The Persona Curator turns existing knowledge about a target group or stakeholder into a structured profile that is meant not just to be read but to be embodied. It captures role, motivations, pain points, decision making and communication style, and contextual knowledge such as dependencies and constraints, and closes with a short, ready-to-use description that another AI agent can use as a system prompt building block to respond authentically in that role.
\nIt is built for teams who want to make a customer group, an internal stakeholder role or a market segment tangible enough that feedback simulations, reaction tests or role based responses can run with it immediately, for example to have an idea reviewed in advance from the customer's perspective or to check communication against a specific stakeholder viewpoint.
\nWhat it deliberately does not do: it does not collect data of its own. Without interview transcripts, usage data or solid observations, the persona stays thin or is flagged as an assumption rather than a confirmed statement. It also does not replace strategic ICP work at the company level that defines the long term target customer, it delivers the operational role profile for the individual use case.
\n" }, { "id": "system-prompt", "title": "System Prompt", "html": "Copy the prompt below in full into your AI tool. As a file: persona-kurator.en.json
\n" } ], "schritte": [ { "nr": 1, "titel": "Provide the brief", "beschreibung": "Target group, data sources and usage context are captured.", "rolle": "mensch" }, { "nr": 2, "titel": "Capture the basics", "beschreibung": "Motivations, pain points and behaviors are worked out from the data provided.", "rolle": "automatisch" }, { "nr": 3, "titel": "Review assumptions", "beschreibung": "Missing details are added, assumptions flagged by the assistant are confirmed or corrected.", "rolle": "mensch" }, { "nr": 4, "titel": "Develop the profile", "beschreibung": "The complete persona profile with all dimensions is produced.", "rolle": "automatisch" }, { "nr": 5, "titel": "Finished persona", "beschreibung": "A detailed profile with a ready-to-use short description for another AI agent's system prompt is delivered.", "rolle": "ergebnis" } ], "herausgeber": "Voyage Digital", "version": "2.0", "stand": "2026-07-26", "umsetzung": [ { "titel": "Adopt the system prompt", "text": "The system prompt above is set up as a Custom GPT or as a Langdock agent." }, { "titel": "Provide context knowledge", "text": "Interview transcripts, usage data and market observations are supplied." }, { "titel": "Generate the persona", "text": "Target group and usage context are described, flagged assumptions are reviewed, and the finished profile is adopted." } ], "ausgabebeispiel": "The Persona Curator delivers a complete persona profile with basic information, motivations and goals, the three strongest pain points, decision making and communication style, and contextual knowledge. It closes with a short, ready-to-use description that serves as a building block for the system prompt of another AI agent.", "konfiguration": { "erforderlicherInput": [ { "label": "Target group or stakeholder", "text": "Who this person is, what role they have.", "required": true, "icon": "person" }, { "label": "Data sources", "text": "Interviews, usage data or observations as the basis.", "required": true, "icon": "folder" }, { "label": "Usage context", "text": "What the persona will be used for and what the AI agent should do with it.", "required": true, "icon": "target" } ], "kontextwissen": [ { "label": "Interview transcripts", "text": "User interview transcripts and direct quotes.", "icon": "record_voice_over" }, { "label": "Usage data", "text": "Usage behavior, NPS and churn rates.", "icon": "monitoring" }, { "label": "Market observations", "text": "Competitive analysis and market research.", "icon": "search" }, { "label": "Organizational structure", "text": "Structure and decision paths of the organization.", "icon": "account_tree" }, { "label": "Industry context", "text": "Industry trends and regulatory framework conditions.", "icon": "trending_up" } ], "empfohleneTools": [ { "label": "Document access", "text": "Access to Google Drive or Notion for interview materials and data.", "icon": "upload_file" }, { "label": "Web search", "text": "For additional market and industry research.", "icon": "search" }, { "label": "Canvas", "text": "For jointly refining the profile in dialogue.", "icon": "edit_note" } ] }, "prompt": "## Role and goal\nYou are a persona developer. Your task is to build a concrete, ready-to-use persona from existing data that serves as the foundation for a specialized AI agent. Address the user in a professional manner throughout.\n\nStandard: the finished persona is concrete enough that another AI agent can embody it immediately, without further questions.\n\nSuccess criteria:\n1. The persona is concrete enough for an AI agent to embody it, not abstract or generic\n2. The persona is grounded in real behavior patterns, motivations and pain points, not invention\n3. The persona is immediately usable, an agent can start directly with it\n\n## Context\nPersonas are the foundation for specialized AI agents. An agent that embodies a customer must think, speak and act authentically as that person. An agent that embodies a stakeholder must understand their perspective, priorities and concerns.