Workflow Control
How do I pause a running workflow?
Click the stop button or pressEsc. The workflow stops with state preserved. Send a new message or click resume to continue.
Can I change parameters while running?
Yes. Open parameters panel (gear icon), change values. Changes take effect on the next iteration. Common updates: switching to manual mode or changing the model.What happens when a workflow fails?
Reliant pauses instead of crashing. Fix the issue (permissions, network, etc.) and click resume to retry.Threads and Branching
How do I branch a conversation?
Click the branch icon on any message. A new chat is created with history up to that point.Can I switch workflows after branching?
Only before sending the first message. After that, the workflow is locked.How do I message a specific sub-agent thread?
Pause the workflow, select the target thread from the selector, then send your message.What’s inherit vs new vs fork?
Thread modes control how sub-agents share conversation context. See Threads for a full explanation with examples.Workflows and Presets
What’s the difference between workflow and preset?
- Workflow = execution pattern (what steps, what order)
- Preset = parameter values (model, temperature, prompt)
Why can’t I change workflows mid-conversation?
Workflows define structure. Changing mid-run would break execution. Branch from earlier and select a new workflow before sending.Response Tools
What are response tools?
Synthetic tools that force structured output from the model. You describe the output with a JSONschema:
choice and an explanatory value, which later edges can branch on. See Workflow Patterns for a full example.
When should I use them?
When you need to branch on structured data—code review pass/fail, classification, validation results.Account, Billing and Machines
Do I need an account?
Yes. Reliant is a cloud service: you sign in to use the web or desktop app, and your chats, projects and settings live in your account. See Key Concepts for how the pieces fit.What does Reliant cost?
There are two separate things you might pay for, and you only pay for the ones you use. Cloud machines are a monthly subscription: Compute Small, Medium, Large, XL and 2XL cost $15, $35, $79, $159 and $299 per month. Reliant AI is pay as you go from a wallet: usage is billed at the provider’s price, and wallet top-ups include a 5% service fee. If you run agents on your own computer with your own API key or provider login, you pay Reliant nothing for those parts and the provider directly for the model. Your current plan and usage are in Settings → Billing.Where do my agents run?
On a machine you choose: your own computer, another computer you own, or a Reliant cloud machine. The daemon on that machine reads files and runs commands for the agent, so your code stays there. See Machines.What happens to a cloud machine when I’m not using it?
It suspends after a period of inactivity, which you can change in Settings → Machines, and wakes up automatically when you send your next message. A suspended machine isn’t billed for compute, but its disk is. Delete the machine to stop all charges for it.Can I use my own API key or my Claude, ChatGPT or Copilot subscription?
Yes. Connect them in Settings → AI. See AI Providers.Can I use a local model?
Yes, through a daemon on the computer that runs the model server. The prompt and reply still pass through Reliant’s servers. See AI Providers.How do I delete my account?
Settings → Account → Delete account. The confirmation screen shows what will be deleted and what will be refunded. See Privacy & Security.Data and Privacy
Where is my data stored?
Reliant is a cloud service. Your chats, messages, tool calls and tool outputs (which often contain code), attachments, memories, workflow runs and project metadata are stored in our Postgres database on Google Cloud (us-central1). Model API keys and provider logins are stored encrypted. Your repository itself stays wherever your tools daemon runs: your machine, another machine you own, or a managed cloud machine. Local config lives in~/.reliant/config.yaml.
Are conversations sent to Reliant?
Yes. Our servers run the agent loop and make the model calls, so your prompts, whatever the agent reads, and whatever commands print are sent to our servers, stored with your chat, and sent to your model provider. We don’t train on customer content. See Privacy & Security for the full picture, including telemetry (on by default; opt out in Settings → Privacy), retention, and how to delete your chats and account.More help: Troubleshooting • Feedback