iSolvoltar ao site

CASE STUDY

Case study: a pre-sales agent that quotes with dollar precision

August 2026 · 5 min read · client name under NDA, numbers real

The business problem

A US construction and remodeling company lived a classic funnel problem: leads write at night, sales answers in the morning, and the first quote draft ate senior time on every single lead, qualified or not. The pricing truth lived in a spreadsheet only two people really knew how to drive.

The architecture

The extraction, live

A realistic lead message, processed today against the live gateway. Note what it does not do: it does not guess a price, it lists what is missing and asks exactly one good next question:

Real pre-sales extraction: structured scope, missing info list and one follow-up question
Real call, captured 2026-08-19. Extraction as JSON, gaps made explicit, and a next question that moves the deal forward.
Real extraction run: the lead's message becomes a structured request, with the list of what is missing and the next question. 7.5s measured.

Results in production

What made it work

Replicate the pattern

Put the agent on your site with the website chatbot guide and keep pricing in your own engine. The extraction prompt above is reusable as-is.

Ready to try it? Your key lives in the customer portal, isollm.ai/account → API keys. The endpoint is https://tokens.4clouders.com/v1. Prefer the outcome delivered instead of building it: that is exactly what iSol Squad is.

See plans →