Build a Grok Bot-style chat app

What you’re building: a chat app where each conversation is more than messages: the agent has a workspace it can use between turns.

Primitives you’ll use: Organization, Sandboxes, Agents, Postgres, Deployments, Custom domains

What you’re building

Most chat apps only talk. The interesting version gives the agent a workspace: a place to keep files, run code, and do work between messages, so the conversation produces real results and not just text.

On MIOSA, a conversation can own a sandbox. The chat turn sends a prompt to the agent against that workspace, streams the events back as a reply, and persists messages in a managed database. Named agents (each with its own instructions and harness) give you the “team of assistants” feel.

Keep the history in Postgres and the workspace in a sandbox; the two together give you continuity across turns and sessions.

What you need on MIOSA

Architecture

Step 1: Create an account and an API key

Install the CLI, sign in, and mint a key for your product. The secret is printed once; store it as an environment variable, never in code.

npm i -g @miosa/cli
miosa login
miosa whoami
miosa api-key create chat-app-key --preset agent     # prints the secret once
export MIOSA_API_KEY="msk_u_..."

Both SDKs read MIOSA_API_KEY from the environment, so a server or a worker needs nothing else. See API keys for scopes and how to create keys in the console.

Step 2: Create the resources

Define a named agent once, then run it per conversation:

miosa agent new assistant --harness claude-code --model sonnet --instructions-file assistant.md

Step 3: Wire the agent loop

The workspace keeps whatever the agent wrote, so the next message can build on it.

Step 4: Preview

A Preview is a throwaway public URL for a port inside the machine. Start the app as a background process so it survives the CLI disconnecting, then expose its port.

Open the exact Preview URL MIOSA returns.

Step 5: Deploy

Publish the machine to an immutable Deployment. Give it the source machine, the path the app lives at inside it, and the command that serves it.

Publishing the same deployment name again creates a new immutable version and keeps the same URL. Roll back with miosa deploy rollback chat-app --to <version-id>, and inspect a live app with miosa deploy logs chat-app -n 100. See Publishing and Rollback.

Step 6: Custom domain

Attach a domain your customer owns to the deployment. The platform URL keeps working while DNS propagates.

miosa deploy domain-add chat-app app.example.com
miosa deploy domains chat-app          # shows the DNS record and verification target
miosa deploy domain-verify chat-app <domain-id>

Copy the exact DNS record MIOSA shows into the customer’s DNS provider; for a subdomain it is normally a CNAME. Once verified and TLS is active, MIOSA routes the domain to the deployment’s active version. In code, read the URL from the publish response instead of building it: the SDK method is miosa.deployments.domains.add(deploymentId, { domain }) (TypeScript) or miosa.deployments.domains(deployment_id).add(domain=...) (Python). See Domains.

Costs and limits

Everything bills while it runs: machines (sandboxes and computers) by the second, managed databases while running, and deployments when they serve. Pausing a machine stops compute billing but keeps disk. Set an --idle-timeout or a --ttl so a forgotten machine cannot run forever, and cap spend with rate limits and per-workspace quotas.

• Pricing - plans, the published rate card, and the free Developer grant.
• Sizing and limits - machine sizes and what each costs to run.
• Timeouts and auto-stop - --ttl, --idle-timeout, and pause/resume.

Next steps