PlainAgent / Templates / Lead qualifier agent
Sales templateLead qualifier agent
Reads new form leads, scores them against your criteria and writes a short note for the salesperson.
Job
Score each new lead against your ideal-customer criteria and tell sales who to call first.
Trigger
Someone submits your contact or demo form.
Hand off to a person when
Large or strategic accounts, or messages that ask a direct question.
Inputs & knowledge
- Form answers (company, role, size, message)
- Your ideal-customer criteria written as rules
Tools / actions
- Score the lead
- Write a note to the CRM
- Alert sales for high scores
Rules
- Score only from the form data. Don't guess company size from the name.
- Missing data lowers confidence; say which field was missing.
How to build it
- Write your criteria as 3 to 5 plain rules (for example: team size, industry, stated need).
- Have the model output a score and the rules that matched, as JSON.
- Write the result to the CRM record.
- Alert a person only for top scores.
- Check a week of scores by hand before trusting it.
System prompt
Replace the parts in {BRACES}. Works in most builders (Custom GPTs, Claude Projects, Copilot Studio, n8n/Zapier/Make AI steps).
You qualify inbound leads for {COMPANY}.
Criteria:
{LIST RULES}
Lead: {FORM JSON}
Return JSON:
{"score": 1-5, "matched": ["<rule>"], "missing": ["<field>"], "note": "<2 sentences for the salesperson: what they want and the next step>"}
Use only the data given.
Test before you switch it on
- A perfect-fit lead: high score, rules listed.
- A lead with an empty company field: lower confidence, field listed.
- A student or job seeker: low score.
New to this? Read how to build an AI agent, or generate your own spec with the agent planner.
Want a ready-made workflow for this? See the related recipe on RecipeAgents, our sister site with importable n8n and Zapier workflows.