Keep your agent. Add quoting intelligence.
Your chatbot can have the conversation. QuoteKernel understands the request, asks the right questions, estimates the work within your pricing rules, and knows when a quote is ready. Connect it yourself through MCP or API, or have your agency or developer do it. No new chatbot required.
Example at right: a wedding photography quote. Amounts and rules are illustrative.
{
"tool": "start_estimate",
"arguments": {
"service": "wedding_photography",
"request": "We're getting married in Tampa. About six hours, and we love a cinematic editorial look."
}
}{
"estimate_id": "est_example_002",
"status": "questions",
"understood": {
"event_location": "Tampa, FL",
"event_hours": 6,
"style": "editorial"
},
"questions": [
{
"id": "guest_count",
"ask": "About how many guests are you expecting?"
}
]
}{
"tool": "submit_answers",
"arguments": {
"estimate_id": "est_example_002",
"answers": { "guest_count": "About 275." }
}
}{
"status": "questions",
"understood": { "guest_count": 275 },
"estimate_range": { "low_cents": 360000, "high_cents": 430000 },
"confidence": "medium",
"questions": [
{
"id": "second_photographer",
"ask": "For 275 guests we include a second photographer. Is that okay?"
}
]
}{
"tool": "submit_answers",
"arguments": {
"estimate_id": "est_example_002",
"answers": { "second_photographer": "Yes." }
}
}{
"status": "ready",
"understood": { "second_photographer": true }
}{
"tool": "get_estimate",
"arguments": { "estimate_id": "est_example_002" }
}{
"status": "ready",
"display_text": "Based on what you've told me, six hours of editorial wedding photography in Tampa with a second photographer comes to $3,960. This is an estimate, not a binding quote. Reference: Q-4M8P.",
"amount_cents": 396000,
"breakdown": [
{ "label": "Editorial wedding coverage, 6 hours", "amount_cents": 288000 },
{ "label": "Second photographer, 6 hours", "amount_cents": 108000 }
],
"priced_on": {
"event_hours": 6,
"event_location": "Tampa, FL",
"style": "editorial",
"guest_count": 275,
"second_photographer": true
},
"valid_for_days": 30,
"quote_reference": "Q-4M8P"
}Your customer talks to your agent. QuoteKernel decides what comes next.
Behind every reply, your agent passes the customer's words to QuoteKernel. QuoteKernel works out what they mean, applies your rules, and hands back the next question or the quote. The customer only ever sees a natural conversation.
- Customer "We're getting married in Tampa. About six hours, and we love a cinematic editorial look."
- Your agent, behind the scenes Passes the customer's words on QuoteKernel Reads it as six hours of coverage in Tampa, editorial style. Missing: guest count. Returns the next question.
- Your agent, to the customer "About how many guests are you expecting?"
- Customer "About 275."
- Your agent, behind the scenes Passes the answer on QuoteKernel Rule: 250+ guests needs a second photographer. Estimates $3,600–$4,300, medium confidence. Confirm coverage before pricing.
- Your agent, to the customer "For 275 guests we include a second photographer. Is that okay?"
- Customer "Yes."
- Your agent, behind the scenes Passes the answer on QuoteKernel Inputs confirmed, rules satisfied. Returns a firm estimate and a sentence to relay word for word.
- Your agent, to the customer "Based on what you've told me, six hours of editorial wedding photography in Tampa with a second photographer comes to $3,960. This is an estimate, not a binding quote. Reference: Q‑4M8P."
The guest-count rule, second-photographer threshold and amounts are examples, not a real business's policy.
A fluent chatbot is not a pricing system.
A conversational agent can sound confident while missing an essential input, misapplying a discount, or inventing a price. Your business needs more than a good answer. It needs a controlled quoting process.
Hybrid AI reasoning for dependable quoting.
QuoteKernel is a hybrid domain reasoning engine. AI reasoning handles the judgment, estimating the work and recommending what fits, and your rules and policy set the boundaries it works inside.
-
Calling agent
Chatbot, voice agent or workflow
-
QuoteKernel
Hybrid domain reasoning engine
- Probabilistic AI Interprets the request, estimates the work from similar past jobs, recommends packages and judges confidence.
- Deterministic logic Exact calculations, hard constraints, minimum margins, eligibility and approvals.
- Domain intelligence Industry knowledge, business expertise, historical patterns and context.
- Governance Validation, evaluation, confidence calibration, escalation and auditability.
-
Structured, evaluated decision
Quote, missing inputs, next question, estimate range, recommendation, or human review
AI reasoning reads what the customer means and picks the most useful next question; your required questions adapt as new facts arrive. A guest count can add a question the agent never knew to ask.
AI reasoning estimates the work from similar past jobs and recommends a package. Your rates, packages, minimums and exceptions are calculated exactly, and the chat cannot talk the number down.
Return "needs more information", "invalid input", an estimate range, a recommendation with its confidence, "requires review" or "ready", or decline to quote, instead of guessing. Low confidence goes to a person.
From your pricing to your agent
- 01
Choose an industry model.
Start from questions and constraints that fit your kind of work.
- 02
Teach QuoteKernel your pricing.
Your services, rates, packages, minimums and the jobs you will not price.
- 03
Test it against realistic jobs.
Run jobs you already know the price of and check the result.
- 04
Connect your existing agent.
Over MCP or API, yourself or through your agency or developer. Your agent keeps the conversation.
Start from an industry model, then make it yours with your own services, prices and questions.
Your agent already knows how to talk.
Give it the intelligence to quote.