liveBook · Manning

Reasoning

Reasoning is the process of deriving conclusions, solutions, or actions from available information through inferential steps.

How 2 Manning books explain it

Designing AI Agents

An agent capability for evaluating information, forming hypotheses, and selecting conclusions or actions.

How it is used
Positions reasoning as the agent's decision-making function between filtered context and action.
How deep it goes
Develops routing, evidence-based evaluation, hypothesis testing, and observable traces, while separating model reasoning from decision records and action evidence.
Examples
Uses a code-review agent's renaming refactor and a reasoning telemetry dataclass to illustrate verification and observation.
What you can do after
Enables readers to evaluate reasoning using accepted outcomes, evidence coverage, routing regret, calibration, and cost.

Read how Designing AI Agents explains reasoning →

Machines that Think

The process of deriving conclusions or solutions from information, premises, or relationships.

How it is used
Uses reasoning to examine how machines can produce inference-like behavior and what that behavior means for intelligence.
How deep it goes
Explains rule-based computation and possible chain-of-thought mechanisms, while noting that why intermediate steps work remains unsettled.
Examples
Uses intermediate steps in a chain-of-thought response to illustrate scaffolding, explanation, and potentially misleading traces.
What you can do after
Evaluate reasoning-like AI outputs by distinguishing observable performance from understanding and recognizing reliability limits.

Read how Machines that Think explains reasoning →

What to know first

Related concepts

Questions about reasoning

What is reasoning?

Reasoning is the process of deriving conclusions, solutions, or actions from available information through inferential steps.

Which Manning books explain reasoning?

Designing AI Agents and Machines that Think.

What should I know before learning reasoning?

Manning books that teach reasoning usually introduce language model, context window, environment and large language model first.

What is reasoning a kind of?

Reasoning is a kind of cognitive function. A cognitive function is one of the agent capabilities represented in the framework as perception, memory, reasoning, action, reflection, collaboration, or governance.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.