Teams for research

Working harness designs — topology, agent roster, model choices, and the evidence behind them. 14 teams match.

9 operated · 5 reference designs — operated teams are listed first, reference designs after them.

See stack trends →

Run an agent team? Add it — no public links needed.

SortFeatured Recently active Highest trust

AgentCV Build Crew

Hyuk Jun Kim

Self-ReportedClaims stated by the owner. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.Real

Claude, Hermes and Codex agents that research, build, review and ship agentcv.ai. One human owner approves every release.

updated 24d ago

Orchestrator–Worker4 agentsMixed

Orchestrator· Claude OpusOperations & review gateBuilders & researchers· Claude Opus / SonnetIndependent reviewer

software-delivery

Outcome[unknown]

Economics[unknown] · deliberate

Virtual Lab

zou-group

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 2 of the 3 evidence-linked proof entries needed for Evidence-Linked are on record.Curated

A human-guided research team used to design SARS-CoV-2 nanobodies.

updated 19d ago

Supervisor4 listed membersCustom

Research leadImmunology adviserMachine learning specialistComputational biology specialist

Outcome[unknown]

Economics[unknown] · deliberate

Bertelsmann Content Search agents

Bertelsmann

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.Curated

A coordinator and four specialist agents that search Bertelsmann's book, broadcast, news and web sources for staff.

Orchestrator–Worker5 listed membersLangGraph

CoordinatorPublishing catalog searchBroadcast archive searchNews archive search+1 more

Outcome[unknown]

Economics[unknown] · deliberate

Claude Research

Anthropic

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.Curated

Parallel research agents gather information for a lead researcher and citation agent.

Orchestrator–Worker3 listed membersCustom

Research coordinationResearchCitation placement

Outcome[unknown]

Economics[unknown] · deliberate

Luke Lin’s GTM agent team

Luke Lin

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.Curated

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

updated 19d ago

Orchestrator–Worker11 agentsCustom

GTM coordination

Outcome[unknown]

Economics[unknown] · deliberate

PGA TOUR Automated Content System

PGA TOUR

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.Curated

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

updated 7mo ago

Other5 listed membersCustom

Research and fact checkingWritingQuality and brand checksChannel editing+1 more

Outcome[unknown]

Economics[unknown] · deliberate

WEBTOON Comprehension AI (WCAI)

WEBTOON Entertainment

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.Curated

LangGraph workflow agents that profile characters, attribute dialogue, summarize story arcs and turn that into business insights for WEBTOON teams.

Pipeline4 listed membersLangGraph

Character profilerDialogue attributionStory summarizerBusiness insight agent

Outcome[unknown]

Economics[unknown] · deliberate

Wyndo's Seven-Bot Grok Bot Team

Wyndo

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.Curated

Seven cloud-run Grok Bot bots that a newsletter writer uses for social posts, scheduling, invoices, content research, SEO, images and business coaching.

updated 1mo ago

Other7 agentsGrok Bot

Social contentChief of staffInvoicesContent research+3 more

Outcome[unknown]

Economics[unknown] · deliberate

Zembl AI sales workforce

Zembl

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.Curated

Toni and the agents added after it research leads, keep Salesforce current, follow up by SMS and run energy comparisons for Zembl's sales team.

updated 14d ago

Other7 listed membersCustom

Lead sales agentSalesforce admin agentSMS follow-up agentEnergy comparison agent+3 more

Outcome[unknown]

Economics[unknown] · deliberate

Agent Laboratory

Samuel Schmidgall

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 2 of the 3 evidence-linked proof entries needed for Evidence-Linked are on record.CuratedReference design

Research assistants for literature review, experiment execution and report preparation.

updated 19d ago

Pipeline5 listed membersCustom

Literature researcherExperiment plannerExperiment implementerData preparation contributor+1 more

Outcome[unknown]

Economics[unknown] · deliberate

AI-Researcher

HKUDS

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 2 of the 3 evidence-linked proof entries needed for Evidence-Linked are on record.CuratedReference design

A research pipeline evaluated on scientific implementation and manuscript tasks.

updated 19d ago

Pipeline5 listed membersCustom

Research resource collectorResearch analystResearch implementerImplementation adviser+1 more

Outcome[unknown]

Economics[unknown] · deliberate

Anthropic Orchestrator-Workers Pattern

Anthropic

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

Central LLM dynamically breaks down tasks and delegates to specialist workers.

Orchestrator–Worker2 listed membersClaude API

OrchestratorWorker

software-deliveryresearchdata-extraction

Outcome[unknown]

Economics[unknown] · deliberate

Claude Code Sub-agents Pattern

Anthropic

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

Lead agent spawns specialist subagents in isolated context windows.

Orchestrator–Worker2 listed membersClaude Code

software-delivery

Outcome[unknown]

Economics[unknown] · deliberate

CrewAI Sequential Research Crew

CrewAI

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

Researcher → Analyst sequential pipeline with natural context handoff.

Pipeline2 agentsCrewAI

ResearcherAnalyst

researchcontent

Outcome[unknown]

Economics[unknown] · deliberate