Persona
A persona is a characterization or assumed identity of a user, person, or software agent, defined by relevant traits, goals, perspectives, expertise, or behaviors.
AI Agents in Action
A persona is an agent's behavioral and biographical characterization that guides how it responds and performs tasks.
- How it is used
- Uses personas to frame agent responses and provide task-relevant roles or personalities.
- How deep it goes
- Explains persona instructions through contrasting prompts and walks through configuring and testing a YAML profile.
- Examples
- Contrasts junior-programmer and medical-professional responses and configures a cooking assistant with a chef-inspired personality.
- What you can do after
- Apply it via Nexus by creating a themed profile and testing responses in the interface.
Grokking AI Applications
The human identity or perspective that a prompt asks a language model to adopt when responding.
- How it is used
- Sets the human perspective or intended audience that guides an LLM's response within a structured prompt.
- How deep it goes
- Explains author and audience roles through a pretraining-pattern rationale and examples, without detailing model internals.
- Examples
- Uses an experienced marketing manager and an atom explanation aimed at a five-year-old to illustrate role choices.
- What you can do after
- Apply it by naming an author role or intended audience when framing a prompt.
AI Agents in Action, Second Edition
An agent persona is a role, background, behavioral style, expertise profile, and operating-constraint specification that guides an AI agent's responses and task behavior.
- How it is used
- Guides an agent’s task behavior and communication as its core instruction layer.
- How deep it goes
- Defines persona attributes and gives design rules, but does not detail implementation of automated persona optimization.
- Examples
- Uses coder and writer roles and a support assistant with JSON output, runtime date, boundaries, and an unknown-answer fallback.
- What you can do after
- Configure an agent with a narrow role, explicit boundaries, typed output, relevant runtime facts, and an uncertainty off-ramp.
Read how AI Agents in Action, Second Edition explains persona →
Architecture Modernization: Socio-technical alignment of software, strategy, and structure
A persona is a representative characterization of a user or participant whose goals, context, and behavior are used to explore an experience.
- How it is used
- Uses personas to warm up domain participants, map roles, and prepare collaborative EventStorming.
- How deep it goes
- Explains purposes, responsibilities, notation, and storytelling, but stops short of prescribing a rigid persona-development process.
- Examples
- Uses real-estate buyers and sellers, plus advertisers from startups and enterprises, to show overlapping roles and divergent experiences.
- What you can do after
- Practice mapping domain participants and telling differentiated experience stories during collaborative EventStorming.
BDD in Action, Second Edition
A persona is a detailed representation of a typical user, including characteristics such as goals, abilities, background, and motivations.
- How it is used
- Uses realistic named users to clarify user stories, acceptance scenarios, application behavior, and automated test state.
- How deep it goes
- Explains persona characteristics, scenario benefits, data lookup, and implementation options, then demonstrates actor configuration without detailing every test framework mechanism.
- Examples
- Uses Jill, Elsa, Sam, and Jane alongside banking, travel-planning, account-summary, and frequent-flyer registration scenarios.
- What you can do after
- Apply it via automated acceptance tests by naming actors and resolving their precise details from configuration, databases, factories, or test state.
Design for Developers
A representative profile describing a target type of user and that user's relevant goals or needs.
- How it is used
- Guides user-centered decisions across research, wireframing, visual design, development, and iteration.
- How deep it goes
- Explains profile content, research grounding, bias risks, and lifecycle use, illustrated through a persona-card example.
- Examples
- Uses a persona card containing age, occupation, family details, goals, and frustrations, plus support forums as a fallback research source.
- What you can do after
- Apply personas to keep target users’ goals and needs central during design and development decisions.
AI Agents and Applications
A persona is a prompt specification of the role, expertise, or perspective that a language model should adopt.
- How it is used
- Frames a language model’s role and expertise within structured prompts and dynamic research-assistant workflows.
- How deep it goes
- Defines persona use and shows prompt composition, but stops short of evaluating persona reliability or model behavior internally.
- Examples
- Uses finance analyst, marketing manager, sci-fi author, copy editor, and dynamically selected research-assistant personas.
- What you can do after
- Apply it via LangChain prompt templates to select specialized assistants and generate role-aware web-search instructions.
Architecting Accessibility
A persona is a representative user model that describes relevant characteristics, needs, constraints, and goals for reasoning about product use.
- How it is used
- Uses representative user profiles to reveal access barriers and guide reasoning about digital product use.
- How deep it goes
- Groups personas by access needs and gives concrete profiles across visual, cognitive, physical, auditory, and speech categories.
