Fixed quote after a free call

An AI chatbot for manufacturers that sticks to your data

Customer service and inside sales answer the same questions daily: what material is this, what are the tolerances, is my order shipped, can you send the datasheet. We build an AI assistant for your website, customer portal or inbox that answers from your approved datasheets and catalogue, gives order status for verified customers from the ERP, captures RFQs with the right details and hands engineering and commercial questions to people. Projects typically cost $2,500 to $7,500 and take five to eight weeks.

The problem

What a manufacturing chatbot should and should not answer

Technical buyers want fast answers, often outside your working hours and across time zones. Most of their questions are already answered in datasheets, catalogues and the ERP, but finding the right page or order takes staff time.

An assistant for a manufacturer has to be stricter than a general chatbot. It must answer only from approved product data, never invent a tolerance or rating, show order data only to verified customers and send anything about suitability for an application to an engineer.

What we build

What our AI chatbot for manufacturing includes

Approved product library

Datasheets, catalogue pages and FAQs approved by engineering, and the only source the assistant answers from.

Spec answers with sources

Each answer cites the datasheet or page it came from, with a download link.

Order status for verified customers

Order and shipment status read from the ERP after the customer verifies with an order number and account email.

RFQ capture

Part, quantity, material, drawing upload and due date collected and sent to the RFQ workflow.

Engineering hand-off

Application suitability, custom work and anything not in the library go to engineering or sales.

Multilingual and disclosed

Answers in the buyer's language where you approve it, with a clear note that the assistant is automated.

Who does what

Automation does the chasing, people make the calls.

Every step is marked: what runs on its own, what a member of staff reviews and what stays with a person who decides.
  1. 01 Automated

    Question asked

    A buyer asks on the website, portal or inbox.

  2. 02 Automated

    Answer from approved data

    Product questions are answered from the library with the source linked.

  3. 03 Automated

    Order or RFQ

    Verified customers get order status; new requests are captured as RFQs.

  4. 04 Office review

    Staff follow up

    Inside sales replies to hand-offs and reviews unanswered questions.

  5. 05 Estimator or quality manager decides

    Engineering judgement

    Suitability for an application and any custom specification are decided by engineering.

How it behaves

How the AI product assistant behaves

What each person sees and what runs in the background, including what happens when something goes wrong.

What the buyer sees

  • A clear note that the assistant is automated
  • Answers with a link to the datasheet used
  • Order status after a quick verification
  • A person for anything about suitability or pricing

What staff see

  • RFQs captured with the right details
  • Hand-offs with the conversation so far
  • A weekly list of unanswered questions

What the automation does

  • Retrieves only approved product data
  • Verifies customers before order lookups
  • Logs every conversation

Edge cases and fallbacks

Question not covered by the library
The assistant says so and offers engineering or sales.
Buyer asks if a part suits their application
Handed to engineering; no answer is generated.
Order number does not match the email
No details shown; a person follows up.
AI provider outage
The widget falls back to a contact and RFQ form.
Abuse or spam
Conversation closed politely and logged.

Architecture

An AI product and order assistant at a glance.

The setup we usually start from. We adapt it to the phone system and practice software you already use.
Buyer Web, portal, email Assistant service n8n or Laravel Language model Claude, Gemini, GPT Product library Approved sheets ERP lookup Order status Answer or RFQ With source Sales, engineering Hand-offs Transcripts Weekly review
  • Input
  • Logic and services
  • AI step
  • Data
  • Output
  • People

How it flows

  1. 1 A buyer asks a question and is told the assistant is automated.
  2. 2 The assistant retrieves approved product pages, or order status after verification.
  3. 3 Answers cite their source; new requests are captured as RFQs.
  4. 4 Engineering and commercial questions go to people, and every conversation is logged.

Project planner

How the project runs, phase by phase.

Typical durations for a first version. Your proposal lists the exact phases, dates and what you sign off at each step.

AI product & order assistant project plan

Typical time to launch: about 6 weeks, then support

  1. 01

    Discovery

    About 1 week

    Real questions from inboxes and calls, product data sources and what the assistant must refuse.

