Case Study: Building Grove with ​Grove

How a small team used Grove to build Grove.

By N-Tree Studios.

Summary

We ran Grove's own development on its core features, and they kept the agents on track.

Work was queued in the evening, agents ran it overnight, and each morning started with executive summaries to review and merge.

An executive summary is the morning report of what each agent did and what needs a decision.

Also built with Grove

  • Website
  • Account platform
  • Marketing assets
  • Infrastructure code

The problem

Every agent session needed someone watching it:

  • Making sure agents weren't running their own made-up versions of our commands
  • Hearing a task was done when it wasn't
  • Checking every result by hand before trusting it
  • Stopping other work to answer a question or unstick a session

The project

Repositories

Multiple, with the main app the largest

Codebase

Close to a million lines

At the start of the project we were a team of two, later three, and keeping agents on track was a frustrating process.

The setup

We used four core parts of Grove. Each replaced a manual step:

Runners

A runner is a named command that Grove runs for the agent.

Replaced

Validating which command an agent ran

How

Builds and tests ran as named runners, so agents ran the same commands we did.

Boundaries

A boundary is a rule about what the agent may do.

Replaced

Course correcting agents

How

A denied call told the agent what to do instead.

Playbooks

A playbook bundles the tools, skills and rules a session starts with. Sessions in the same project can use different playbooks.

Replaced

Setting up every session by hand

How

Each session began with its services running and its environment and runners ready.

Task lists

A task list sets the evidence a task needs before it can close.

Replaced

Taking the agent's word for it

How

A task stayed open until the agent attached evidence that it worked.

Boundaries blocked agents from running commands we wanted to control through runners and task validations. Each denial pointed the agent to Grove's built-in tool instead.

Grove gate decisions table, the last six decisions newest first. Columns are when, tool, session and decision. Five calls are allowed and one Bash call is blocked.

The log shows five allowed calls and one blocked Bash call.

Task lists

We built six reusable task lists, one for each kind of work.

bug-fix Fixing a bug in the backend or CLI
ui-bug-fix Fixing a bug in the app's interface
chore Maintenance, cleanup, dependency updates
ui-chore Interface cleanup and polish
feature New backend or CLI functionality
ui-feature New interface functionality

Each session started with the right list attached, so the agent knew what it had to show before a task could close.

A proof is evidence the agent attaches to a task, such as a screenshot or command output.

Grove task list with proof requirements. The tasks Product page: add bag photo and cupping notes and Cart: order summary with promo code each show Proof required: 2 of 2 expectations unmet. Product page needs a screenshot or image and command output. Cart needs a screenshot or image and a recording.

Each task lists the proofs it still needs.

The loop

Daily loop in six steps: queue the work in the evening, agents run overnight under your boundaries, review executive summaries in the morning, merge what passed review, cut a release, QA with agents against the new release, then repeat. The daily loop in six steps, top to bottom: queue the work in the evening, agents run overnight under your boundaries, review in the morning with executive summaries, merge what passed review, cut a release as a new build, and QA with agents against the new release. The loop then repeats.

The daily loop, six steps

The only step that needed a person was the morning review. Each task came back with its evidence attached, and when something needed cleaning up, we left feedback directly on the running app in the preview browser.

Grove executive summary for the session Roastery checkout polish. The status bar reads All 4 tasks done, 9 proofs, 0 checks. Task 1, Product page: add bag photo and cupping notes, is completed, with its image evidence listed below.

The summary counts 4 finished tasks and 9 proofs.

Results

From June to November 2026, agents closed about 1,700 tasks a month, and about 95% passed review the first time.

Tasks closed

1,700 a month

Across 215 sessions a month

Releases tagged

54 a month

Largest overnight queue

30 sessions

Review time each morning

30 minutes to a couple of hours

Sessions and review

Sessions run overnight

90%

Passed review the first time

95%

Share of tasks closed, by kind of work

Features

66%

Bug fixes

23%

Chores

11%

A task counts as closed once the agent attaches the required evidence and the checks pass. It counts as passing review when it merges without going back to the agent.

Every task list made the agent run the project's tests before a task could close.