The AI teammate that follows your rules
Tag @Duet in Slack. It works on your code in its own sandbox and opens draft pull requests, and every model call runs through your org's policies and guardrails.
Ask in a thread. Get a draft pull request.
Anyone on your team tags @Duet. It does the work in its own sandbox and replies in the same thread.
- 1Tag @Duet in a thread. It reads the thread and replies there, with files.
- 2It clones your repos, runs the tests, and opens pull requests, always as drafts.
- 3A failed CI check, or a reviewer who mentions @Duet on its pull request, starts a new task in the same thread.
- 4It picks a thread up days later where it left off, and keeps your team's notes in Slack canvases.
- 5Save a thread as a team skill with one click, and Duet reuses it.
Most AI teammates come with their own rules. Duet follows yours.
Its limits are fixed rules outside the agent: the same answer every time, whatever a prompt says.
Only the repos you grant
Duet pushes only to its own branches, in the repos you grant, and opens its pull requests as drafts. It can't merge, and it can't change your CI workflow files.
Never your keys
GitHub tokens and model keys are added on the way out, never inside its sandbox. The sandbox holds only a short-lived key that reaches Cloptima and nothing else.
Your guardrails on every call
Secrets and personal data are masked before a model sees them, and prompt attacks in what Duet reads are caught, with guardrails from Azure, Google, AWS, your own webhook, or your own rules.
Hard limits, set by your org
A push to main is refused before any access is granted. The models Duet may use, its spend limits, and an off switch are yours to set.
Every hop, checked outside the agent
Three short films follow Duet's work hop by hop, for the engineers who review it.
Which repos can it push to?
One push, from the sandbox to GitHub. Every push is checked before it leaves, and GitHub access lasts one hour, for one repo, added on the way out.
Whose keys does it hold?
Each task runs in its own isolated sandbox with a closed network: read-only web, package mirrors, and GitHub. When the work is done, the sandbox and its access are gone.
What does the model get to see?
Every model call follows your rules: the models you allow, limits that stop runaway loops, masked secrets and personal data, and spend checked first. Each call is recorded with its cost.
The same policies and guardrails as all your AI
Duet's model calls run through Cloptima, like the rest of your AI traffic, so your admins see and control it in one place.
- Choose the model: Claude, GPT, or Gemini, with your own API keys or Cloptima credits.
- Set spend limits: daily and monthly hard limits, chosen by your admins.
- See every task: each step is logged with its model, tools, and cost.
- Turn it off: the next request is refused at once.
Duet is in early access on the AI Growth, Platform Growth, and Enterprise plans.
- Duet will investigate cloud costs, logs, resources, and Kubernetes, read-only first, under a role you grant.
- Duet will work in Jira, Linear, Notion, Google Drive, and your own MCP servers.
- Duet will run inside your own cloud, so its sandbox, credentials, and model calls stay in your network.
Questions security leads ask
Get early access to Cloptima Duet
Duet is in early access on the AI Growth, Platform Growth, and Enterprise plans.