How to Pick a Harness
Start at the lowest layer that solves the problem. A new framework, runtime, and orchestrator introduced together create three independent failure surfaces before the team has measured one.
- Job: What must the agent do: generate an answer, edit a repository, run commands, or coordinate several workers?
- Adoption surface: Can the team support a CLI, IDE extension, local service, container, or managed cloud environment?
- Autonomy: Which actions need approval, and what can run without a person present?
- Recovery: What must survive a failed command, process restart, exhausted context window, or interrupted network call?
- Usage and cost: Is the workload interactive, bursty, continuous, or parallel? Compare accepted-task cost, not token price alone.
- Exit: Can prompts, repository instructions, state, tools, and audit data move to another runtime?
Feature count and GitHub popularity cannot answer those questions for a specific codebase.