Pipelines Docs is in beta — content is actively being added.
AgentsEnd-to-End Workflows

Agent Types and Path Selection

Understand the runtime modes, then lock the path before configuration work.

Core runtime modes

ModeWhere it runsTypical fit
External HTTPYour infrastructureExisting hosted agents and custom runtime control
Code (sandbox)Pipelines sandboxAgents you want Pipelines to execute directly

Sandbox execution paths

PathWhat runsTypical fit
Python functionPython entrypoint called by the platformFramework agents and proxy-first tools
Shell commandCommand executed in a seeded workspaceCoding CLIs (Claude Code, Codex, Cursor, Aider)

Patterns layered on top

  • Multi-turn: session-based evaluation across turns, not a separate mode.
  • Multi-agent: topology + attribution, not a separate mode.
  • Browser automation: a capability pattern layered onto either runtime mode.

Choosing your path

Lock the path below before opening any setup form.

Step 1: Choose runtime ownership

  • External HTTP: keep execution on your infrastructure.
  • Sandbox code: run execution in Pipelines-managed sandboxes.

Step-by-step guides:

Step 2: Choose execution style

If you picked sandbox code:

  • Python entrypoint: framework-based agent code + proxy tool calls.
  • Shell command: coding CLI workflows in seeded workspaces.

Step-by-step guides:

Step 3: Layer testing patterns

  • Add multi-turn when conversational memory and behavior matter.
  • Add multi-agent when delegation and handoff quality matter.

Step-by-step guides:

Step 4: Plan observability

Pick where your team will debug failures and validate quality: