home / use cases / chat, leads and customer service / quote-request-intake

Quote requests collected, priced and drafted

A prospect asks for a quote in your site chat or by email; your Aivell collects the missing specs, looks up prices and stock in your own database, and assembles a draft quote — which waits for a human yes before anything reaches the customer. Price lists and margins are read onboard, never uploaded anywhere.

Watch the demo

starts when: A prospect asks for a quote — in the site chat or by email

The problem

A quote request is homework with a deadline. Someone reads the inquiry, notices half the measurements are missing, emails back, waits, looks up prices across a database and two spreadsheets, checks stock, formats a document — and does it fastest for the prospects who were probably buying anyway. Estimators at busy shops spend whole mornings on this; analysts reckon about 45% of professional-services work is automatable with what exists today, and quote assembly is squarely inside it.

The slow part is rarely the pricing — it is the collecting. Requests arrive incomplete, the ping-pong to complete them takes days, and every day of ping-pong is a day a competitor’s quote might land first.

How your Aivell does it

The intake, the lookup and the drafting run without you. The signature stays yours:

  1. The request comes in either door. A chat on your site or an email to sales — the same chore handles both, in the prospect’s language.
  2. The spec gets completed conversationally. Whatever the price list needs and the request lacks — dimensions, quantities, finishes — is asked for immediately, not discovered on day three.
  3. Prices come from your database, live. Unit prices and stock straight from your own system, read by the box. Standard items get list price; custom work gets the workshop rate — the chore’s rule, applied without exception.
  4. A draft assembles itself. One line per item, totals, validity — shaped like your quotes because your rules shaped it.
  5. Franca releases it. The draft lands in her inbox; big totals and any discount always stop there. Her approval — from her phone, if she likes — is what lets the quote leave the building.
  6. The sheet remembers everything. Every quote, every outcome, one row each — which sizes get requested, which quotes convert, where the €5,000 line should really sit.

Guardrails carry the weight: the database is read-only, and customer-bound mail is locked behind approval. What is left in the chore is your pricing policy in plain sentences — which is exactly where a pricing policy should live.

The chore, as you'd write it.

No flowcharts, no code — a chore is just a message to your Aivell, in your own words. It shapes it into a solid, guarded procedure and follows it to the letter. This one:

Giulia Aivell · draft quotes for approval ● active

a quote request arrives by chat or email — greet, then get the specs

missing measurements or quantities? keep asking until the list is complete

look up unit prices and stock in the price database

standard items at list price; custom work gets the workshop hourly rate

over €5,000, or any discount at all — draft only, wait for Franca

build the draft — one line per item, totals, valid 30 days

send it to Franca for approval; her yes releases it to the customer

log each quote and what became of it in the quotes sheet

You
Got it — I'll start right away, and check with you whenever something needs a human.
Giulia Aivell

The tools it uses.

Connected with single-click passkeys — no copied tokens, no OAuth hell.

Chat widget collects specs, conversationally
Email takes emailed requests, sends approved quotes
Database unit prices and stock, straight from your system
Spreadsheets logs every quote and its outcome

Sensible guardrails.

Every tool can be limited to exactly what this chore needs. For this one, you might set:

Database Read-only on the price and stock tables. This chore cannot write to the database at all.
Email Draft quotes go to Franca only. Mail to the customer is released solely after her approval.

Questions, answered.

Can a quote go out to a customer without anyone seeing it? +

No — and not as a policy, as a mechanism. The chore pauses at the draft, and the Email guardrail physically blocks customer-bound mail until Franca approves, which she can do from her phone. The Aivell does the assembling; the committing stays human.

What if the prospect's request is vague — "roughly twenty meters of shelving"? +

Then the conversation continues until it isn't. Depth, material, wall or free-standing, delivery or pickup — the Aivell asks for what the price list needs, the way your estimator would, and only starts drafting when the spec list is complete.

Does my price list end up on some AI company's servers? +

No. Prices, stock levels and the margins they imply are read from your database by the box in your office, and the drafting happens onboard. Competitors' favorite spreadsheet — your pricing — never transits a cloud service.

Where do the pricing rules live — hourly rates, minimums, surcharges? +

In the chore, as sentences anyone can read. List price for catalog items, workshop rate for custom work, no discounts without Franca. When your rates change, you edit the line and the next quote follows the new rule.

Related.

What is an Aivell?

An Aivell is an on-premise AI colleague: a small box that plugs into your network, runs its own AI onboard and takes the repetitive work off your desk. Prompts, documents, data — nothing ever leaves your office. Unplug the internet: it keeps working.

You describe each task as a chore, in plain language. Your Aivell turns it into a solid, guarded procedure and runs it in the background — with guardrails on every tool, a complete audit trail, and approvals in your hand when you want them. One-time setup, fixed monthly fee. No tokens, no overages.

Watch the demo

onboard inference · air-gapped · fixed monthly fee