Skip to content

ShareWell · Agent orchestration

The conductor for your repos.

Maestro is the control plane ShareWell uses to run fleets of Claude coding agents. It hands each agent a task and a git worktree, tracks the work, and performs every merge itself after a human approves. Agents never merge.

maestro@sharewell ~ %

The problem

A crowd of soloists is not an orchestra.

Parallel agents are easy to start and hard to land. What breaks is the coordination between them.

Branches everywhere

Ten agents, ten worktrees, no score. Work gets lost between terminals and half-finished branches pile up.

Review debt

Diffs arrive faster than any human can read them, so the work piles up unreviewed like inventory nobody has counted.

Bookkeeping

Who did what, on which task, merged when: someone has to write it down. Usually nobody does.

The Maestro manifesto

We built the conductor, not another console.

You can point a raw agent at a repo and hope. We would rather a person stayed in the loop: reading the diff, steering the work, and owning the call on what lands. So rather than run fleets out of Codex or the Claude console, we built Maestro around that person.

A human reads every diff.

Nothing merges on an agent’s say-so. The change is reviewed in the diff plane by a person who can veto it before it lands.

The direction is ours.

Planning, priorities and project direction stay with the operator. Agents fill in the work; they do not decide what the work is.

Steering, not vibes.

Every dispatch carries a human’s steer on how to approach the task, and any running agent can be corrected mid-flight.

Agents propose. You decide. Maestro merges.

The one rule the whole system is built to keep. The merge is deterministic, logged, and performed by Maestro, never an agent.

This is what makes it fit a company rather than a demo: accountable code, a name against every decision, and a merge history that reads as a record of human approvals.

How it works

Dispatch. Review. Merge.

01

Dispatch.

Point Maestro at the backlog. Each task gets its own agent, its own worktree and its own branch, maestro/. The orchestrator keeps eight to ten in flight.

maestro — fleet
Animated illustration of a fleet of agents working in parallel worktrees; when a human approves, Maestro performs the merge and closes the task.

02

Review.

Every finished branch arrives with a report card: a summary, a risk level and gauges for correctness, clarity and coverage. Chat with the agent that wrote it, or go deeper with /code-review.

report card — maestro/violin-2
AI scorecard · claude
low risk

Adds the distribution statement CSV export behind the existing report permissions. Reuses the statement query; new code is covered by four unit tests. No schema changes.

14 files +412 −87
  • Reuses the existing statement query — no new N+1
  • Four unit tests cover the export path
  • No migration: the export reads existing columns
84 overall
Correct
92
Clarity
88
Tests
74
Risk
18
An AI-generated report card grading an agent's branch on correctness, clarity, test coverage and risk.

03

Merge.

One button. Maestro checks mergeability in memory, merges --no-ff into main, cleans the worktree, archives the branch, closes the task. Deterministic, every time.

triage — maestro/violin-2
Animated illustration of Maestro's human-gated merge: mergeability is checked in memory, a human approves, and Maestro performs the merge and closes the task.

Maestro Tasks

The tracker stays true without anyone touching it.

Dispatch, attribution, comments and closure happen automatically. Bots are first-class actors, so the history is honest.

app — tasks
A task board where AI bot actors are assigned tasks alongside humans.

Maestro Orchestrator

Watch the whole fleet from one seat.

Live lanes for every agent: in flight, needs review, human review. When you approve, Maestro performs the merge and writes the log line.

Explore Maestro Orchestrator →
maestro — fleet
Animated illustration of a fleet of agents working in parallel worktrees; when a human approves, Maestro performs the merge and closes the task.

Governance

Autonomy you can hand to an auditor.

Pre-merge gates an agent cannot skip, a tool-policy ceiling admins set, a multi-approver queue, and an append-only trail behind every merge. Enforced in the server, not the UI.

See the governance layer →
maestro — /audit
An audit trail listing each governed action in order: a dispatch, the agent's tool calls, a policy-denied git push, a passing gate run, a reviewer's approval, and the merge.

Case study

How ShareWell uses Maestro.

~35

repos in one tree

8–10

agents in flight

0

merges by an agent

FAQ

Questions, answered plainly.

▪ shipping deterministic orchestration

Take the podium.