Cognition
Cognition is the set of processes by which an agent acquires, processes, represents, and uses information.
Machines that Think
Mental processes involved in acquiring, processing, storing, and applying information.
- How it is used
- Uses human cognition as a reference for interpreting artificial intelligence without treating it as the sole possible form of intelligence.
- How deep it goes
- Compares cognitive capabilities and mechanisms conceptually while acknowledging that internal processes can be difficult to inspect.
- Examples
- Illustrates cognition through pre-speech reasoning, expert intuition, spatial reasoning, and language generation.
- What you can do after
- Evaluate claims about AI cognition by distinguishing observable performance from underlying mechanisms and human-like understanding.
AI Agents in Action, Second Edition
Cognition is an agent’s ability to model a task, decompose problems, reason about dependencies, compose tools, and update its understanding from new information.
- How it is used
- Frames agent cognition as the task-modeling capability needed to handle ambiguity, conflicting evidence, and incomplete knowledge.
- How deep it goes
- Defines four observable capabilities and maps them to reasoning primitives, while explicitly stopping short of claims about consciousness.
- Examples
- Illustrates tool composition with separate lookups that must be joined or compared to answer a request.
- What you can do after
- Evaluate agent behavior by checking whether it decomposes novel tasks, respects dependencies, composes tools, and updates its plan.
Read how AI Agents in Action, Second Edition explains cognition →
Inside AI
Living intelligence is the adaptive information-processing capacity exhibited by biological organisms and their cells.
- How it is used
- Frames cognition as biological intelligence for adapting to information, from cellular responses to human thought.
- How deep it goes
- Connects memory, generalization, intuition, and subconscious influence while leaving the mechanisms producing thought unresolved.
- Examples
- Uses measles infection to illustrate immune-cell learning, antibody adjustment, and inherited cellular memory.
- What you can do after
- Evaluate AI claims against human capacities for imagination, intuition, memory, and perception.
Natural Language Processing in Action, Second Edition
Cognition is the set of mental processes involved in acquiring, representing, manipulating, and using knowledge.
- How it is used
- Connects reading and writing with thought to explain why natural language processing is associated with artificial intelligence.
- How deep it goes
- Defines cognition broadly as thought and illustrates it through reading and writing, without detailing underlying mental processes.
- Examples
- Uses composing sentences and paragraphs, and recalling a concept through its word, as examples of thought.
- What you can do after
- Understand why machine text processing is associated with the thinking involved in human reading and writing.
Read how Natural Language Processing in Action, Second Edition explains cognition →
Also covered in
- Designing AI AgentsIn early access (MEAP)
What to know first
- artificial intelligenceArtificial intelligence is the field of computing concerned with creating systems that perform tasks associated with intelligence, such as learning, reasoning, perception, and decision-making.
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- memoryMemory is a storage capability or mechanism for retaining information or computational state for later access or use.
Related concepts
- neural networkcontrasts with · A neural network is a computational model composed of interconnected, parameterized units or transformations that learn to map inputs to outputs.
- cognitive modulehas part · A separable agent subsystem responsible for a cognitive function such as perception, memory, reasoning, action, reflection, or collaboration.
- problem solvingcontrasts with · Problem solving is the process of analyzing a problem and developing, selecting, or applying a solution to address it.
- memoryincludes · Memory is a storage capability or mechanism for retaining information or computational state for later access or use.
- working memoryincludes · Working memory is information temporarily retained and available for immediate use during an ongoing task or interaction.
Questions about cognition
What is cognition?
Cognition is the set of processes by which an agent acquires, processes, represents, and uses information.
Which Manning books explain cognition?
Machines that Think, AI Agents in Action, Second Edition, Inside AI and Natural Language Processing in Action, Second Edition.
What should I know before learning cognition?
Manning books that teach cognition usually introduce artificial intelligence, language model and memory first.
What is the difference between cognition and neural network?
Cognition is the set of processes by which an agent acquires, processes, represents, and uses information. A neural network is a computational model composed of interconnected, parameterized units or transformations that learn to map inputs to outputs.
What kinds of cognition are there?
Kinds of cognition include memory, working memory and artificial cognition.
What are the parts of cognition?
Cognition includes cognitive module.
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.



