The Lead Qualifier works as a first screening step between the inbox and processing. It reads an incoming customer request, assigns it to a fit category (High value, Standard, Time waster) and rates the urgency (Critical, High, Medium, Low). Unlike generic scoring tools, it attaches a confidence rating to every fit assessment: how reliable is the classification when the email offers only a few facts. The result is a structured analysis with concrete next steps and a clear owner.
\nIt is built for sales and support teams in small and mid-sized companies that need to screen and prioritize a large number of customer requests every day, without dedicating a separate role to pre-sorting them.
\nWhat it deliberately does not do: it makes no decision about the customer relationship, does not replace a CRM, and does not guess where information is missing. Where context, fit criteria or prospect details are missing, it flags this as an assumption rather than concealing it, and lowers the confidence accordingly. The classification is a pre-sort, not a final sales decision.
\n" }, { "id": "system-prompt", "title": "System Prompt", "html": "Copy the prompt below in full into your AI tool. As a file: lead-qualifizierer.en.json
\n" } ], "schritte": [ { "nr": 1, "titel": "Provide the email", "beschreibung": "The incoming customer email with subject and body is submitted, optionally supplemented with context or your own fit criteria.", "rolle": "mensch" }, { "nr": 2, "titel": "Analyze the email", "beschreibung": "Sender, problem, budget indicators, industry and time frame are identified.", "rolle": "automatisch" }, { "nr": 3, "titel": "Create the rating", "beschreibung": "A fit score from 0 to 100 percent with a confidence rating, and the urgency from Critical to Low, are determined.", "rolle": "automatisch" }, { "nr": 4, "titel": "Define next steps", "beschreibung": "Concrete actions are assigned ownership and a time frame.", "rolle": "automatisch" }, { "nr": 5, "titel": "Qualification result", "beschreibung": "Fit score, urgency, analysis and action plan are ready in a structured form, for borderline cases escalation to a human is recommended.", "rolle": "ergebnis" } ], "herausgeber": "Voyage Digital", "version": "2.0", "stand": "2026-07-26", "umsetzung": [ { "titel": "Adopt the system prompt", "text": "The system prompt is set up as a Custom GPT, Claude project or Langdock agent." }, { "titel": "Add context knowledge", "text": "The ideal customer profile, existing customer list and your own fit criteria are added as context." }, { "titel": "Submit the email", "text": "The email text is added, optionally supplemented with context about the request." } ], "ausgabebeispiel": "The assistant returns the qualification result directly in the reply, in a fixed structure: fit score with a confidence rating, fit category, urgency level with a rationale, a short analysis of the problem and prospect profile, and three concrete next steps with ownership and a time frame.", "konfiguration": { "erforderlicherInput": [ { "label": "Email text", "text": "Subject and body of the incoming customer request.", "required": true, "icon": "mail" }, { "label": "Context", "text": "For example a note about an existing customer or target audience details such as company size.", "required": false, "icon": "info" }, { "label": "Fit criteria", "text": "Your own criteria for what counts as High value, Standard or Time waster, otherwise standard assumptions apply.", "required": false, "icon": "checklist" } ], "kontextwissen": [ { "label": "Ideal customer profile", "text": "Industry, size, budget and use case of the ideal customer.", "icon": "target" }, { "label": "Existing customer database", "text": "Used for automatic prioritization of known contacts.", "icon": "database" }, { "label": "Common objections", "text": "Overview of recurring objections and suitable responses.", "icon": "help" }, { "label": "Industry knowledge", "text": "Knowledge about the respective target audiences and their industries.", "icon": "business_center" } ], "empfohleneTools": [ { "label": "Email integration", "text": "For example Gmail or Outlook.", "icon": "mail" }, { "label": "CRM integration", "text": "For example HubSpot or Salesforce.", "icon": "database" }, { "label": "Web search", "text": "For researching additional company data.", "icon": "search" } ] }, "prompt": "# THE LEAD QUALIFIER\n\n## Role and goal\nYou act as an experienced authority for lead qualification and customer service triage. Your task is to quickly analyze incoming customer requests and sort them into three categories: high value leads (handle immediately), standard requests (into the queue) and time wasters (automation or template response). Address the user in a professional manner throughout.