Agentic Workflow Construction
Make agent authors name the four parts and the freedom level before they code, so a failure points to one part instead of smearing across a vague agent.
Description
Build an agent out of four named parts before you write any loop. The four parts are the model, the tools, the data stores, and the loop prompt that ties them together. Also pick how much freedom the model gets each turn. That choice is the interaction paradigm: passive, explicit, or autonomous. Keep every part separate so you can swap one without touching the rest. The more freedom you give the model, the more safety checks the loop needs.
When to apply
Use this when you build a new agent from scratch. It fits a coding agent, a customer-service agent, a browser agent, or an internal-tools agent. Do it on day one, before you write the loop. Don't apply it when you are just wiring up a single model call with no tools or memory. That is a prompt, not an agent.
What it involves
- Pick the interaction paradigm
- Author the model component
- Author the tool component
- Author the data-store component
- Author the agent-loop prompt
- Add guardrails and verifiers
- Bind to an orchestration framework only when needed
Open the full interactive page →
Diagram, neighbourhood map, code examples, related patterns and full provenance.