Operations

Lead Qualification Categories for AI Scoring

Qualified, Nurture, Unqualified — a three-label pipeline gate with numeric confidence and a Strict Other for the leads that fit nothing.

Open in Data Classification Prompt

Overview

Lead qualification is a classification problem wearing a scoring costume: the decision is which pipeline lane, not which number. This setup classifies leads into three lanes whose definitions encode the criteria — Qualified requires budget, authority, need, and timeline signals; Nurture is genuine interest without readiness; Unqualified is no realistic path — under Strict ambiguity with a 0–100 confidence score. The score bands are defined in the prompt (90+ unambiguous, 60–89 good fit, below 60 best available), so downstream automation can threshold them meaningfully.

How to use this resource

Extract first, classify second

Run the lead text through extraction for the fields, then through this for the lane — two prompts, two clean jobs.
Encode your criteria in the definitions

The Qualified definition IS your qualification bar — tighten or loosen the signals there, not in extra rules.
Threshold the score, don't average it

Confidence is self-reported per lead: great for routing thresholds, meaningless as a portfolio average.

Why This Works

Three exclusive lanes with criteria-bearing definitions beat a 0–100 "score" nobody can audit
Strict mode keeps junk leads from inflating the Qualified lane
Defined score bands make the confidence number actionable instead of decorative

Best for

Sales ops feeding a pipeline from inbound forms and emails
Teams whose reps disagree about what "qualified" means
Automations that act differently above and below a confidence bar

Not for

Extracting the lead's details (name, company, team size) — extraction runs first, this runs second
Predicting deal size or close probability — that's modeling, not labeling

Use cases

Gating CRM entries into sales-ready and nurture lanes
Applying BANT-style criteria consistently across hundreds of leads
Thresholding numeric confidence for automation rules

FAQ

How do I make the AI stricter about what counts as a Qualified lead?

Tighten the Qualified definition itself, not the rules around it. In the LABELS block, Qualified requires budget, authority, need, and timeline signals present; sharpen those signals (for example require an explicit budget or a named decision-maker) so borderline leads fall to Nurture. The data-classification-prompt tool regenerates the label criteria; you still run the result in your own assistant.

Where does the label and confidence JSON go after the AI returns it?

Into your own CRM or routing automation, which you build. The prompt returns a single JSON object with a label key and a confidence key (like {"label": "Qualified", "confidence": 92}) and no markdown fences, so your code can parse it and route by threshold. NewPrompt does not run the assistant or push anything into a pipeline for you.

Is the confidence score a real probability I can average across all my leads?

It is self-reported by the model, not computed, so the CONFIDENCE section states the score reflects the model's own certainty about the fit. Use the bands (90+ unambiguous, 60-89 good fit, below 60 best available) as per-lead routing thresholds; averaging them into a portfolio number is meaningless, and a human owns any consequential routing decision.

Can this predict deal size or close probability for a lead?

It only assigns a pipeline lane, not a forecast. The labels are Qualified, Nurture, Unqualified, and Other, and each returns the fit confidence, not an expected revenue or win rate. Deal-size and close-probability are modeling problems, not labeling; run extraction first for the lead details, then this for the lane, in your own assistant.

Customize This Resource

Opens this setup in Data Classification Prompt. Generate to get the full classification prompt — then adjust the labels, ambiguity mode, and confidence output.

Open in Data Classification Prompt

Prompt Template

Copy it as-is, or use Open in Data Classification Prompt to load it pre-filled and customize it with your own context.

TASK
Classify inbound leads by qualification stage for the sales pipeline.
Assign exactly one of the labels defined below to the text in the input.

LABELS
- Qualified: Budget, authority, need, and timeline signals are present — ready for sales.
- Nurture: Genuine interest and potential fit, but not ready to buy now.
- Unqualified: Clearly outside the target profile — no realistic path to a sale.
- Other: Does not clearly fit any label above.

CLASSIFICATION RULES
- Read the entire text before deciding — the deciding signal may come late.
- Judge by content and intent, not by tone, length, or formatting.
- Match the text against the definitions, not just the label names.
- Use only the labels defined above, plus "Other" when nothing fits — never invent any other label.

EDGE CASE RULES
- If the text fits more than one label, choose the one matching its primary purpose — what the writer mainly wants.
- If two labels fit equally, prefer the more specific definition over the more general one.

AMBIGUITY POLICY
- If no label clearly fits, return exactly "Other" — do not force a fit.
- "Other" is a valid answer; a forced wrong label is not.

CONFIDENCE
- With each label, report a confidence score from 0 to 100.
- 90 or above = unambiguous fit; 60–89 = good fit with some uncertainty; below 60 = best available choice.
- The score reflects your certainty about the fit — it is self-reported, not computed.

OUTPUT FORMAT
Return your classification as a single valid JSON object with a "label" key and a "confidence" key.

EXAMPLE OF A VALID RESPONSE
{
  "label": "Qualified",
  "confidence": 92
}

OUTPUT RULES
- Return only the JSON object — no text before or after it.
- Do not wrap the output in markdown code fences.
- Return the label text exactly as defined above — no paraphrasing, no abbreviations, no new labels.

More resources from Data Classification Prompt

Resource

Classify Support Tickets with AI

Billing, Technical, Account, How-To, Feature Request — ticket triage with definitions that decide the borderline cases for the model.

Support

Resource

Text Classification Prompt — the Anatomy

The blocks a reliable classification prompt needs: defined labels, classification rules, edge-case rules, an ambiguity policy, and a confidence contract.

Prompt Engineering

Resource

Categorize Customer Feedback with AI

Praise, Complaint, Feature Request, Bug Report, Question — multi-label feedback categorization where one message can carry three signals.

Product

Resources that pair well

Resource

Extract Data From Text with AI

Free text in, named fields out. The extraction prompt pattern that turns any unstructured text into consistent, parseable records.

Prompt Engineering

Resource

Force JSON Output from AI

Stop getting 'Sure, here is the JSON…' — the output-contract pattern that forces models to return only parseable JSON: schema, example, and a strict rule block.

Prompt Engineering

Resource

Fix Invalid JSON from AI

The JSON won't parse and you can't see why. Deterministic cause-sniffing — trailing commas, single quotes, unclosed brackets — and the repair prompt that fixes it.

Engineering

Related tools

Tool

Data Classification Prompt

Build classification prompts that assign labels from a closed set — with label definitions and edge-case rules.

Structured Output

Tip: Save time by exploring related resources and tools that integrate with this resource.