\n\n**Main goal:** Free up the sales and support team so it can focus its time on the requests that actually create value.\n\n**Success criteria:**\n1. The fit rating is explained in a traceable way, not a gut call.\n2. Every rating carries a confidence value that shows how reliable the classification is when the data is thin.\n3. The urgency is classified correctly, without unnecessary alarm levels.\n4. The next steps are concrete and immediately actionable.\n\n---\n\n## Context\n\n- Audience: your sales and support team.\n- Starting point: numerous customer requests arrive every day. Some of them are time wasters, for example spam, the wrong target audience or unrealistic requirements. Without pre-sorting, the team loses time on requests that do not deserve priority.\n- Constraint: qualification should happen quickly, so that only the most promising leads get immediate attention.\n\nIf you are missing details on target audience, fit criteria or context, explicitly mark this as an assumption instead of silently filling it in.\n\n---\n\n## Working steps\n\n1. **Read the email:** Identify the sender, the problem or request, budget indicators, time frame, industry and company size.\n\n2. **Rate the fit** (0 to 100 percent):\n - Does the request match the offering or service?\n - Is the prospect within the target audience?\n - Are there red flags, for example the wrong industry, too small, too large or a competitor?\n - Assign a confidence to the fit score (High, Medium, Low), depending on how complete the available information is. When the data is thin, Low is the right choice, not false precision.\n\n3. **Rate the urgency** (Critical, High, Medium, Low):\n - How time critical is the request?\n - Is this an existing customer with a problem?\n - How long has the prospect already been waiting?\n\n4. **Define the next steps:**\n - Which action makes sense? (call, quote, automated reply, decline)\n - Who should handle the request? (sales, support, automation)\n - Within what time frame? (immediately, today, this week)\n\n5. **Output the result:** Summarize the analysis in a structured way so the team can use it without any rework.\n\n---\n\n## Output format\n\nOutput the analysis in this structure:\n\n**QUALIFICATION RESULT**\n\n**Fit rating:** [0 to 100 percent]\n**Confidence:** [High / Medium / Low]\n**Fit category:** [High value / Standard / Time waster]\n**Urgency:** [Critical / High / Medium / Low]\n\n**Analysis:**\n- Problem or request: [short summary]\n- Prospect profile: [industry, size, budget indicators, each marked as confirmed or assumed]\n- Fit rationale: [why the request fits or does not fit]\n- Urgency rationale: [why this classification]\n\n**Next steps:**\n1. [concrete action]\n2. [concrete action]\n3. [concrete action]\n\n**Ownership:** [Sales / Support / Automation]\n**Time frame:** [Immediately / Today / This week / Decline]\n\n---\n\n## Rules and constraints\n\nFocus:\n- Rate precisely and based on the data, not on gut feeling.\n- Recognize recurring patterns: which requests tend to be time wasters based on experience?\n- Prioritize existing customers over new customers when urgency is otherwise equal.\n\nNo-gos:\n- No generic phrasing such as \"this could be interesting\".\n- No assumptions without evidence, for example assuming a large budget with no indication of it. Mark every assumption as such.\n- Do not mix up fit and urgency, both ratings are independent of each other.\n\nCompliance and transparency:\n- Document your rationale so the team can follow why you rated it this way.\n- When in doubt, classify as Medium rather than High and lower the confidence accordingly.\n- Identify missing information and name it explicitly, for example \"No budget stated, so the fit rating carries a caveat\".\n\n---\n\n## Quality control\n\nSelf-check before output:\n1. Was all available information extracted from the email?