We won the Open Agentic AI Innovation Award at the first AAIF Technical Excellence Awards.We won the Open Agentic AI Innovation Award Read why

AI quote generation with your price rules in code

Quotes drafted by agents, priced by your rules

For an engraved die manufacturer, pricing went from about 30 minutes to a few clicks, and the price rules stayed in tested code.

Book a free consultation How we build agents
quote-desk

  1. Sales engineerYour team

    A customer sent a drawing for a custom part and wants a quote today. Can the quote agent take it?

  2. Quote agentAgent

    1. inbox.read request and drawing
    2. vision.measure dimensions from the drawing
    3. crm.get_account past orders and discount
    4. pricing.apply_rules material, volume, discount

    Draft quote ready. The discount on this account has expired, so the price needs your sign-off.

    Needs a personExpired account discountDraft quote for a custom part
    Approved by Sales manager

  3. Quote agentAgent

    1. crm.log_quote quote, inputs and approval

    Quote sent from the sales engineer's mailbox and logged with every input behind the price.

Example data. An agent at work in a team channel, with a person approving the step you choose.
Mixam: conversion to a final sale from about 20% to about 40%
Where agents help

Quotes queue behind the one person who knows pricing.

Agents prepare each quote from your rules and data, and your team signs off the exceptions.

  1. 01

    Where it stallsPricing knowledge lives in a few people's heads.

    What we do Price lists, discounts and margins move into tested code that every quote runs through.

  2. 02

    Where it stallsEvery quote means re-reading drawings and history.

    What we do An agent reads the request and drawings and pulls customer history and discounts from your CRM.

  3. 03

    Where it stallsSlow quotes lose deals to faster suppliers.

    What we do Agents draft quotes as requests arrive. A person approves only the ones outside your rules.

What we build

What we build for quoting

Whatever comes in, every project is built from the same parts below, set up for your files and your systems.

Quotes we prepare

  • Configured products
  • Custom manufacturing
  • Print and packaging
  • Services and projects
  • Logistics and freight
  • Insurance quotes
  • Wholesale price lists
  • Renewals and upsells

How we build it

  • Quote agents that read the request

    They read emails, drawings and specs, ask for missing details and fill the quote.

  • Price rules as tested code

    Price lists, discounts and approval limits written as code, so every quote adds up.

  • CRM, ERP and drawing connections

    Customer history, stock and drawings read live, with the access you set.

  • Quote logs and monitoring

    Every quote logged with its inputs, and failures flagged in your team chat.

Not seeing your case? Bring the quote type your team rebuilds by hand and we start from that.

Tell us about your workflow
How we build agents

Agents that work as part of your team

They work in the tools your team already uses, take on whole tasks and stop for a person where you decide.

  1. Routines: agents that start on a schedule, on new GitHub issues or on an API delivery.
  2. Connected systems: GitHub, Linear, Notion, Slack, Jira and other tools an agent may call, each connected with its own sign-in.
  3. Approvals log: each action that waited for a person, with who asked, who decided and when.
Routines: agents that start on a schedule, on new GitHub issues or on an API delivery.
Connected systems: GitHub, Linear, Notion, Slack, Jira and other tools an agent may call, each connected with its own sign-in.
Approvals log: each action that waited for a person, with who asked, who decided and when.

Screens from the workspace our agents run in, with example data.

Where it runs

Teams and industries that use it

Each page shows where agents fit in that team or industry.

Engineering in the open

We help build what agentic AI runs on

Open standards, open-source tooling and published research, all public, so you can check our engineering before you hire us.

Shaping agentic AI

Agentic AI Foundation

Vstorm was the first agentic AI engineering company to join the Agentic AI Foundation and received its 2026 Open Agentic AI Innovation Award.

Read the announcement

Open source

We build open-source agent tooling that other engineering teams install

10M+ PyPI downloads
4,000+ GitHub stars
33 public repositories

Framework contributors

When the framework breaks, we fix it at the source

We maintain our own open-source agent framework and contribute fixes to the frameworks our agents run on, through official partnerships with their teams. Breaking changes reach us before they reach your codebase.

Research

Our engineers and PhDs publish peer-reviewed research

Peer-reviewed papers on agent architectures, evaluation and AI security, and an open benchmark anyone can rerun against our results.

Track record

Frontier AI teams now build on what we shipped first

Our client agents were in production before most of today's agent frameworks had a stable release. You get a team that already knows what breaks between a promising demo and a system people rely on every day.

Case studies
All case studies
Engagement models

Ways to start

Each path starts with a free call with a founder or senior AI engineer. A build goes ahead only after its Proof of Value meets the agreed threshold.

Start with one workflow

We map one workflow with your experts and agree a success threshold before any build.

Best whenYou want the success test agreed before you commit to a build.

Book a free consultation
  1. Process redesign and build Best whenYou want one team accountable for the outcome.
FAQ

AI quote generation, answered

What is AI quote generation? +
AI quote generation uses an agent to turn a customer request into a priced quote. The agent reads the email, specification or drawing, matches products and options, pulls the customer's history and discounts, and passes everything to your price rules in code. The result is a draft quote that a rep sends, or one that goes out on its own within limits you set.
Can AI automate quotes for custom or configured products? +
Yes. That is where it saves the most time, because custom work needs reading: drawings, materials, volumes and the customer's past terms. An agent does that reading and a pricing engine in code does the maths. Start with one product family, test the agent on quotes your team has already priced and compare the results line by line.
Have you built AI quote generation before? +
Yes. For one of the largest engraved die manufacturers we built image-based pricing connected to a 20-year customer database. Pricing went from about 30 minutes to a few clicks, and time of work fell 72% across pricing and database operations. For Mixam we built an agent that turns a buyer's intent into an order specification Mixam can actually print.
How do you keep AI-generated quotes accurate? +
The agent reads the request and picks the options. Your price lists, discounts and approval limits run as tested code, so the agent never sets a price itself. Quotes outside your rules wait for a person. Every quote is logged with its inputs, and negative feedback from your team is stored and posted to your team chat, so errors surface quickly.
How do you know it works before the full build? +
We agree a success threshold with your team before the build and test the agent on your own cases in a Proof of Value. It measures accuracy and running costs, and the build goes ahead only when the threshold is met. Corrections from your team go back into the test set, so every later version is checked against them.
Who owns the system, and which models does it run on? +
You own the code, prompts, evaluation sets and rules by contract. The agents run in your environment on hosted or open-weight models. The model sits behind an interface in code, so you can change it when accuracy, speed or your hosting rules change, without rebuilding the agent.
Start with one workflow

Test one workflow on your own data

A Proof of Value shows accuracy and running costs before the full build.

Book a free consultationRead case studies