Workflow-driven AI operator

Run AI work where your tools, access, and context already live

Autopilot runs work on the right machine, sends back a reviewable result, and waits for a human to decide what happens next. Code, research, content, ops — same loop.

Works with your existing Claude, Codex, or OpenCode subscription. No new AI vendor — Autopilot reuses the tools you already pay for.

CLI-firstRepo-nativeDurable previewsApproval-awareBring your own subscription
Proof loop

Task in, reviewable result out.

No transcript archaeology.

01
Task becomes workflow state
Runs, artifacts, and previews stay durable — not trapped in a session.
02
Worker executes on the right machine
The host already has the repo, the toolchain, and the credentials.
03
Human decides what ships
Approve the result, or reply with feedback for another pass.
01

The loop is the product

Work moves through a controlled, inspectable loop — not a conversation you have to scroll back through.

01

Start with a task

Create work from the CLI. Intake attaches the right workflow — no ad hoc prompt choreography.

02

Workflow decides the next step

Repo-authored policy picks the agent, the instructions, and what runs next.

03

Worker executes where access exists

The right worker claims the run on a host that already has the repo, toolchain, and credentials.

04

Result comes back reviewable

The run finishes with a summary, artifacts, and a durable preview URL — available after the worker is gone.

05

Human decides what moves forward

Approve to continue, or reply with feedback that becomes the next implementation pass.

02

Who this is for

Any team whose work needs real machine access, reviewable outputs, and human approval — from engineering to marketing to ops.

01

Small engineering teams

Multiple repos, client environments, limited bandwidth. You need durable runs and review loops, not more prompt wrangling.

02

Machine-bound access

The work depends on a VPN, staging host, local toolchain, or private network. Where execution happens matters.

03

Review before merge or deploy

Risky work needs a human gate. Autopilot stops, surfaces the result, and waits for an explicit decision.

04

Teams producing recurring research or reports

Weekly summaries, competitor briefs, docs audits — through a controlled loop with durable outputs, not one-off prompts.

03

Why workflow-first beats chat-first

A conversation is the wrong primitive for routing, policy, previews, and approvals.

01

A transcript is not a control plane

Task state, run history, event logs, artifacts, and human decisions need to survive beyond the current session.

02

Execution surface matters

When work depends on the repo, the toolchain, local credentials, or a private network, you can't abstract the machine away.

03

Policy belongs in the repo

Workflows and execution rules live in `.autopilot/`, next to the code — diffable, reviewable, changeable like any other config.

04

Review needs real surfaces

A durable preview URL and explicit approve/reject/reply actions are stronger than asking someone to scroll through generated text.

04

What you can run today

No Worker App needed. The CLI and API already expose the full operator loop.

Implement a feature end-to-end: spec, plan, code, review, deploy.
Respond to an incident: triage, investigate, hotfix, deploy, verify.
Monitor competitors: scrape changelogs, analyze changes, produce a brief.
Draft and publish a blog post with human review and CMS webhook.
Draft and publish social posts with human review via provider handlers.
Generate a weekly executive report and deliver via Slack.
05

The same loop, beyond code

The operator loop is domain-agnostic. The same primitives that implement a feature also produce a research brief or publish a blog post.

01

Engineering

"Implement dark mode" → plan → code → preview → approve → deploy

02

Research

"Monitor competitor pricing" → scrape → analyze → brief → human review

03

Content

"Write launch blog post" → research → draft → preview → approve → publish via API

Run the loop on a real repo

Create a task. Inspect the run. Open the preview. Decide what ships.

$bun add -g @questpie/autopilot