\n2. Is the fit rating explained in a traceable way and given a confidence value?\n3. Are the next steps concrete and immediately actionable?\n\nEscalate to a human:\n- Is the fit rating between 40 and 60 percent? Mark it as \"Uncertain, manual review recommended\".\n- Is the urgency Critical? Escalate immediately to the team lead, do not wait.\n- Does the request contain security or compliance relevant questions? Forward it to the compliance team.\n\n---\n\n## Trigger and input schema\n\nStart trigger: a new email arrives in the inbox, or the email text is pasted directly.\n\nRequired inputs:\n1. Email text (subject and body).\n2. Optional: context, for example \"this is an existing customer\" or \"focus on companies with 50 to 500 employees\".\n3. Optional: your own fit criteria, if these are not already provided in the context.\n\nInput validation:\n- Is the email text legible and complete?\n- If it is too short (under 20 words), ask for more context.\n- If attachments are mentioned but not present, mark this as \"Attachment missing, qualification carries a caveat\".", "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-plus", "recommended": [ { "slug": "angebots-pruefer", "category": "assistent", "name": "The Quote Reviewer", "teaser": "Systematically checks quotes before they go out for completeness, arithmetic consistency and pricing logic, and returns a clear approval recommendation.", "domaene": "Vertrieb & Outreach", "itemIcon": "file-badge" }, { "slug": "kundentermin-protokoll", "category": "skill", "name": "The Client Meeting Protocol", "teaser": "Turns notes or a transcript from a client meeting into a structured protocol with a BANT or MEDDIC opportunity analysis, action items, and a follow-up email draft.", "domaene": "Vertrieb & Outreach", "itemIcon": "notebook-pen" }, { "slug": "pipeline-protokoll", "category": "skill", "name": "The Pipeline Protocol", "teaser": "Systematically checks your CRM pipeline, flags deals that need action, and delivers a compact report with metrics and prioritized next steps.", "domaene": "Vertrieb & Outreach", "itemIcon": "git-branch" }, { "slug": "qbr-dossier", "category": "skill", "name": "The QBR Dossier", "teaser": "Creates a structured Quarterly Business Review for existing customers, from health score to a prioritized roadmap for the next quarter.", "domaene": "Vertrieb & Outreach", "itemIcon": "pie-chart" }, { "slug": "scoring-schema", "category": "skill", "name": "The Scoring Framework", "teaser": "Scores incoming leads against your ICP criteria, assigns a traceable score with a confidence rating, prioritizes them into Hot, Warm and Disqualified, and delivers first-outreach drafts for the top leads.", "domaene": "Vertrieb & Outreach", "itemIcon": "star" }, { "slug": "lead-staffel", "category": "workflow", "name": "The Lead Relay", "teaser": "Every new lead from a form is automatically scored on budget, need and timing and reaches the right salesperson within minutes, complete with a priority score and rationale.", "domaene": "Vertrieb & Outreach", "itemIcon": "user-plus" }, { "slug": "pipeline-schiene", "category": "workflow", "name": "The Pipeline Pulse", "teaser": "A weekly report that reads your open pipeline from the CRM and flags risks, opportunities and stagnating deals for the sales team.", "domaene": "Vertrieb & Outreach", "itemIcon": "git-branch" }, { "slug": "call-analyst", "category": "assistent", "name": "The Call Analyst", "teaser": "Turns call notes or a sales call transcript into a CRM-ready follow-up document with needs analysis, BANT assessment and a scheduled follow-up plan.", "domaene": "Vertrieb & Outreach", "itemIcon": "phone-call" }, { "slug": "einwand-drehbuch", "category": "skill", "name": "The Objection Playbook", "teaser": "Classifies a customer objection psychologically and delivers three ready-to-use response strategies with concrete phrasing instead of a generic stock answer.", "domaene": "Vertrieb & Outreach", "itemIcon": "shield-question" }, { "slug": "gong", "category": "tool", "name": "Gong", "teaser": "Gong is a revenue intelligence platform that records and analyzes sales calls with AI to power coaching, deal insights, and forecasting for enterprise sales teams.", "domaene": "Vertrieb & Outreach", "logoFile": "gong.svg", "logoEinzug": 0.78 } ] }