Intelligent workflows

Deterministic Workflow or Agent?

A practical decision framework for choosing explicit orchestration, AI assistance, agent behavior, or a controlled combination.

By Francis Bellocchio8 min readUpdated 2026-07-22

01

Autonomy is a risk decision

Agents are attractive when a task requires interpretation, tool selection, or flexible sequencing. They are a poor default when the process has stable rules, consequential side effects, strict timing, or a narrow set of valid states.

The useful question is not whether a process can use an agent. It is which decisions benefit from flexible reasoning and which must remain explicit.

02

Prefer deterministic orchestration when

A state machine or workflow engine provides stronger control when the happy path and important exceptions can be enumerated. It supports replay, testing, service-level commitments, and operational ownership.

  • Inputs and transitions are well defined.
  • The same evidence should produce the same result.
  • Actions carry financial, legal, security, or customer consequences.
  • Operators need predictable recovery and replay.

03

Use bounded intelligence inside the workflow

AI can interpret unstructured input, draft a response, rank candidates, or explain a rule while deterministic orchestration controls when tools run and which actions require approval.

This hybrid design often delivers most of the value attributed to agents with clearer evaluation and a smaller failure surface.

Decision guide

Questions to carry into the work

  1. Map states, transitions, exceptions, and side effects.
  2. Identify steps where ambiguity prevents reliable rules.
  3. Bound model inputs, outputs, tools, time, and cost.
  4. Require approval before consequential actions.
  5. Design timeout, retry, fallback, and replay behavior.

Apply this perspective

Bring the decision into your operating context.

Start an Architecture Conversation