Common sense
Common sense is ordinary background knowledge and practical judgment used to interpret everyday situations and draw plausible conclusions about entities, events, relationships, and consequences.
The Art of AI Product Development
Common-sense reasoning is the application of ordinary background knowledge and practical assumptions to interpret situations and make judgments.
- How it is used
- Positions common-sense reasoning as a human strength for designing effective human–AI collaboration and assigning appropriate automation.
- How deep it goes
- Defines contextual inference and adaptation through examples but stops short of explaining computational mechanisms.
- Examples
- Uses X-ray interpretation, empathetic customer service, and product-feature alignment as practical examples.
- What you can do after
- Evaluate which decisions require human contextual judgment when integrating AI into product workflows.
Read how The Art of AI Product Development explains common sense →
Natural Language Processing in Action, Second Edition
Commonsense knowledge is general background knowledge about everyday entities, events, relationships, and expectations.
- How it is used
- Supports natural language interpretation by supplying everyday knowledge that literal text leaves unstated.
- How deep it goes
- Defines the challenge and outlines ontologies and knowledge graphs, but stops short of implementation details.
- Examples
- Uses “good morning,” “which way is up,” everyday expectations, and relationship-rich knowledge graphs as examples.
- What you can do after
- Evaluate how missing background knowledge can cause language systems to misinterpret ordinary statements.
Read how Natural Language Processing in Action, Second Edition explains common sense →
Inside AI
Common-sense knowledge is informal background knowledge about ordinary situations, entities, and expectations that people typically apply without explicit instruction.
- How it is used
- Guides human decision-making, ordinary action, and interpretation of complex situations through shared experience and contextual judgment.
- How deep it goes
- Defines common sense through everyday examples, abstractions, implications, and AI contrasts without detailing its cognitive mechanisms.
- Examples
- Uses physical expectations, changing ride conditions, weather implications, figurative language, and aircraft damage analysis.
- What you can do after
- Evaluate/understand why data-driven AI fails on context-dependent, figurative, and counterintuitive reasoning tasks.
Knowledge Graphs and LLMs in Action
Common-sense reasoning is the use of ordinary human background knowledge and intuitive context to draw plausible conclusions.
- How it is used
- Frames common sense as a design concern when combining knowledge graphs and language models in intelligent systems.
- How deep it goes
- Defines the capability and contrasts reasoning roles, but stops short of specifying an implementation method for human-like common sense.
- Examples
- Uses a farmer, sheep, and boat river-crossing puzzle to test constraint handling and reasoning capabilities.
- What you can do after
- Evaluate reasoning systems by probing intuitive context, constraint handling, ambiguity, and failures to make human-like inferences.
Read how Knowledge Graphs and LLMs in Action explains common sense →
Related concepts
- decision makingpart of · Decision making is the process of selecting an action, outcome, or judgment from available alternatives based on information, objectives, or constraints.
- abstractionuses · Abstraction is a simplified representation that exposes relevant properties or behavior while omitting lower-level details unnecessary for a given purpose.
- generationuses · Generation is the computational production of outputs from supplied inputs or context, often by applying a model to produce predictions or new content.
- contextuses · Context is the surrounding information, state, or circumstances that condition how an entity, event, or task is interpreted or how a system behaves.
- world modeluses · A world model is an internal computational representation of entities, relationships, states, and dynamics in an environment that supports prediction, reasoning, or action.
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.