Skip to main content
Build observable agent systems | beyond10xMove from focused Claude guidance to provider-neutral loops, controlled execution, and outside-in evaluation.build-agent-systemsexperiencebuild-agent-systemsexperiencedeveloper

Build · Experimental

Build observable agent systems

Move from focused Claude guidance to provider-neutral loops, controlled execution, and outside-in evaluation.
Audience
Developer
Expected time
About 20 minutes
Access
Public · 3 required artifacts
Finish with
Choose the smallest agent-system layer that owns the execution or evaluation need.

Adoption contract

Choose an available path without crossing an access boundary.

These are ordered alternatives, not interchangeable promises. A blocked option stays visible so evaluation access is never mistaken for deployability.
Primary path

Build observable agent systems

Available now
Support: ExperimentalDeclared access: PublicEffective access: Public

Choose the smallest agent-system layer that owns the execution or evaluation need.

Orientation time: about 20 minutes

Required artifacts

Alternative path

Build AgentIDE from source with approved dependencies

Access required
Support: PreviewDeclared access: Approval RequiredEffective access: Approval Required

Build and gate AgentIDE from its public source after obtaining the private dependency required by the generated hosted package.

Orientation time: about 30 minutes

Prerequisites

  • Rust 1.98 or newer
  • Node.js
  • Approved GitHub access to the private Service SDK dependency

Required artifacts

  • Agentide DocumentationDocumentation · Available · Public
  • Agentide SourceSource · Available · Public

    The source is public, while a complete build currently requires approved access to the private Service SDK dependency.

  • Agentide Private Build DependenciesPackage · Available · Approval Required

    A complete AgentIDE source build requires approved access to the private Service SDK dependency used by the hosted package.

Use the public binary for self-service evaluation; source visibility alone is not a complete build path.

Review access requirements

01 · Learn

Choose the layer that owns your problem

Understand the boundary and prerequisites before running commands.

02 · Do

Run and bound the loop

Follow the technical instructions in the repository that owns them.

03 · Verify

Observe the system from outside

Check an observable outcome before treating the experience as complete.
  1. Evaluate with Metaharness

    Drive or compare harnesses from outside their native loop when independent observation matters.

    Complete when

    You can compare retained outcomes without relying only on the harness's own account.

    Open this step