As of 13 August 2026, AI can compare leads with your ideal customer profile.
Most people should hand this to a purpose-built tool.
Can you do it?
5 minutesto a draft.
30 minutesto something you’d act on.
Cost, all in£0
Skill neededchat-fluent
Who has to check ityou
What the alternative costsThe supplied tool data gives no price for a comparable alternative, so no pounds figure is stated.
If this goes wrong: good prospects are discarded or poor-fit leads consume sales time, and the error may remain hidden in the ranking.
What to actually do
Use a tool built for this
The route this page recommends
Do it yourself
Second choiceA chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.
How to actually do it
- Open your current ideal customer profile, sales qualification rules and any documented exclusions, then paste the relevant criteria into the prompt.
- Export or copy the leads you are allowed to use from your CRM, spreadsheet or lead form, including a stable lead ID and the fields that support qualification.
- Remove unnecessary personal data and confirm that you have permission to process the remaining lead information in the AI tool you are using.
- Paste the profile, qualification rules and lead table into the prompt, then ask the model to produce the comparison table and unknown fields.
- Compare every stated criterion and supporting quote in the output against the original profile and lead record, correcting any misread field or invented inference.
- Test the result on a few leads whose fit you already know, then revise ambiguous rules in the profile before applying the method to the full list.
- Send only the qualified leads that pass your own review into the next sales action, and record the evidence and unanswered question in your CRM.
Prompt
Compare the leads below with the ideal customer profile and return a practical qualification table. Use only the information provided. Do not invent missing facts, infer sensitive personal characteristics, or treat unknown information as a negative signal. Ideal customer profile: [Paste the profile, including target sector, organisation size, location, role, problem, budget or buying signal, and exclusions.] Qualification rules: [Paste the rules, including which criteria are essential, preferred or disqualifying.] Lead data: [Paste a table or list of leads with a lead ID and the available fields.] For each lead, provide: 1. Fit rating: strong fit, possible fit or insufficient evidence. 2. Criteria met, with the exact supporting field or quote. 3. Criteria not met or still unknown, clearly separated. 4. A short reason for the rating. 5. The single best next qualification question. 6. A confidence label based on how complete and reliable the supplied data is. Do not rank a lead above another unless the supplied evidence supports the difference. Preserve the lead ID. Flag any rule that is ambiguous or conflicts with another rule. Finish with a list of assumptions and a list of fields that would most improve the comparison.
Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.
Hand it to a person
The distant thirdA person who owns the outcome does this end to end, worth it when the failure is dear.
What it gets wrong
- AI cannot decide whether an ambiguous business need is genuinely important to the buyer.
- AI cannot access private CRM, email or enrichment data unless you provide authorised access or paste the relevant information.
- AI can overvalue polished wording, incomplete firmographic data or explicit buying signals while missing context held by the account owner.
- AI cannot take responsibility for excluding a lead, contacting a person, or applying a qualification rule unfairly.
- AI cannot replace a clear qualification policy when your ideal customer profile contains subjective terms such as good fit or strategic account.
Even on a YES, the friction has a name: judgement under ambiguity, private data access and stakes of error.
How we scored this
Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.
| Axis | Score (0–2) |
|---|---|
| Output | 2 |
| Inputs | 2 |
| Verification | 1 |
| Liability | 1 |
| Effort delta | 2 |
| Total | 8 / 10 |
The methodology and its thresholds are published in full.
FAQ
- Can ChatGPT qualify leads against my ideal customer profile?
- Yes. Give it the profile, explicit qualification rules and lead records, and it can compare the evidence, separate unknowns from failures and suggest the next question. Check the source fields and keep the final qualification decision with the responsible salesperson.
- Can AI score leads from a spreadsheet?
- Yes, if the spreadsheet contains the fields needed by your profile and you are authorised to use the data. Ask the model to preserve each lead ID, cite the supporting field and mark missing information as unknown rather than treating it as a poor fit.
- How accurate is AI lead qualification?
- There is no single accuracy figure for this task because the result depends on your criteria, data quality and how much judgement the profile requires. AI is easier to trust when each rating points to source evidence and a person checks borderline cases.
- Should I let AI reject leads automatically?
- Not without a tested rule set and an audit trail. Use AI to identify likely fit and missing evidence, then have a salesperson check exclusions and borderline leads before automated rejection or outreach.
Nearby answers
Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.
The newsletter
AI news, new answers and product picks, straight to your inbox.