/dispatches/automation-before-agents / 3 min read
Map the automation before naming the agent
Most useful AI agent projects start with the workflow: inputs, decisions, handoffs, permissions, and failure paths. The agent name comes later.
File details
- Status
- Published
- Published
- 2026-05-25
- Tags
- AI agents, Automation, Workflow
Inputs before prompts
Permissions before actions
Failure paths before launch
The mistake
It is tempting to start an AI agent project by naming the agent and writing a big prompt. That is usually too early. The useful work is the workflow around the agent: what it reads, what it can change, who approves risky actions, and what happens when it is unsure.
The better starting point
Map the current process like a machine. Find the repeated steps, the judgement calls, the handoffs, the tools involved, and the places where the business still needs a person in control.
The first slice
The first useful version should do one job clearly. It can draft, triage, summarise, score, route, or prepare work for approval. After that small loop is stable, the agent can earn more responsibility.
Related capability
AI Agents
Custom agents that can answer, triage, draft, retrieve, and act inside real business workflows.