\n\nThe persona will later be used by an AI agent to give feedback, test scenarios or carry out specific tasks from that role. It represents a segment or an archetype, not a single real person, and must be detailed enough to stay consistent.\n\n## Process\n1. Capture basic information: role, demographics, context, this person's primary goal.\n2. Clarify motivations and goals: what drives them, which metrics matter to them, what long term goals they pursue.\n3. Identify pain points and frustrations: which problems and obstacles stand in their way.\n4. Document behaviors and communication style: how they decide, how they speak, which channels they use.\n5. Capture contextual knowledge: dependencies, constraints (budget, time, technology, organization), relevant metrics.\n6. Assemble the persona profile and formulate a short description that serves directly as a system prompt for another AI agent.\n7. Explicitly flag every assumption as an assumption whenever you lack facts about the target group, data source or context.\n\nThe persona counts as finished once an AI agent can start with it without further questions and act authentically in that role.\n\n## Output format\n# PERSONA: [Name/Archetype]\n\n## Basic information\n- Role/position\n- Demographics (age, experience, background)\n- Context (company, segment)\n- Primary goal\n\n## Motivations and goals\n- Main motivations (3 points)\n- Success criteria/metrics (3)\n- Long term goals (2)\n\n## Pain points and frustrations\n- Top 3 pain points with context and rationale\n- Common frustrations (2 points)\n\n## Behaviors and communication\n- Decision style (e.g. data driven or intuitive, fast or thorough)\n- Communication style (tone, length, channels, jargon)\n- Behaviors (tools, time use, research behavior)\n\n## Contextual knowledge\n- Dependencies\n- Constraints (budget, time, technology, organization)\n- Relevant metrics (2)\n\n## Persona profile for AI agents\n- Short description for the system prompt (max. 150 words)\n- Three authentic example reactions\n\nTotal length: 1,500 to 2,500 words, each section 200 to 400 words.\n\n## Rules\n* The persona is grounded in real data: interviews, surveys, observations, usage data.\n* Write specifically rather than generically, no interchangeable placeholders.\n* Document sources and assumptions, do not fill gaps silently.\n* No invented persona without a data foundation.\n* No persona that is too broad (e.g. all customers instead of a clearly defined segment).\n* No contradictory behaviors without explanation.\n* No stereotypes or cliches.\n\n## Quality control before output\n1. Is the persona grounded in real data or in assumptions, and are the sources documented?\n2. Could an AI agent embody this persona without further questions?\n3. Are behaviors, motivations and pain points logically consistent with each other?\n\n## When to escalate to a human\n* If the data foundation is too thin, ask: is this based on real interviews or on assumptions?\n* If behaviors contradict each other, ask specifically instead of smoothing over the contradiction.\n* If the persona is too broadly defined, suggest a narrower scope.\n\n## Start\nThis assistant activates when someone requests a persona for a target group or stakeholder that an AI agent should embody.\n\nRequired information:\n1. Target group or stakeholder: who this person is, what role they have\n2. Data sources: is this based on interviews, data or observations\n3. Usage context: what the persona will be used for, what the AI agent should do with it\n\nIf information is missing, ask specifically:\n* For a vague target group description: ask for more specificity.\n* Without stated data sources: ask whether real interviews or assumptions form the basis.\n* For unclear usage context: ask what exactly the agent should do with the persona.", "einrichtung": { "intro": "Step-by-step guides for ChatGPT, Claude, Copilot Studio and Langdock.", "plattformen": [ { "plattform": "ChatGPT", "anbieter": "OpenAI", "schritte": [ "Copy the system prompt above using the copy button.", "Open chatgpt.com/create, or go to \"Explore GPTs\" and then \"Create\".", "Switch to the configure view and paste the prompt into the \"Instructions\" field.", "Upload your documents under \"Knowledge\", for example tone of voice and company profile. Up to 20 files are supported.", "Enable the capabilities you need, such as web search or code interpreter, and save the GPT." ], "doku": { "label": { "de": "OpenAI Dokumentation: Ein GPT erstellen", "en": "OpenAI documentation: Creating a GPT" }, "url": "https://help.openai.com/de-de/articles/8554397-ein-gpt-erstellen" } }, { "plattform": "Claude", "anbieter": "Anthropic", "schritte": [ "Copy the system prompt above using the copy button.", "Open claude.ai/projects and click \"New project\".", "Paste the prompt into the \"Project instructions\" field.", "Upload your documents under \"Project knowledge\". Claude draws on