Skip to content
Sapiom Docs
Go To Dashboard

Build your first agent

Build the same hello-sapiom starter in Agent Studio, Claude Code, or Codex. Sign in to Sapiom first, ask your coding agent for a ready-to-run starter, then run both steps locally.

What the starter does

Section titled “What the starter does”

The default starter declares two steps:

start → finish

start accepts a name and passes a greeting to finish. finish completes the run with { "done": true }. Keep the starter unchanged so your result matches the verified output below.

  1. Ask for a ready-to-run starter

    Section titled “Ask for a ready-to-run starter”
    Download Agent Studio

    Open Browse templates from the welcome screen, or choose Add Workspace → Start from a template. Under Bundled starters, open Default starter, choose Use template, and select an empty destination named hello-sapiom.

    Choose Claude Code or Codex from the Coding agent menu, then select Start session. Studio gives the coding agent the starter goal and the project context it needs.

    Ask:

    Keep the default starter unchanged, get it ready to run locally, and tell me its entry step, step count, and any warnings.

    Your coding agent chooses the Sapiom project tools, reads the generated project instructions, installs dependencies when needed, and checks the agent. You do not need to invoke MCP tools or run setup or check commands yourself.

    A ready starter has entry start, two steps, and no warnings. If the coding agent finds a setup or validation problem, let it resolve the problem before continuing.

  2. Run both steps locally

    Section titled “Run both steps locally”

    In Agent Studio or your standalone coding agent, ask:

    Run this agent locally with the input { "name": "Ada" } and show me the result of each step.

    The verified result, with only the run-specific execution ID omitted, is:

    {
      "outcome": "completed",
      "output": { "done": true },
      "steps": [
        {
          "step": "start",
          "status": "succeeded",
          "output": { "greeting": "hello from Sapiom, Ada" }
        },
        {
          "step": "finish",
          "status": "succeeded",
          "output": { "done": true }
        }
      ],
      "unusedStubs": [],
      "stubWarnings": []
    }

    completed proves the local runner reached a terminal directive. The two succeeded traces prove both real step bodies ran. Empty stub lists mean no supplied local response was ignored or malformed.

What you have now

Section titled “What you have now”

You have an authenticated authoring session, a typed and checked agent project, and a genuine local execution. You have not linked the project to a hosted agent, deployed it, or called a paid capability.

Create from a template Compare the live gallery with bundled starters and materialize either one safely.
Test locally Control stubs, cover branches, and interpret the per-step evidence.
Understand agents and projects Learn how the source folder, step graph, hosted identity, and runs relate.
Deploy your agent Create a cloud build and start a production run from your authenticated project.

© 2026 Sapiom, Inc.