Teams

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

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

Andon Labs' AI-run boutique in San Francisco, managed by the agent Luna with persistent helper agents for procurement, email, phone, social media and scheduling.

Planner and coding agents built into Atlassian's internal Jira that take a work item to a pull request, with an engineer approving each step.

Personal bots supporting communications, family logistics and engineering work.

A self-hosted OpenClaw team supports recurring family school-progress reporting.

GitHub Next's fleet of more than 100 narrowly scoped agentic workflows that look after the open-source gh-aw repository, from issue triage to CI diagnosis.

An Italian online daily that is researched, written, verified and edited by five AI agents and goes live without prior human review.

Spotify's internal agent setup for code changes: an interactive agent scopes the task, a background coding agent opens the pull request, and an LLM judge checks the diff.

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

Multi-agent chat assistant that lets people at Wix ask business data questions in natural language and steers them to the right metrics and dimensions.

Specialist agents turn campaign requirements into data-informed media plans.

Specialist agents analyze team designs before an orchestrator reconciles their findings for engineer review.

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

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

A chief of staff and specialist agents supporting business operations.

Internal fleet-scale Java 8/11→17 upgrades — >4,500 dev-years saved, $260M.

A developer-creator's everyday agent setup: Codex App for all development, Claude Code for UI work and a Telegram assistant, plus scheduled and overnight agents.

A personal team for information collection, analysis and development.

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

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

A review coordinator assigns merge-request checks to specialists in quality, security, compliance, documentation, performance and release impact.

Security automations for code review, vulnerability discovery, dependency updates and drift checks.

Human-orchestrated Devin fleet — 8-12x efficiency on a 6M-LoC migration.

A planner splits web research into parallel tasks while an observer retains shared context.

A supervisor agent routes Fastweb + Vodafone customer questions to specialist use-case agents, while Super Agent coaches human consultants.

An internal on-call copilot answering questions from Uber documentation.

Specialist agents investigate data questions and prepare pipeline changes for engineer review.

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.

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.

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.

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.

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

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

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.

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.

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.