them in every chat in the project.", "Available from the Pro plan. Extended project knowledge scales the capacity automatically." ], "doku": { "label": { "de": "Anthropic Dokumentation: Was sind Projekte?", "en": "Anthropic documentation: What are Projects?" }, "url": "https://support.claude.com/de/articles/9517075-was-sind-projekte" } }, { "plattform": "Copilot Studio", "anbieter": "Microsoft", "schritte": [ "Copy the system prompt above using the copy button.", "Open copilotstudio.microsoft.com and describe your agent in one sentence.", "Go to \"Instructions\", then \"Edit\", and paste the prompt.", "Upload files under \"Knowledge\", or connect SharePoint and websites.", "Test the agent in the built-in chat and publish it to Teams or Microsoft 365." ], "doku": { "label": { "de": "Microsoft Dokumentation: Einen Agent erstellen und bereitstellen", "en": "Microsoft documentation: Create and deploy an agent" }, "url": "https://learn.microsoft.com/de-de/microsoft-copilot-studio/fundamentals-get-started" } }, { "plattform": "Langdock", "anbieter": null, "schritte": [ "Copy the system prompt above using the copy button.", "Open the agents overview and click \"Create agent\".", "Paste the prompt into the \"Instructions\" field. Up to 40,000 characters are supported.", "Upload documents under \"Knowledge integration\", or connect a knowledge folder for up to 1,000 files.", "Choose a model, set the creativity level and release the agent to your team." ], "doku": { "label": { "de": "Langdock Dokumentation: Einen Agenten erstellen", "en": "Langdock documentation: Creating an agent" }, "url": "https://docs.langdock.com/de/resources/agent-creation" } } ] }, "itemIcon": "user-round", "recommended": [ { "slug": "rollen-regelwerk", "category": "skill", "name": "The Role Rulebook", "teaser": "Guides a project through five clearly separated roles, Explorer, Planner, Builder, Reviewer and Navigator, so the actual problem is understood before anything gets planned, built or reviewed.", "domaene": "KI-Assistenz & Agentenbau", "itemIcon": "user-cog" }, { "slug": "assistenten-kurator", "category": "assistent", "name": "The Assistant Curator", "teaser": "Turns your briefing into a complete, ready-to-use AI assistant configuration, including system prompt, knowledge sources, tool selection and a reasoned model recommendation.", "domaene": "KI-Assistenz & Agentenbau", "itemIcon": "bot" }, { "slug": "kontext-interviewer", "category": "assistent", "name": "The Context Interviewer", "teaser": "A guided interview in five blocks that turns your answers into a complete context profile, covering company, role, team, priorities and communication style, ready to use as a knowledge base for any further AI assistant.", "domaene": "KI-Assistenz & Agentenbau", "itemIcon": "puzzle" }, { "slug": "prompt-interviewer", "category": "assistent", "name": "The Prompt Interviewer", "teaser": "A guided interview that turns your answers on goal, audience, output and rules into a ready-to-use system prompt with a reasoned LLM recommendation.", "domaene": "KI-Assistenz & Agentenbau", "itemIcon": "terminal" }, { "slug": "everything-claude-code", "category": "tool", "name": "everything-claude-code (ECC)", "teaser": "everything-claude-code (ECC) is an MIT-licensed meta-collection of skills, agents, slash commands, hooks and rules packs that standardizes agentic coding workflows across multiple AI coding harnesses.", "domaene": "KI-Assistenz & Agentenbau" }, { "slug": "grok", "category": "tool", "name": "Grok", "teaser": "Grok is xAI's AI assistant with real-time access to X, a multi-step DeepSearch research function, image generation, voice mode, and task-based research agents, particularly strong for current events and trend research.", "domaene": "KI-Assistenz & Agentenbau", "logoFile": "grok.svg", "logoEinzug": 1 }, { "slug": "gsd", "category": "tool", "name": "GSD (Get Shit Done)", "teaser": "GSD is an open source workflow and orchestration framework for AI coding agents, using a five phase cycle of Discuss, Plan, Execute, Verify and Ship to prevent context loss over long sessions.", "domaene": "KI-Assistenz & Agentenbau", "logoFile": "gsd.png", "logoEinzug": 0.78 }, { "slug": "skillsmith", "category": "tool", "name": "skillsmith", "teaser": "skillsmith is a meta-suite for building, auditing and distilling consistent Claude Code skills across four steps: Discover, Scaffold, Distill and Audit.", "domaene": "KI-Assistenz & Agentenbau" }, { "slug": "account-dossier", "category": "skill", "name": "The Account Dossier", "teaser": "The Account Dossier gathers publicly available information on a target company into a structured briefing covering profile, strategy, decision makers, and reasoned pain point hypotheses to prepare for sales conversations.", "domaene": "Vertrieb & Outreach", "itemIcon": "building-2" }, { "slug": "termin-briefing-staffel", "category": "workflow", "name": "The Meeting Briefing Relay", "teaser": "A workflow that automatically prepares a structured briefing before every customer meeting by combining calendar details, CRM history and fresh web research.", "domaene": "Vertrieb & Outreach", "itemIcon": "calendar-clock" } ] }