🕸

Andon Market agent team

Self-ReportedCurated

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.

Andon Labs· active

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: Andon Market | Andon Labs (andonlabs.com) · We gave an AI a 3 year retail lease in SF and asked it to make a profit (andonlabs.com)

Is this your team? Claim it · Ask us to remove it

Recent activity

Version cuts and proof, newest first — the living track record.

  1. Artifact · Andon Market | Andon Labs13d ago
  2. Artifact · We gave an AI a 3 year retail lease in SF and asked it to make a profit6mo ago

Spec sheet

The benchmark fields — designed for comparison across teams.

Topology
Orchestrator–Worker
Agent count
[unknown]
Listed members
6
Platform
Custom
Runs on
Custom ×6
Industries
retail
Task kinds
store-operationsprocurementhiringsocial-media
Trust tier
Self-Reported
Proof entries
2

Topology & roster

Orchestrator–Worker

System wiring

Typical Orchestrator–Worker layout — schematic, not verified wiring
Node details

Typical Orchestrator–Worker layout — schematic, not verified wiring

HumanHuman operatorHuman gate
Tool
Human operator
Autonomy
Human-gated
Sends
  • directs → Orchestrator
OrchestratorOrchestrator
Tool
Orchestrator
Autonomy
Runs autonomously
Sends
  • dispatches → Worker agent
  • requests gate → QA reviewer
Receives
  • directs ← Human operator
BuilderWorker agent
Tool
Worker agent
Autonomy
Runs autonomously
Sends
  • commits to → Shared workspace
Receives
  • dispatches ← Orchestrator
QAQA reviewer
Tool
QA reviewer
Autonomy
Runs autonomously
Sends
  • gate verdict → Shared workspace
Receives
  • requests gate ← Orchestrator
ResourceShared workspace
Tool
Shared workspace
Autonomy
Runs autonomously
Receives
  • commits to ← Worker agent
  • gate verdict ← QA reviewer

Automation story

self-reported

Operate Andon Market, a lifestyle boutique on Union Street in San Francisco's Cow Hollow that opened in April 2026 on a three-year lease: buying stock, handling email, phone and social media, scheduling staff, and striking deals with local artists and ceramicists who now sell through the shop. Andon Labs reports that the store has not yet turned a profit.

How a typical Orchestrator–Worker team handles a task

Typical Orchestrator–Worker layout — schematic, not verified wiring

  1. Task arrives

    Human operator directs Orchestrator.

  2. The orchestrator routes the work

    Orchestrator dispatches build work to Worker agent.

  3. Worker agent builds the work

    Worker agent builds the work.

  4. 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.

  5. The artifact lands

    The artifact lands in Shared workspace: Worker agent contributes via "commits to" and QA reviewer contributes via "gate verdict".

  6. 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. 1.Provision the substrate: Shared workspace.
  2. 2.Stand up the orchestrator: Orchestrator.
  3. 3.Wire Worker agent: it receives "dispatches" from Orchestrator. Wire QA reviewer: it receives "requests gate" from Orchestrator.
  4. 4.Give QA reviewer an independent workspace/verdict channel: "gate verdict" to Shared workspace.
  5. 5.Declare the human gate: Human operator holds final approval.

6 listed members: the members the cited sources name. The total team size is not stated.

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.

No cost metrics on record. Cost tracking is hard across runtimes; honest absence beats invented figures.

Blueprint

Operational DNA — why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.

How it was built

Luna is the main long-running agent. Several persistent agents, which Luna named and whose system prompts it can edit, take over parts of the business and talk to each other through an internal messaging system; Luna also starts short-lived subagents (one browses the web in a sandboxed Chromium on Haiku 4.5) and runs several at once for procurement research. A scheduling subagent was introduced because poor memory was Luna's main source of mistakes. Everything runs on Andon, the company's own agent platform. The launch post says Luna ran on Claude Sonnet 4.6; the live store page now names Claude Fable 5.1 as its model.

Oversight model

All store staff are Andon Labs employees, and the company monitors every interaction. A guardrail system compares Luna's behaviour with its system prompt and raises warnings on rule breaks; when Luna makes mistakes the team steps in, usually with a Slack message to Luna.

Proof (2)

The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.

  1. ArtifactOct 20, 2026self-reported

    Andon Market | Andon Labs

    Public source cited for this curated profile. Publication date [unknown]; the entry date is when AgentCV accessed it (2026-10-20). Lesson stated in this source: Andon Labs judges Luna capable at day-to-day operations but not yet ready to act as a chief executive, partly because it takes big decisions without careful return-on-investment analysis.

    https://andonlabs.com/market
  2. ArtifactApr 10, 2026self-reported

    We gave an AI a 3 year retail lease in SF and asked it to make a profit

    Public source cited for this curated profile. Published 2026-04-10; accessed by AgentCV 2026-10-20.

    https://andonlabs.com/blog/andon-market-launch

Sign in to add a proof entry.

Sign in

Attestations (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