  2. 02

    Product library

    About 1 week

    Collect and approve datasheets and FAQs with engineering.

  3. 03

    Build

    About 2 weeks

    Assistant, retrieval, ERP lookup, RFQ capture, hand-off and logging.

  4. 04

    Test

    1 to 2 weeks

    Real, tricky and out-of-scope questions; engineering signs off.

  5. 05

    Launch

    2 to 3 days

    Soft launch on product pages, then widen.

  6. 06

    Support

    Ongoing

    Weekly transcript review at first, then monthly library updates.

What it runs on

Real products only, connected through the access each vendor provides. See all integrations

Claude, Gemini or OpenAI models n8n AI Agent node or Laravel Your ERP API for order status Website chat widget SharePoint or Google Drive for the product library

Cost estimate

What it costs, line by line.

Estimates to plan with. Your fixed quote follows a free call, once we have seen your systems and volumes.
  • Discovery and product library

    Real questions, approved datasheets and refusal rules.

    $500 – $1,200

  • Build

    Assistant, retrieval, ERP lookup, RFQ capture and admin view.

    $1,200 – $4,000

  • Integrations

    ERP, document storage and RFQ workflow.

    $300 – $1,000

  • Testing and evaluation set

    Real, tricky and out-of-scope prompts before launch.

    $300 – $900

  • Launch and training

    Soft launch and team walkthrough.

    $200 – $400

  • Total project estimate

    $2,500 – $7,500

Optional monthly care after launch is quoted with your proposal. Fixed quote after a free call. Product-only assistants sit at the lower end; ERP order lookups add to the build. Model usage is billed to your account directly.

Monthly running costs you pay directly

Estimates from the vendors' published pricing, checked November 2026. Billed to you by each vendor, never marked up.

  • AI model usage: Billed by the provider per use; short answers cost little per conversation.
  • Hosting: n8n Cloud from about €20 a month, or your own server.

What pushes cost up

  • Systems without an API, or with integration access that must be requested from the vendor
  • Writing data back into your core system rather than only reading from it
  • Several locations, brands or very different processes to support
  • Custom apps, dashboards or a voice line on top of the workflows

What keeps cost down

  • One location and one clear process to start with
  • Cloud software with a documented API
  • Using tools you already pay for instead of adding new ones
  • Approved wording and sample data ready at the start
Get a fixed quote

Privacy and consent

Rules we design for, with the sources.

General information to plan with, not legal advice. Your counsel or data protection adviser confirms what applies to your practice.

EU: tell people they are talking to AI

Article 50 of the EU AI Act requires AI systems that interact with people to inform them they are interacting with an AI system, from 2 August 2026.

Source: artificialintelligenceact.eu

EU and UK: chat data

Names and emails collected in chat are personal data, so the privacy notice states purposes, legal basis, recipients and retention.

Source: gdpr-info.eu

No unapproved product claims

The assistant answers only from engineering-approved documents and refuses suitability questions, so it cannot create claims about conformity your documentation does not support.

How we deliver

Agile delivery, in 1 to 2 week sprints.

We deliver in short Agile sprints using Scrum, so you see working software every one or two weeks instead of waiting for a big reveal at the end.

Every sprint

  1. 1 Sprint planning. At the start of each sprint we agree which backlog items we will finish, each with written acceptance criteria you can check.
  2. 2 Daily stand-up. A short internal check-in on progress and blockers. You get a written update in your Slack or Teams channel, not another meeting.
  3. 3 Sprint review and demo. At the end of each sprint we demo what was built on test data or in a shadow run, and you accept it or ask for changes.
  4. 4 Retrospective. The team looks at what went well and what to change in the next sprint, and we share anything that affects you.

How scope stays under control

Product backlog
Every feature, fix and question in one prioritised list you can see at any time.
Acceptance criteria
Plain-language conditions for "done" on each item, agreed before work starts.
Change requests
New ideas go into the backlog with an estimate. Nothing changes scope or price without your written approval.
User acceptance testing (UAT)
Before launch your team tests the real workflow against the acceptance criteria and signs off.

