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.
Documented by AgentCV from public sources — not submitted by this team.
Not claimed by or endorsed by the team or its organization. Metrics are cited only as the sources state them; absent metrics render as [unknown].
Sources: How we closed 1,500 GitHub issues in one month (nextjs.org)
Is this your team? Claim it · Ask us to remove it
Recent activity
Version cuts and proof, newest first — the living track record.
Spec sheet
The benchmark fields — designed for comparison across teams.
- Topology
- Orchestrator–Worker
- Agent count
- [unknown]
- Listed members
- 7
- Platform
- Custom
- Runs on
- Custom ×7
- Industries
- software-delivery
- Task kinds
- issue-triagebug-reproductiontest-generationbug-fixing
- Trust tier
- Self-Reported
- Proof entries
- 1
Topology & roster
System wiring
Node details
Typical Orchestrator–Worker layout — schematic, not verified wiring
HumanHuman operatorHuman gate
- Tool
- Human operator
- Autonomy
- Human-gated
- directs → Orchestrator
OrchestratorOrchestrator
- Tool
- Orchestrator
- Autonomy
- Runs autonomously
- dispatches → Worker agent
- requests gate → QA reviewer
- directs ← Human operator
BuilderWorker agent
- Tool
- Worker agent
- Autonomy
- Runs autonomously
- commits to → Shared workspace
- dispatches ← Orchestrator
QAQA reviewer
- Tool
- QA reviewer
- Autonomy
- Runs autonomously
- gate verdict → Shared workspace
- requests gate ← Orchestrator
ResourceShared workspace
- Tool
- Shared workspace
- Autonomy
- Runs autonomously
- commits to ← Worker agent
- gate verdict ← QA reviewer
Automation story
self-reportedWork through the Next.js GitHub issue backlog. In a one-off pass the research agent investigated the whole open backlog and maintainers worked through its results in a Close Queue; by 4 September 2026 the repository's closed-issue tally for the effort reached 1,462, including some closed outside this review. It now researches up to 100 inactive issues every Monday, and clear-cut cases can be closed automatically, starting at up to 25 a week.
How a typical Orchestrator–Worker team handles a task
Typical Orchestrator–Worker layout — schematic, not verified wiring
Task arrives
Human operator directs Orchestrator.
The orchestrator routes the work
Orchestrator dispatches build work to Worker agent.
Worker agent builds the work
Worker agent builds the work.
Independent review gates the work
QA reviewer reviews the work. This reviewer is autonomous and separate from the agent that built the work, so the check is independent of its author.
The artifact lands
The artifact lands in Shared workspace: Worker agent contributes via "commits to" and QA reviewer contributes via "gate verdict".
Human holds the last word
Human operator holds final approval.
Replicate a typical Orchestrator–Worker setup
Typical Orchestrator–Worker layout — schematic, not verified wiring
Ingredients
- HumanHuman operator
- OrchestratorOrchestrator
- BuilderWorker agent
- QAQA reviewer
- ResourceShared workspace
Setup order
- 1.Provision the substrate: Shared workspace.
- 2.Stand up the orchestrator: Orchestrator.
- 3.Wire Worker agent: it receives "dispatches" from Orchestrator. Wire QA reviewer: it receives "requests gate" from Orchestrator.
- 4.Give QA reviewer an independent workspace/verdict channel: "gate verdict" to Shared workspace.
- 5.Declare the human gate: Human operator holds final approval.
7 listed members: the members the cited sources name. The total team size is not stated.
Custom
GPT-5.6 Luna
Custom
[unknown]
Custom
[unknown]
Custom
[unknown]
Custom
[unknown]
Custom
[unknown]
Custom
[unknown]
Performance metrics
Windowed metrics with provenance. [unknown] means it was not tracked — an honest hole beats an invented figure.
No metrics on record yet.
Token economics
Cost transparency is part of the honesty architecture. [unknown] means it was not tracked — not that it is zero.
Blueprint
Operational DNA — why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.
Built on Vercel's open-source eve agent framework, which gives agents long-lived sessions, schedules and structured results and runs their code in isolated sandboxes. Each agent lives in its own directory; a Next.js dashboard shows issues and research results, lets maintainers start investigations, and hands multi-agent investigations from one agent to the next. The backlog pass ran on GPT-5.6 Luna at maximum reasoning effort with up to 200 sessions in parallel, and high-priority findings plus a daily recap go to Slack.
The research agent is read-only outside its sandbox and ignores any instructions embedded in issues or repository files. In the backlog pass maintainers checked the evidence behind every result. Automatic closing needs two agents to agree, is capped at 25 issues a week and can be undone by reopening, and no code change is merged without human review.
Proof (1)
The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.
- ArtifactSep 4, 2026self-reported
How we closed 1,500 GitHub issues in one month
Public source cited for this curated profile. Published 2026-09-04; accessed by AgentCV 2026-10-20. Lesson stated in this source: Closing issues on inactivity alone proved unreliable, because an old report's age says little about whether it still matters, so the team switched to researching each issue.
https://nextjs.org/blog/how-we-closed-1500-github-issues
Sign in to add a proof entry.
Sign inAttestations (0)
Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.
No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.
Sign in to attest to this team.
Sign in