mediumAnthropic Sierra Cognition

Workflows versus agents: how much autonomy should you actually give an AI system, and how do you decide?

The industry conflates 'agent' with anything that calls an LLM. The useful distinction is how much control you hand to the model, and more autonomy is not better. Here is the spectrum and the decision rule.

Updated Aug 2026 · Grounded in real Applied AI Engineer interview loops and written to a senior-engineer editorial bar.

Unlock the other 754 answers · ₹2,000 / $25includes both full courses · progress stays saved · 6 months · one payment · no auto-renew

LEARN THE BACKGROUND

These lessons teach the material this question tests, in order and from the beginning.

Agent Engineering·What an agent is, and when not to build oneFree14mWhat an agent is, and the question to ask before you build oneAgents are the most over-applied pattern in applied AI. This lesson gives you the spectrum from fixed workflow to autonomous loop, the honest cost of each step along it, and the decision rule the rest of this course is built on: use the least autonomy that solves the task.Applied AI Engineering·Tools and your first agentSign in12mTry these five things before you build an agentNow that you can build an agent, here is the ladder of cheaper designs to exhaust first. Each rung handles a large share of what people reach loops for, and moving up one rung at a time is how you end with a system you can operate.

UP NEXT ON YOUR JOURNEY

Next in this trackBuild a customer-support agent over a fake product/SQL database: tool-calling, retrieval, and a control loop.Next in this trackBuild a small in-memory document indexer and retriever from scratch (inverted index + BM25), then add a vector option.Next in this trackHow do you operate a multi-vector (ColBERT-style) index in production without it blowing up storage?

DISCUSSION · 0

No comments yet — be the first to share your approach.