Tools we use

Jira, ClickUp or Trello for the backlogSlack or Microsoft Teams for updatesGitHub for code and version historyLoom or a live call for demos

Project manager / Scrum master

Runs the sprints, keeps the backlog and timeline honest, and is your single point of contact.

Business analyst

Maps how the work runs today, writes the workflow specification and acceptance criteria with your team.

Automation engineer

Builds the n8n workflows, integrations, AI steps and error handling.

Backend developer

Writes custom code where a no-code step is not enough: APIs, data sync, secure storage.

Frontend / mobile developer

Builds forms, booking pages, dashboards, web apps or Android apps when the project needs them.

QA engineer

Tests every workflow against the acceptance criteria, including edge cases and failure paths.

DevOps engineer

Sets up hosting, access, backups, monitoring and alerts, and the deployment pipeline.

Who does what at each phase

Free call
Project manager, business analyst
Understand the problem, check it is worth automating and outline a rough range.
Discovery
Business analyst, automation engineer
Map the current process, systems and data, and agree success measures.
Design
Business analyst, automation engineer, backend developer
Write the workflow specification, data flows, compliance notes and backlog with acceptance criteria.
Sprints
Automation engineer, developers, QA
Build, test and demo in 1 to 2 week sprints; you accept or adjust after each demo.
UAT and launch
QA, DevOps, project manager
Your team tests and signs off, we switch on, monitor closely and train the team.
Support
Automation engineer, DevOps
Stabilisation window, then optional monthly care with monitoring and changes.

A point of contact

One person who can answer questions and approve decisions, with about an hour a week during the project.

Access

Admin or API access to the systems involved, created as separate accounts with the least access needed.

Sample data

Real but non-sensitive records (or de-identified ones) so we can design and test against reality.

Approved wording

Message templates, policies and consent wording (for SMS, your opt-in and opt-out text) reviewed by you.

Vendor agreements

Signed agreements with the software vendors that will handle personal data, such as a BAA or processor contract.

Time for testing

A few hours from the people who will use the system, for the demos and user acceptance testing.

Working system

Workflows, integrations and any apps running in your accounts, under your keys.

Documentation

Workflow specification, data-flow map, run book and exported workflow files.

Training

A walkthrough for the team and a short recorded video for new starters.

Handover

All access, credentials and code handed over; you can keep us or take it in-house.

Stabilisation window

Fixes for anything that does not meet the agreed acceptance criteria after launch.

Support options after launch

  • No plan

    You run it yourselves after the stabilisation window and contact us when you need a change.

  • Monthly care

    Monitoring, error alerts, small changes and updates each month, with an agreed response time.

  • Priority care

    Faster response times for business-critical workflows and a monthly review call.

How a project moves through our team

Free call PM and analyst Discovery Process and data Design Spec and backlog Sprints Build, test, demo Your review Accept or adjust UAT and launch Sign-off, go live Support Monitor and improve
  • Input
  • Logic and services
  • People
  • Output
  • Data

How it flows

  1. 1 A free call with the project manager and business analyst to understand the problem and whether it is worth building.
  2. 2 Discovery and design produce a written specification, data-flow map and a backlog with acceptance criteria.
  3. 3 The team builds in 1 to 2 week sprints; you review a demo at the end of each and accept or adjust.
  4. 4 Your team runs user acceptance testing, we launch, then monitor and improve under a support plan.

FAQ

AI product & order assistant questions, answered.

Product and specification questions from approved datasheets, order status for verified customers, lead-time policies and how to request a quote. It does not judge suitability for an application or quote prices.

The library only contains approved versions, and engineering updates it. Retired datasheets are removed, so the assistant cannot quote them.

Yes, where you approve it. Answers are generated from the same approved English sources, and you can review translations of key pages.

Order status is shown only after verification with an order number and account email, and tests include attempts with other customers' numbers.

If inside sales spends a large part of the day on repeat questions, often yes. A product-only assistant is the cheaper starting point.

Questions answered without a hand-off, RFQs captured, response time out of hours and questions missing from the library.

Free 20-minute call

Want this for your manufacturer?

Book a free 20-minute call. We will look at how the work runs today, tell you honestly whether it is worth building and give you a fixed quote if it is.

Book a free 20-minute call