Buying · 9 min read · Sep 16, 2026

Three products. One question tells them apart.

These three get compared as if they were competing purchases. They are not — they are three different amounts of autonomy, and picking the wrong amount is the most common and most expensive mistake in this category. One question separates them cleanly, and it is not a question about the technology.

The question: who decides the next step?

That is the whole taxonomy. A chatbot answers, and a human decides what to do about it. Workflow automation acts, but only along a path you drew in advance. An AI agent chooses the path itself, at runtime, from the data in front of it.

Everything else — which model, which vendor, which integration count — is downstream of that. Get the autonomy level wrong and no amount of model quality rescues it: too little and the exceptions pile up on a human; too much and you have a nondeterministic system where a flowchart would have done, costing more and failing in ways that are harder to reproduce.

Three levels of autonomy distinguished by who decides the next step: a chatbot answers and a human acts, workflow automation follows a predefined path, and an AI agent selects its own path at runtime.
Not three products competing. Three amounts of autonomy, priced accordingly.

Side by side

ChatbotWorkflow automationAI agent
Decides the next stepA humanYou, in advanceThe model, at runtime
BehaviourReactive — waits to be askedIdentical every runVaries with the input
ReproduciblePer conversationYesNot reliably
DebuggingRead the transcriptRead the flowRead the trace, then guess
Cost driverConversationsExecutionsTokens per loop
Measured byResolution, satisfactionThroughput, error rateTask completion, cost

The reproducibility row is the one that decides operability. A workflow that failed can be replayed and understood; an agent that failed produces a trace that has to be interpreted, and interpreting it is a skill your team may not have on staff.

The screening test

A usefully blunt rule circulates in this literature: if it is the same inputs, same steps, same outputs every time, with no judgement required, it is workflow automation — build it in a deterministic tool and stop. If even roughly a fifth of cases need a different response, you are into conversational or agentic territory.

Buy the least autonomy that solves the problem. Cost and failure risk both climb with autonomy, and neither climbs gently.

That principle is not ours and is not new, but it is worth noticing who states it and who does not. Most of the material defining this category is published by vendors selling one of the three — Lindy, Slack and Glean all publish versions of it. The most trustworthy guidance in the category is consistently the guidance arguing against buying the expensive tier — so weight it accordingly, including here.

They are layers, not rivals

The framing as a three-way choice is itself the error. In every system we have shipped, all three are present and the value sits in the handoffs: the conversational surface captures a request, deterministic orchestration moves it through the systems of record, and the model does judgement work on the narrow part that genuinely needs judgement.

Which means the interesting engineering is not "which one" but "where are the seams". A clean handoff has a schema, a validation step, and a defined behaviour when validation fails. A dirty one passes free text between components and degrades silently — and that failure mode looks identical to a bad model, which is why it gets misdiagnosed for months.

A system built on this split: deterministic routing and state, model judgement only where the path cannot be known in advance. Sixty seconds, no sound.

Where each one earns its cost

  • Chatbot. When the bottleneck is that people cannot find or phrase things, and a human is going to act on the answer anyway. Cheapest to run, cheapest to be wrong.
  • Workflow automation. When the process is stable enough to draw. Cheaper, faster and far easier to debug than the alternatives — and it stays correct while nobody is watching it.
  • AI agent. When the sequence of steps genuinely cannot be known in advance. This is a narrower set of cases than the marketing suggests, and it is where the token bill lives.

The sequencing that works: deterministic orchestration first, conversational surface where it helps, agentic decision-making reserved for the specific step that needs it. Reversing that order — starting with an agent because agents are what is being sold — produces a system that is expensive to run and impossible to explain to an auditor.

The question to ask a vendor

Ask which of the three they are selling, and then ask what happens on the case it gets wrong. Those two answers together tell you more than any feature list, and a vendor who will not separate the three is usually charging agent prices for a flowchart. We wrote the longer version of that argument in what an AI solution actually is.

Dealing with this in your own group?

We answer scoping questions before there's a contract in sight — including the ones about cost and data handling.

Questions

Short answers,
in full.

The questions this article gets asked most, answered so each one stands on its own.

Talk to us
What is the difference between an AI agent and a chatbot?

Who decides the next step. A chatbot answers a question and a human decides what to do about it — it is reactive and its job ends when the conversation does. An AI agent selects its own course of action at runtime from the data in front of it and then executes it, which makes it more capable, more expensive per task, and considerably harder to reproduce when it goes wrong.

When should I use workflow automation instead of an AI agent?

Whenever the process is stable enough to draw as a flowchart. Workflow automation runs identically every time, which makes it cheaper, faster and far easier to debug. A usable screening test: same inputs, same steps, same outputs with no judgement required means deterministic automation. If roughly a fifth or more of cases need a genuinely different response, you are into agent territory.

Are AI agents, chatbots and workflow automation competing products?

No — they are three amounts of autonomy and most working systems contain all three. The conversational surface captures a request, deterministic orchestration moves it through the systems of record, and the model handles judgement on the narrow part that needs it. The engineering that matters is the handoffs between them, which need a schema, validation, and defined behaviour on failure.

Why is choosing the wrong autonomy level expensive?

Both cost and failure risk climb with autonomy. Too little and exceptions pile up on a person, so the automation never pays back. Too much and you get a nondeterministic system where a flowchart would have worked — higher token spend, failures that cannot be replayed reliably, and a debugging burden your team may not be staffed for.