Teams for qa

Working harness designs — topology, agent roster, model choices, and the evidence behind them. 6 teams match.

4 operated · 2 reference designs — operated teams are listed first, reference designs after them.

See stack trends →

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

SortFeaturedRecently activeHighest trust
🧩

The Ari Collective

Intronode

Evidence-LinkedReal

Four-agent operating team: orchestration, engineering, operations, independent audit.

updated 4mo ago
Orchestrator–Worker4 agentsOpenClaw
OrchestratorEngineerOperationsAuditor
software-deliveryoperations
Outcome90.8%
Economics[unknown] · deliberate
3 proof
🕸

Alexey Grigorev’s software agent team

Alexey Grigorev

From public sources · Self-ReportedCurated

Claude Code roles take tasks through specification, implementation, testing and final acceptance.

updated 19d ago
Pipeline3 listed membersClaude Code
Implementation and testsQuality assuranceCI/CD monitoring
software-delivery
Outcome[unknown]
Economics[unknown] · deliberate
1 proof
🕸

Alireza Rezvani's Seven Claude Code Subagents

Alireza Rezvani

From public sources · Self-ReportedCurated

Seven Claude Code subagents in separate context windows, including product, backend, launch and a hostile QA reviewer, used to plan a solo product.

updated 5mo ago
Other7 agentsClaude Code
ProductBackendLaunchQA reviewer
software-delivery
Outcome[unknown]
Economics[unknown] · deliberate
1 proof
🕸

PGA TOUR Automated Content System

PGA TOUR

From public sources · Self-ReportedCurated

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
sportsmedia
Outcome[unknown]
Economics[unknown] · deliberate
1 proof
💬

ChatDev Communicative Pipeline

Academic / Open-Source (ChatDev & MetaGPT)

From public sources · Self-ReportedCuratedReference design

5-role sequential pipeline — 22,949 tokens, 148s per software task.

updated 3y ago
Pipeline5 agentsChatDev
CEOCTOProgrammerReviewer+1 more
software-delivery
Outcome[unknown]
Economics22,949
1 proof
🏭

MetaGPT Software Dev Pipeline

Academic / Open-Source (ChatDev & MetaGPT)

From public sources · Self-ReportedCuratedReference design

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

updated 3y ago
Pipeline5 agentsMetaGPT
Product ManagerArchitectProject ManagerEngineer+1 more
software-delivery
Outcome85.9%
Economics[unknown] · deliberate
1 proof