liveBook · Manning

Persona

As explained in AI Agents and Applications

A persona is a prompt specification of the role, expertise, or perspective that a language model should adopt.

A persona is a prompt specification that tells a language model which role, expertise, or perspective to adopt. Use it to set expectations before providing context, instructions, input, or output requirements. section 2.6

A concrete persona

For a research question about investments, begin with: “You are an experienced finance analyst AI assistant. Your objective is to create detailed, insightful, unbiased, and well-structured financial reports based on the provided data and trends.” The persona frames how the model should generate its work. section 4.5.1

Use a persona as one part of a larger prompt specification:

  • Choose a role suited to the task, such as a marketing manager, sci-fi author, copy editor, or finance analyst. section 2.6
  • Combine the role with context, explicit instructions, input, processing steps, tone, output format, and examples when the task needs them. section 2.6
  • For dynamic research workflows, select an assistant type from the user’s question, then pass its instructions into a later web-search prompt. section 4.5.1
Listing 4.2 prompts.py: Generating assistant instructions
from langchain_core.prompts import PromptTemplate

ASSISTANT_SELECTION_INSTRUCTIONS = """
You are skilled at assigning a research question to the correct 
research assistant. 
There are various research assistants available, each specialized
in an area of expertise. 
Each assistant is identified by a specific type. Each assistant
has specific instructions to undertake 
the research.   #1

How to select the correct assistant: you must select the 
relevant assistant depending on the topic of the question, 
which should match the area of expertise of the assistant.

------
Here are some examples on how to return the correct assistant
information, depending on the question asked.

Examples:
Question: "Should I invest in Apple stocks?"
Response: 
{{
    "assistant_type": "Financial analyst assistant",
    "assistant_instructions": "You are a seasoned finance
analyst AI assistant. Your primary goal is to compose 
comprehensive, astute, impartial, and methodically arranged
financial reports based on provided data and trends.",
    "user_question": {user_question}
}}
Question: "what are the most interesting sites in Tel Aviv?"
Response: 
{{
    "assistant_type": "Tour guide assistant",
    "assistant_instructions": "You are a world-travelled
AI tour guide assistant. Your main purpose is to draft
engaging, insightful, unbiased, and well-structured 
travel reports on given locations, including history, 
attractions, 
and cultural insights.",
    "user_question": "{user_question}"
}}

Question: "Is Messi a good soccer player?"
Response: 
{{
    "assistant_type": "Sport expert assistant",
    "assistant_instructions": "You are an experienced AI
sport assistant. Your main purpose is to draft engaging,
insightful, unbiased, and well-structured sport reports on 
given sport personalities, or sport events, including 
factual details, statistics and insights.",
    "user_question": "{user_question}"
}}

------
Now that you have understood all the above, select the
correct research assistant for the following question.
Question: {user_question}
Response:

""" 

ASSISTANT_SELECTION_PROMPT_TEMPLATE = PromptTemplate.from_template( 
    template=ASSISTANT_SELECTION_INSTRUCTIONS
)

The assistant-selection prompt demonstrates how a persona can be generated dynamically from a question and returned with specialized instructions. section 4.5.1

A persona guides framing but does not replace task specification. Improve reliability by pairing it with clear instructions, few-shot examples, and a structured response format such as JSON. section 2.6 section 4.5.1

How AI Agents and Applications covers it

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 it assumes
Assumes familiarity with basic prompt elements and introduces persona alongside context, instructions, input, steps, tone, and output format.
What you can do after
Apply it via LangChain prompt templates to select specialized assistants and generate role-aware web-search instructions.
How it connects
Connects persona with prompt structure, context, instructions, few-shot prompting, output formatting, and research assistants.

Also explained in

Compare how 6 books explain persona →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of AI Agents and Applications. The section links point to the parts of the book it draws on.