AOSplaneFAQFAQ
Frequently asked questions
Short answers from the rest of the site: what AOSplane runs, what it will not do on its own, and how a ticket becomes a pull request you merge.
- Hard spend cap per task
- Linear and Jira
- Claude Code and Codex
5 sections · 3 min read
On this page5 sections
Common questions
Is AOSplane another coding agent?
No. AOSplane runs the coding agents you already use, like Claude Code and Codex, in the cloud. It adds what a team needs around them: a private sandbox for every task, spending limits, approvals for sensitive steps, and a record of everything they did.
We already use Claude Code. Why add AOSplane?
AOSplane runs Claude Code, so you keep the agent you like. It adds what a team needs around it: a spec with acceptance criteria you approve before work starts, QA that checks each one before you see the pull request, spending limits checked before a task starts, approvals for sensitive steps, and one record of every step. It does the same for Codex, so a team that uses both runs them one way, on its own accounts.
Which agent does the work?
You choose. When you set up an agent, you pick which coding agent it runs and which model it uses. Matching each task to the best agent automatically is something we are still building.
What happens when a budget runs out?
A new task doesn’t start if its cost would go over any of your limits: the company’s, the project’s or the agent’s. Tasks that are already running are not cancelled by that limit.
Can I use my own AI subscriptions and keys?
Yes. Connect an Anthropic or OpenAI API key, Amazon Bedrock with an AWS role or a bearer token, Claude Platform on AWS, Azure OpenAI, another compatible provider, or a Claude or ChatGPT subscription you already pay for (sign-in for subscriptions is still rolling out). Agents use the account directly, so the provider bills you and its limits apply, with no markup. AOSplane bills separately for platform usage.
How do I stay in control of risky actions?
An agent can stop and ask for permission before a sensitive step. You see what it wants to do, then approve or deny it. Your answer is saved in the task’s history.
Can an agent change my code without me?
No. Every task runs in its own isolated sandbox, and agents can’t push to your repositories. Their changes come back as a pull request for you to review.
Tickets and pull requests
Can I start from a Linear or Jira ticket?
Yes. Start a session from a Linear issue or a Jira Cloud issue, or hand the issue to the AOSplane agent inside Linear. You can also start from the console, or from CI with a project API key. Slack is rolling out: mention @AOSplane or use /aos. The change comes back as a pull request on GitHub.
What has to happen before a pull request opens?
With Plan first, the product manager writes a spec with acceptance criteria, each with a check, and you approve it before any code. Your agent then builds in a private sandbox. Review reads the change, and QA runs the repository’s checks and one command per acceptance criterion. A draft pull request opens once they pass. You decide what gets merged.
Plans, Claude Code and Codex
What does the free plan include?
The Free plan is self-serve: 2 projects, 2 tasks at a time per project, small machines, 7 days of history and a $5 monthly usage credit. Brief and Spec from the product manager are included. Paid plans start with a short call.
How do Claude Code and Codex differ on AOSplane?
You pick the harness and the model for each agent. Claude Code runs on your Anthropic account and reads a CLAUDE.md in the repository. Codex runs on your OpenAI account and reads an AGENTS.md. Both get the same sandbox, the same budgets and the same approval gates. A team can use both on one task, one role each. Matching a task to an agent automatically is still being built.
Conductor Cloud
Is AOSplane a Conductor Cloud alternative?
Conductor’s announcement of 4 November 2026 says Conductor Cloud goes read-only on 13 November 2026 and shuts down on 20 November 2026, when deletion of Cloud user data begins. AOSplane is a separate product. It runs Claude Code and Codex in the cloud on your own accounts, and it does not import Conductor workspaces or chats.
Where to read next
- From a Linear issue to a reviewed pull request
- From a Jira ticket to a reviewed pull request
- Review and QA before your team sees the pull request
- How to set a spend limit on Claude Code agents
- From a Linear or Jira ticket to a pull request
- Claude Code vs Codex on AOSplane
- Run Claude Code agents in the cloud
- Conductor Cloud alternative
- Cloud agents, explained
- Pricing on the home page