The 4 paths
Four ways to build an agent.
Not a ranking — different tools for different jobs. The decision that matters most is the first one: which path do you start on, and why? Compare them by where ownership sits.
Not sure which? Take the fitting| path | builds | runs | decides |
|---|---|---|---|
| 01Build it yourself | You | You | You |
| 02Build it with a coding agent | A coding agent | You | You |
| 03Deploy an open-source agent | The community | You | Shared |
| 04Use a managed service | The vendor | The vendor | Shared |
Build it yourself
Code-first. You own the full stack.
Write the agent yourself: model calls, tool wiring, memory, the orchestration loop, deployment, monitoring. Frameworks give you blocks; the architecture is yours.
explore patternBuild it with a coding agent
You decide the architecture. The agent writes the code.
Agentic engineering, not vibe coding. You make the architectural calls before the agent touches the keyboard; Claude Code or Cursor handles implementation. You review the decisions, not just whether it compiles.
explore patternDeploy an open-source agent
It already exists. Clone, configure, run.
The OSS agent space has matured. When something already does 80% of what you need, deploying it on your own infrastructure beats rebuilding it. The question is no longer "does it exist?" but "which one is worth deploying, and why?"
explore patternUse a managed service
Someone else runs the harness. You configure via API.
The path to watch most closely in 2026. Session persistence, the execution environment, retry logic — these are rarely your competitive advantage. A managed service wires them so you can spend engineering time on what makes your agent actually better.
explore pattern//Paths combine. A team on a managed service may still do agentic engineering on top; a project that started with open source may fork until it’s effectively build-it-yourself.