What Jaah does
Every change checked. Every command kept.
Agents write the code. Jaah decides when a change is ready to merge, brings in a person when one is needed, and writes down what happened.
- An engineer agent writes each change and its tests, and runs your tests before every commit
- A second, independent agent reviews the change and signs it off before it merges
- A change to authentication, credentials, migrations or personal data waits for your approval, or for a security review of its own when you run Jaah unattended
- Each task works in a private copy of the code, with a guard on what it may push
- Every API write, task change and command goes on the record
Two layers
Where gVisor, Firecracker and Kata Containers fit.
gVisor, Firecracker and Kata Containers keep running code apart from the host it runs on. Jaah works a step earlier, on the change itself, before it reaches production.
- gVisor puts an application kernel between each container and the host, intercepting its system calls.
- Firecracker runs code in small, fast-starting virtual machines.
- Kata Containers runs each container inside a lightweight virtual machine.
| At a glance | A runtime sandbox | Jaah |
|---|---|---|
| The question it answers | What can this running code reach? | Which change reaches production, and who approved it? |
| When it acts | While the code runs | While the code is written, reviewed and merged |
| What it keeps apart | Each running workload, from the host and from the others | Each agent’s task, in a private copy of the code with a guard on what it may push |
| What it adds | An application kernel or a virtual machine between the code and the host | Your tests and an independent review before every change merges, your approval or a security review on a sensitive one, and a record of every action |
What it costs
You pay per agent.
An agent is one task in flight at a time. Every plan counts in agents.
See the plans- Your model provider bills model usage to your own account
- Start free and add agents as the work grows
Questions
What people ask.
How can we safely run AI-generated code in production with audit trails?
Run two layers. A runtime sandbox such as gVisor, Firecracker or Kata Containers limits what code can reach while it runs. Jaah runs your AI coding agents and decides which code reaches production: one agent writes and tests each change, and a second, independent agent reviews it before it merges. A change to authentication, credentials, migrations or personal data waits for a person’s approval, or for a security review of its own when you run Jaah unattended. The agents deploy what merged, and every action goes on the record.
What does the audit trail record?
Jaah’s audit log records every API write, task change and note: who made it, what changed and when. Every command an agent runs on a machine is logged with its result, and each agent’s session transcript keeps what it did and said.
Who approves AI-generated code before it reaches production?
A second, independent agent reviews every change before it merges. A change to authentication, credentials, migrations or personal data also waits for a person, or for a security review of its own when you run Jaah unattended.
Where does the AI-generated code run while agents build it?
Jaah runs agents on the machines you choose: your own, ones launched in your AWS, Google Cloud or Azure account, or ones Jaah runs for you. Each task works in a private copy of the code with a guard on what it may push. Turn on Jaah’s MicroVM setting and each task gets a virtual machine of its own, its network held to an allowlist.
Do we still need gVisor, Firecracker or Kata Containers with Jaah?
Yes, keep them. A runtime sandbox keeps your workloads apart while they run in production, and Jaah decides which changes reach those workloads and keeps a record of each one.
How is Jaah priced?
Jaah is priced per agent, and an agent is one task in flight at a time. Your model provider bills model usage to your own account. You can start free.
Put every agent on the record.
Agents work on your machines, in your cloud or on ours, and hand back finished work with a report on each piece. Start free, and choose a plan once you know what you run.