- Examples
- Uses profiles including Silvey’s color blindness, Sam’s memory and focus challenges, Steve’s one-handed use, and Gill’s need for captions.
- What you can do after
- Evaluate digital experiences by identifying barriers that arise when technologies do not accommodate people’s differences.
Effective Behavior-Driven Development
A representative user profile or named representation of a situation used to discuss expected behavior.
- How it is used
- Names business concepts and data situations so stakeholders can discuss intended behavior clearly.
- How deep it goes
- Defines personas and persona definitions, then previews ways to place and manage them.
- Examples
- Uses admin users, website guests, and customers with massive order histories as examples.
- What you can do after
- Understand how named users or data sets make scenario behavior and its supporting data clearer.
Read how Effective Behavior-Driven Development explains persona →
Build High Value Software Systems
A structured brief that shapes an AI assistant's responses toward specified characteristics, principles, or standards.
- How it is used
- Uses team architectural standards to configure an AI coding assistant as a pairing partner for implementation questions.
- How deep it goes
- Defines the persona and illustrates its guidance in a pairing exchange, but does not specify a process for creating one.
- Examples
- Uses Tom's inventory-reservation change and a Java architect persona with event-only communication constraints.
- What you can do after
- Apply it via an AI coding assistant to get architecture-aligned guidance while working in unfamiliar parts of a system.
Read how Build High Value Software Systems explains persona →
WordPress Power Toolkit: Harness AI to build next-level websites
A prompt role is the persona, perspective, or function assigned to an artificial-intelligence system within a prompt.
- How it is used
- Assigns the AI a function or perspective to shape its response, such as an editor or site designer.
- How deep it goes
- Defines role as a core prompt element and demonstrates it in reusable instructions and a complete example prompt.
- Examples
- Uses an expert nonfiction editor and an experienced professional site designer as assigned roles.
- What you can do after
- Apply it by assigning the AI a role before describing the task and the response you want.
Read how WordPress Power Toolkit: Harness AI to build next-level websites explains persona →
Also covered in
- Designing Deep Learning Systems: A guide for software engineers
- The Well-Grounded Data Analyst
- Coding with AI
- Context EngineeringIn early access (MEAP)
- Learn AI-Assisted Python Programming, Second Edition
What to know first
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- conversational aiConversational AI is artificial intelligence that enables software systems to interpret user input and interact with users through natural-language dialogue.
- AI agentAn AI agent is a computational system that uses artificial intelligence to interpret information and select or perform actions toward goals while interacting with an environment.
- promptA prompt is text or other input supplied to an AI model to provide instructions, context, or other information that guides its response or generated output.
Related concepts
- agent profilepart of · An agent profile is a specification of an agent's identity, background, demographics, behavioral guidance, and task-oriented characteristics.
- promptpart of · A prompt is text or other input supplied to an AI model to provide instructions, context, or other information that guides its response or generated output.
- AI agentpart of · An AI agent is a computational system that uses artificial intelligence to interpret information and select or perform actions toward goals while interacting with an environment.
- ai coding assistantconfigures · An AI coding assistant is a software tool or agent that uses artificial intelligence to help create, modify, explain, test, or review computer code.
- data personaincludes · A named description of data attributes for key inputs, preconditions, outputs, or other data representing a particular business situation.
- rolecontrasts with · A role is a defined function or status assigned to a participant that specifies responsibilities, permissions, behavior, or perspective within a system or organization.
Questions about persona
What is persona?
A persona is a characterization or assumed identity of a user, person, or software agent, defined by relevant traits, goals, perspectives, expertise, or behaviors.
Which Manning books explain persona?
AI Agents in Action, Grokking AI Applications, AI Agents in Action, Second Edition, Architecture Modernization: Socio-technical alignment of software, strategy, and structure, BDD in Action, Second Edition, Design for Developers, AI Agents and Applications, Architecting Accessibility and 3 more.
What should I know before learning persona?
Manning books that teach persona usually introduce language model, conversational ai, AI agent and prompt first.
What is the difference between persona and role?
A persona is a characterization or assumed identity of a user, person, or software agent, defined by relevant traits, goals, perspectives, expertise, or behaviors. A role is a defined function or status assigned to a participant that specifies responsibilities, permissions, behavior, or perspective within a system or organization.
What kinds of persona are there?
Kinds of persona include data persona.
What is persona part of?
Persona is part of agent profile. An agent profile is a specification of an agent's identity, background, demographics, behavioral guidance, and task-oriented characteristics.
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.










