Comparisons

Pairs engineers genuinely confuse — goal and implementation, MVP and bad prototype, prototype and spike, reversible and irreversible. Neither column wins; what decides is the problem. Each record leads with the confusion, because the confusion is what it costs.

Deterministic workflow vs agent

What people get wrong about this pair

The plan for an assistant over company documentation starts with a multi-agent framework because that is what the demos show, and the single question — why is one deterministic workflow insufficient? — is never asked. The cost is a system whose behaviour cannot be predicted, tested or explained, solving a problem that a retrieval step and one model call would have solved observably. The strongest form of the agent side is real: some tasks are open-ended, and a fixed sequence fails on them in ways that show up in an evaluation; the honest position is that the evaluation has to exist first, and the agent is the answer to a failure it shows, not to a demo.

Deterministic workflow — steps known in advance, possibly with a model call inside one of them
Use it when

When the sequence is known: retrieve the relevant documents, call the model once, return the answer with sources. Most "AI assistant" requests are this.

Agent — the next step chosen at run time from what the last step found
Use it when

When the sequence genuinely cannot be known in advance — the task branches on findings, tools must be chosen per case — and a measured failure of the single workflow says so.

AspectDeterministic workflow — steps known in advance, possibly with a model call inside one of themAgent — the next step chosen at run time from what the last step found
StepsFixed, known before the requestChosen during the request
TestableYes — same input, same pathOnly statistically, against an evaluation set
Explainable failureWhich step returned whatWhich choice at which turn, if logged
First version of a docs assistantRetrieve, call once, citeRarely
Justified byThe task being a sequenceA measured failure of the sequence
Sign of the mistakeA hard-coded flow that branches on twenty flagsA framework chosen before the evaluation exists