Skip to main content
Start with the result your application must produce. Choose an execution shape, add its tools and context, then decide how requests arrive and how long work lives. Add evaluation and tracing while the application is still small.

​
Choose who controls the next step

These choices compose. A harness can drive a workflow; a workflow can call an Agent. Compare the approaches before adding another layer.

​
Add one capability, then verify it

​
Follow an application path

Once the execution and state choices are clear, follow one of these routes. The first example gives you a runnable starting point; the later guides add the capabilities that path needs.

​
Assistants and APIs

Build: an assistant that answers from your data, remembers a conversation, and calls application functions. Start with: @agentium/core. Add @agentium/transport for HTTP or sockets; add @agentium/eval and @agentium/observability to check quality and diagnose runs.
  1. Run the first support Agent, then add a lookup tool.
  2. Choose structured output when code consumes the response, retrieval for source evidence, and sessions for context between turns.
  3. Assert the behavior with a quality gate.
  4. Serve the owned-session API, then apply the request-serving deployment checks.

​
Harnesses and automation

Build: reusable capabilities or a controlled business process with explicit grants, budgets, and approval decisions. Start with: @agentium/core + @agentium/harness. Choose agentDriver for model-led work, workflowDriver for a known sequence, or teamDriver for coordinated specialists. Begin with the research harness or the approval workflow. Add selected file context, conversation sessions, MCP resources, or watches as the task requires.

​
Background and recoverable work

Build: scheduled analysis, asynchronous processing, or work whose status must survive a request or process.
  1. Run the producer and worker with core + @agentium/queue and inspect its terminal job result.
  2. Register the executor in each worker and choose job retention, concurrency, and scheduling.
  3. For recoverable state, add durable tasks and actions with a replay-aware driver and store. Persist an operation identity before an external effect.
  4. Rehearse interruption and reconciliation. A queue retry alone does not prevent duplicate effects.

​
Voice and phone applications

Build: a realtime voice assistant, a composed speech pipeline, or an outbound phone application. Start with: core’s voice entry point. Add core’s telephony entry point for call control and @agentium/transport when a supported gateway fits your client.
  1. Choose native realtime or streaming STT → Agent → TTS.
  2. Connect browser audio or LiveKit media.
  3. If the application dials, choose a carrier adapter and learn the call intent lifecycle.
  4. Handle voice recovery and carrier callbacks at their separate boundaries.

​
Browsers and execution workspaces

Build: an assistant that operates web interfaces or runs code in an execution workspace.
  1. Start with BrowserAgent from @agentium/browser and core, or choose a sandbox adapter for code execution.
  2. Give it a narrow task, model, credentials, and explicit environment ownership. A local subprocess does not provide OS isolation.
  3. Add selected file context when a harness needs evidence from a workspace.
  4. Inspect the result and close owned browsers, sessions, and sandboxes. Follow the browser deployment profile.

​
Device applications

Build: an Agent that observes or controls a device through @agentium/edge and core.
  1. Choose the system, GPIO, servo, sensor, camera, or BLE toolkit that fits the hardware.
  2. Configure an edge model and inspect tool results on the intended device.
  3. Add runtime monitoring and optional cloud synchronization. The host owns recovery actions and applying cloud configuration.
  4. Verify device permissions, disconnection handling, and shutdown with the device shipping profile.

​
Develop, measure, and manage

Use @agentium/cli to scaffold or watch a project. Build a quality gate with @agentium/eval and @agentium/observability before changing models or prompts. Add cost accounting and throughput limits where they affect operation. Add @agentium/admin when your application needs to create or update entity configuration through an API. Your host still owns administrator authentication, authorization, configuration persistence, and secret resolution. When the first application path works, move to Ship for deployment profiles and release checks. Use Examples for complete projects or Reference for exact contracts.