Fixed quote after a free call

An AI beauty advisor that recommends from your own shade data

Shoppers ask the same questions a counter advisor would: which shade, which order to use products, is this fragrance-free, will it work with my routine. We build an AI beauty advisor for your site and chat that answers from your approved shade maps, INCI lists and routine guides, asks simple questions to narrow down shades, tells shoppers it is an AI and hands skin concerns, reactions and complaints to a person. Projects typically cost $2,500 to $7,500 and take five to eight weeks.

The problem

Why beauty shoppers need a virtual beauty advisor that stays on facts

Online beauty shopping loses the counter advisor. Shade uncertainty drives returns and abandoned carts, and ingredient questions from shoppers with sensitivities land in the support inbox, where answers vary by who replies.

A generic chatbot is risky in beauty. It might invent a shade match, call a product hypoallergenic when you have not claimed that, or respond to "my skin is burning" with a product tip. The advisor must be narrow: your data, your approved claims and a fast hand-off for anything about skin health.

What we build

What our AI shade finder and advisor include

Shade finder

A short question flow (current shade in other brands, undertone, coverage) mapped to your own shade data.

Routine builder

Product order and pairing suggestions from routine guides your team wrote.

Ingredient answers

Answers from your approved INCI lists and free-from statements only, quoting the list.

Order and returns help

Order status and shade exchange policy for verified customers.

Skin concern hand-off

Mentions of reactions, burning, rashes or medical conditions go straight to your safety inbox with a calm message.

Disclosure and review

Clear AI disclosure and a weekly list of questions it could not answer.

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

    Shopper asks

    A shopper asks about shades, ingredients or routines.

  2. 02 Automated

    Facts retrieved

    The advisor pulls matching shade data, INCI lists and guides.

  3. 03 Automated

    Recommendation given

    It recommends from your data and links the product page.

  4. 04 Team review

    Team reviews

    Customer care reviews handed-off chats and unanswered questions.

  5. 05 Founder or regulatory lead decides

    Claims and safety

    Product claims and anything about skin reactions are decided by the regulatory lead or safety contact.

How it behaves

How the AI beauty consultant behaves

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

What the shopper sees

  • A clear note that the advisor is an AI
  • A shade suggestion from a few simple questions
  • Ingredient answers quoting the INCI list
  • A person whenever they mention a skin problem

What the team sees

  • Skin concern chats flagged straight away
  • A weekly list of unanswered questions
  • Shade queries by product to guide launches

What the automation does

  • Retrieves approved shade and ingredient data
  • Refuses claims and skin advice
  • Logs every conversation

Edge cases and fallbacks

Shopper names a competitor shade not in your map
The advisor asks more questions or offers a sample route rather than guessing.
Question about pregnancy or a medical condition
No advice; the shopper is directed to their doctor and your team is notified.
Prompt injection or abuse
Ignored, chat closed politely and logged.
AI provider outage
The widget falls back to the static shade guide and a contact form.

Architecture

An AI beauty advisor for a brand site at a glance.

The setup we usually start from. We adapt it to the phone system and practice software you already use.
Shopper Chat or quiz Advisor service n8n or Laravel Language model Claude, Gemini, GPT Shade maps Your own data INCI and claims Approved only Recommendation With product link Care and safety Skin concerns Transcripts Weekly review
  • Input
  • Logic and services
  • AI step
  • Data
  • Output
  • People

How it flows

  1. 1 A shopper starts a chat or the shade quiz and is told the advisor is an AI.
  2. 2 The service retrieves your shade maps, INCI lists, claims and routine guides.
  3. 3 The model recommends from those facts only and links the product page.
  4. 4 Skin concerns and complaints go to people, and every chat is logged for review.

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 beauty advisor & shade finder project plan

Typical time to launch: about 6 weeks, then support

  1. 01

    Discovery

    About 1 week

    Real customer questions, shade data, approved claims and what the advisor must never answer.

  2. 02

    Data and guides

    About 1 week

    Shade maps cleaned, routine guides and ingredient answers approved.

  3. 03

    Build

    About 2 weeks

    Advisor service, shade flow, retrieval, chat widget, hand-off and logging.

  4. 04

    Test

    1 to 2 weeks

    Real, tricky and safety prompts tested; the team signs off.

  5. 05

    Launch

    2 to 3 days

    Soft launch on one product range, then widen.

  6. 06

    Support

    Ongoing

    Weekly transcript review at first, then updates with each launch.

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 Shopify Storefront or Admin API Your master product record (PIM or sheet) Website chat widget Gorgias or Zendesk for hand-off

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 data preparation

    Question analysis, shade maps and approved answers.

    $500 – $1,200

  • Build

    Advisor service, shade flow, retrieval, chat and hand-off.

    $1,200 – $4,000

  • Integrations

    Store, product record, help desk and alerts.

    $300 – $1,000

  • Testing and evaluation set

    Real, tricky and safety prompts tested.

    $300 – $900

  • Launch and training

    Soft launch and transcript review.

    $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. Photo-based shade analysis is out of scope by default and quoted separately after a privacy review. Model usage and hosting are billed to you 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; scales with chat volume.
  • 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: AI disclosure

Article 50 of the EU AI Act requires AI systems that interact with people to inform them they are dealing with AI, from 2 August 2026. We disclose in every market.

Source: artificialintelligenceact.eu

No claims beyond your approved list

The advisor quotes only approved claims; advertising must not imply characteristics a product lacks under Article 20 of Regulation 1223/2009.

Source: eur-lex.europa.eu

EU and UK: skin information can be health data

Descriptions of skin conditions may be special category data under Article 9 GDPR, so the advisor collects as little as possible and hands those chats to people.

Source: gdpr-info.eu

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 beauty advisor & shade finder questions, answered.

An AI beauty advisor is a chat assistant that helps shoppers choose shades and products and answers routine questions, the way a counter advisor would. Ours answers only from your own product data and approved claims.

It asks a few questions (shades worn in other brands, undertone, coverage and finish) and maps the answers to your shade data. We do not analyse face photos by default; that needs a separate privacy review.

Yes, from your approved INCI lists and free-from statements. It quotes the list and never says whether an ingredient is safe for a person's skin; those questions go to your team.

The advisor stops recommending, shows a calm message with your contact route and sends the conversation to your safety inbox immediately.

It is a narrow AI agent: it can look up shades, ingredients and orders and recommend products, but it cannot make new claims or give skin advice.

Shade quiz completion, add-to-cart from recommendations, shade-related returns, chats handed to people and questions it could not answer.

Free 20-minute call

Want this for your beauty & cosmetic?

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