Skip to content
Courses/AI Consultant: From Assessment to Production/Revenue, customers, and operating constraints

Revenue, customers, and operating constraints

An AI proposal can be technically sound and commercially wrong. The same delay means different things in a low-margin catalogue business, a high-value B2B sale, and an emergency service. Learn the economics and customer expectation before measuring automation.

Map the customer promise

Ask what the customer expects at each stage: a quick response, an accurate quote, a confirmed delivery date, a knowledgeable answer, or a human escalation. An AI workflow must protect that promise. Faster but less reliable is often a regression.

Northstar constraints

  • Prices and stock change, so a model cannot invent or autonomously confirm either.
  • Some quote requests include contact details and past order information, so assessment data must be minimised and access controlled.
  • Sales staff remain responsible for commercial promises, even if a system drafts a response.
  • The company has only one part-time CRM administrator, so any pilot must be simple to operate.

Constraint is a design input

A constraint is not a nuisance to work around later. It selects the solution. If stock is authoritative only in an ERP, a drafting assistant should cite the ERP record or abstain. If no reliable data exists, process work may be a better investment than an LLM.

Terminal
Opportunity constraint record
Customer promise at risk: _____________
Commercial authority: _________________
Authoritative system of record: ________
Personal or sensitive data: ____________
Human approval required: ______________
Operational constraint: ________________
Non-AI alternative: ___________________

Practical mission

Create the constraint record for Northstar. State one action the future prototype must never take without human approval.

How this course fitsOpen the map only when you need it.

Complete Aulafy map

How all courses connect

This is not a checklist. Start with the foundation, choose an outcome, and go deeper only when your project needs more control.

  1. 1Understand
  2. 2Apply or build
  3. 3Operate with confidence
01

Choose an application

Turn the foundation into a visible outcome: a website, a business improvement, media, or an interactive experience.

Continue into the technical branch when you need to maintain code, data, or infrastructure.

02

Build with code

Prepare your environment, work with coding agents, and run models while keeping control of your projects.

This branch prepares you to design and operate reliable AI systems.

03

Take systems to production

Combine retrieval, agents, evaluation, security, deployment, and model adaptation when the problem requires it.

You do not need every course: choose the component your system needs and return as it grows.

View full catalogue