024.

Personal code review with parallel specialists and a consolidated assessment.

An orchestrator delegates document analysis and response formatting to specialist agents.

A recruiting assistant that delegates sourcing, evaluation and engagement work to specialist sub-agents.

Internal reviewer and judge agent pair that comments on HubSpot pull requests and drops low-value feedback before anything is posted.

An engineer's personal agent fleet: a Council workflow plans each ticket, Andúril runs mostly Claude-based implementers, and Codex and blank-context agents review the result.

LangGraph agents on Amazon Bedrock AgentCore that check change requests, enrich incidents and help staff choose change models at Iberdrola.

An early personal-blog setup for Japanese writing, English translation and editorial support.

Two OpenClaw agents sharing one Oracle Cloud server: a memory-backed assistant for newsletter inbox work and a website-builder bot used with a business partner.

Heterogeneous ensemble + critic voting — 75.2 GAIA validation Pass@1.

Domain-specific data retrieval agents share a routing and aggregation layer for financial queries.

Two-thirds of customer-service chats in month 1 — 2.3M conversations.

Planner + executor pool + per-step verification — vendor-claimed 77.6% on GAIA.

Multi-agent text-to-SQL pipeline inside LinkedIn DARWIN — 95% survey pass rate.

A standing go-to-market team dispatches work from Slack using shared context and memory.

Microsoft Research generalist 5-agent system: GAIA 32.33%, WebArena 32.8%.

Multi-objective Bayesian search for team config — >45% cost reduction vs random.

Planner + executor in a cloud sandbox — vendor-claimed GAIA SOTA at launch.

A multi-agent question-answering system that answered prospective students' admissions questions for the University of Transport Technology in Hanoi during summer 2025.

39.33% on SWE-bench Lite (lab-page claim).

Project-specific coding specialists coordinated through a main Claude Code session.

5-agent SOP-encoded pipeline — 124.3 tokens/LoC, executability 3.75/4.

A Hermes Agent profile set up as a personal fitness trainer that runs its work past a council of specialist sub-agents, such as a mobility expert, a physical therapist and a calisthenics coach.

Minimal bash-only agent — reference floor on SWE-bench Verified.

Planning, research and tool-calling roles collaborate on e-commerce support tickets.

Agents for content and website code, coordinated through a task board.

An orchestration agent delegates focused work to analysis and writing subagents.

Independent agents the Next.js maintainers use to research, reproduce, verify and fix GitHub issues; they helped cut the backlog by 1,462 closed issues in about three weeks.

Specialized Claude Code review agents check pull requests before human reviewers assess design.

Triage-to-specialist handoff pattern — educational Swarm framework, now replaced by the OpenAI Agents SDK.

A supervisor coordinates incident-investigation sub-agents while engineers steer the work.

Fleet diagnostic agents combine anomaly detection, parallel investigation and report synthesis.

Research, writer, validation, editor and multimedia agents on Amazon Bedrock that produce PGA TOUR recaps and betting profiles every week.

A supervisor coordinates specialist agents for incident investigation.

Solo agent, multi-model orchestration — 70.4% on SWE-bench Verified.

A core coding loop delegates to workers and specialist subagents.

A product-manager agent and a coder agent, built from the author's own Bobbo agent code, that take turns running his MCP deals server.

A scientific workflow connects literature research and data analysis to human-run experiments.

Sam, Barry, Karen and a CRM agent answer leads, check calls for compliance, route complaints and keep CRM records current for Send Payments.

Internal agent toolkit Shopify uses to port its Shopify app from React Native to native, with an orchestrator, an implementer, a test-writing subagent and independent reviewers.

Specialist analysis agents and domain judges that propose and vet changes to Shopify's product taxonomy before the taxonomy team reviews them.

A personal agent team for research, content drafts and engineering tasks.

Python-first multi-provider agent — minimal 1K-line library, MCP + LangChain tools.

Claude Code terminal 'employees' with set jobs, from marketing and ops to project coordination and finance, that help Drew Burdick run the StealthX agency.

An agency founder's role-specific Hermes Agent sub-agents for Shopify engineering, search engineering and client-meeting prep, with Hermes also handling almost all of his social media.

Solo software agent with custom ACI — 12.5% SWE-bench, 87.7% HumanEvalFix.

Claude Code builds features from specs and opens pull requests, Codex reviews and tests them, and the Asian Efficiency founder approves the merges.

An orchestrator coordinates service agents for internal platform operations.

A one-person Tucson local news site where AI models write the morning brief, preview council agendas, draft meeting reports and voice a podcast and a Spanish newscast.

Coordinator + reused sub-agents across two developer-platform tools.