THE SHORT ANSWER
Traditional automation follows IF X → DO Y. Agentic automation can follow GOAL → INTERPRET → DECIDE → ACT → CHECK, selecting among permitted actions as observations change. Keep calculations, eligibility rules, approvals and other exact controls deterministic whenever possible.
Add interpretation without surrendering structure
| Dimension | Traditional automation | Agentic automation |
|---|---|---|
| Instruction | IF X → DO Y | Pursue a bounded goal |
| Path | Predefined | Chosen from allowed actions as evidence changes |
| Input | Expected fields and events | Can interpret variable language and documents |
| Failure | Known exception branches | May encounter unplanned states and need escalation |
| Testing | Paths and rules | Paths, decisions, tools, outcomes and limits |
Evidence & context: Anthropic
Keep deterministic work deterministic
Use code for exact calculations, access rules, required fields, transaction limits and final policy enforcement. A model can interpret an email's intent; code can verify the account and allowed action. A model can draft a response; a separate gate can require approval before sending.
The strongest automation often mixes methods. Flexibility belongs at uncertain interfaces, while stable controls remain explicit and testable.
Illustrative example: campaign intake
A fixed form starts the process. A model interprets an incomplete brief and identifies missing decisions. The workflow retrieves approved brand guidance, drafts options and checks required fields. Budget changes and publication stay deterministic and approval-gated. Results return to measurement rather than triggering unlimited self-adjustment.
This connects to AI Marketing Automation, where the business objective and governance remain more important than the label applied to the mechanism.
Increase adaptability one decision at a time
- Map the current deterministic process and exceptions.
- Identify one variable decision that constrains useful automation.
- Give the model a small allowed action set.
- Verify results and preserve a human escalation path.
- Measure accepted outcomes, cost and failure by category.
- Widen scope only when the evidence supports it.
Evidence & context: NIST
Sources & further reading
- Building effective agents
Anthropic. A provider's engineering taxonomy of agents and workflows, not a universal industry definition. We use the conceptual distinction, not its changing product recommendations.
- Function calling
OpenAI Developers. Official documentation for model-selected function calls. The application, not the model, executes custom functions and must validate arguments, permissions and results.
- Generative Artificial Intelligence Profile (NIST AI 600-1)
NIST. Risk-management guidance, including confabulation. It does not establish a universal error rate.
Examples and exercises are illustrative unless attributed to a source. No independent expert review is claimed.
A correction, a counterexample or an experience worth sharing?
Join the conversation ↗