Forward Deployed Engineer Training: One Customer, From the First Meeting to Production
Where can I get forward deployed engineer training?
Become a Forward Deployed Engineer, a self-paced course at systemdesign.academy, trains you by doing the job once for one fictional US insurer, Bramfield Mutual, with labs in your own AWS account. It is in early access: 8 of 63 planned lessons are ready today, about 6 hours with 4 hands-on labs. The rest is being written. Every later lesson is included in one payment.
Save your progress and get the AI Engineering cheat sheet PDF
This page explains what the training in our Forward Deployed Engineer course is, what is ready today and what is still the plan, in 12 short answers. Every count on it is computed from the course's own lesson files.
12 questions · 4 sections · answers from the course
These answers come from our course Become a Forward Deployed Engineer: Ship AI for Real Customers: 8 lessons are ready to study today, about 6 hours of learning, with 4 hands-on labs, 3 of them in your own AWS account, and more than 150 diagrams and real screenshots. New lessons are added as they are finished, and you get every one.


The short answer
The course trains you by doing the job once, for one fictional customer, with labs in your own AWS account. It is early access: read the free lessons first, and know that most lessons are still being written.
1. What this forward deployed engineer training is
What you practise, in what form, and who it is written for.
What is forward deployed engineer training, in this course?
It is practice at the job itself. A forward deployed engineer sits with one customer and gets AI working inside that customer's own systems. In our course, Become a Forward Deployed Engineer, you do that once from start to finish for one customer, in the order the real work happens: the first meeting, getting into old systems safely, messy data, an AI agent a person approves, proof that it works, production and the handover.
The course is planned as 63 lessons in a short "Start here" section and 8 parts. It is in early access: 8 lessons are ready today, and the rest is being written. The answers below say plainly which parts are ready and which are still the plan.
Is it a video course?
No. It is a self-paced course of written lessons with real labs. Each lesson starts with a problem at the customer, explains why it matters, draws the idea, then does it on real systems, and ends with a knowledge check. Every screenshot comes from a real run, and each lesson says up front whether its lab is reading only, calls a model API, runs on AWS, or both.
There are no live sessions and no start date. You read and run the labs at your own pace.
Who is this training for?
Backend, full-stack and data engineers who want a forward deployed engineer job and want to practise the work before the interview. Solutions engineers, implementation engineers and consultants who want to own the production system, not only the demo. And engineers already in customer-facing AI roles who want one complete engagement to show.
You should be able to change a 200-line Python program, write a SQL query with a join, and use the terminal and Git. You need an AWS account you can put a card on. You do not need AI, AWS or consulting experience; each idea is explained the first time you need it, and the free lesson "Before you start" has a five-minute self-check.
2. What the whole course builds, according to the plan
The customer, the parts and the labs, read from the course's own curriculum. Most of this is still being written.

Who is the customer you work for?
Bramfield Mutual, a fictional US insurer in Harrisburg, Pennsylvania, with a claims backlog, an old claims database, a SOAP policy service, nightly file drops, a sign-in service and strict rules on personal data. It does not exist, and every record in its systems is synthetic, made by the course's own generator: 20,000 policies, 6,000 auto claims and 300 documents, counted on 13 November 2026.
You build its systems yourself, on your own AWS account, in the free lesson on meeting Bramfield. That is ready today, so you can see the customer before you decide anything.
What do the parts of the course cover?
This is the plan in the curriculum, and these parts are still being written. Part 1, The job and the customer: the job, how an engagement runs, and your first day inside systems you did not build. Part 2, Discovery and scoping: the first meeting, a baseline measured on the customer's own data and a written scope of work. Part 3, Getting into the customer's systems: scoped access, single sign-on, an old SOAP API, the nightly file drop, loads that only take what changed, write-back without duplicates, private networking, the corporate proxy and secrets.
Part 4, From messy data to safe data: cleaning, a data contract, masking personal data before any model sees it, and a golden set agreed with the claims team. Part 5, The pilot: an AI that does the job: the claims triage agent, built with LangGraph and an MCP server, with a lesson called "A person approves every decision" so that an adjuster approves, edits or refuses each draft. Part 6, Proving it works: an evaluation harness, a checked judge and shadow mode beside the adjusters. Part 7, Production inside the customer's walls: the customer's AWS account, private services, a security review and an audit trail. Part 8, Handover, adoption and the next engagement: the runbook, the field report back to product, an expansion proposal and a capstone you run yourself.
Full walkthrough: The full contents, with which lessons are ready
Where do the labs run, and how many are there?
In your own AWS account, in us-east-1. Nothing runs on ours. In the plan, 45 of the 63 lessons have a lab on real AWS and 23 call a real model API with your own key; the rest are reading and a knowledge check, such as the lessons on the first meeting and the scope of work.
Today 4 hands-on labs are published, 3 of them in your own AWS account: "Before you start" checks your account and sets a budget alert before anything is built, and the lesson on meeting Bramfield builds the customer's systems with one command and removes them with another. Every lab lesson ends by stopping or destroying what it started.

3. What is ready today, and what is not
The honest status, counted from the published lessons, not typed.
Which lessons can I study today?
8 lessons are published today: "Introduction: what this course builds", "Before you start", "What a forward deployed engineer does", "How the job differs from solutions engineer, consultant and product engineer", "Meet Bramfield Mutual, the customer in this course", "How a customer engagement runs", "Your first day inside systems you did not build" and "Working notes, a decision log and a daily update". Together they are about 6 hours of learning, with 4 hands-on labs and 162 diagrams and real screenshots. 4 paid lessons are ready beside the free ones, and 55 more are still being written.
They cover what the course builds, what a forward deployed engineer does in the words of the companies that hire them, the tools and the account setup, and the customer's systems built on your own AWS account.
What happens to the lessons that are not written yet?
They are added to the course as each one is finished, in course order, and anyone who has bought it gets every one at no extra cost. We do not promise dates. The contents page always shows which lessons are ready, so you can check the status yourself at any time.
The paid lessons ready today are listed on the contents page, next to the ones still being written.
Full walkthrough: The contents page, with each lesson's status
How is this page different from the forward deployed engineer guide and the course page?
The free guide at /forward-deployed-engineer explains the role: what the job is, what the companies ask for and how people get into it. The course page at /forward-deployed-engineer-course is where you see the full contents and buy. This page is the short, plain version of what the training is and what is ready, for someone deciding whether to start.
Full walkthrough: What a forward deployed engineer is: the free guide
4. Trying it and buying it
How to check the course yourself, and what a payment includes.
Can I try the training before I pay?
Yes. 4 lessons are free to read with their labs: "Introduction: what this course builds", "Before you start", "What a forward deployed engineer does" and "Meet Bramfield Mutual, the customer in this course". They are the start of the course, so you see the teaching style, the customer and a real AWS lab before you decide.
How does buying work?
You pay once and keep the course for life, with every lesson added to it later and the code zip for each lesson that has code. There is no subscription. The course sells at an early-access price while it is being written, and that price rises once every part is out. The price for your country is in the box on this page and on the course page.
A payment opens every paid lesson that is ready now, and each new one as it is published.
Full walkthrough: The course page, with the full contents and price
How is this different from a video course or a live bootcamp?
There are no videos and no live sessions. You read written lessons and run real labs on your own AWS account, at your own pace. The course spends whole parts on the integration work that fills an engineer's first weeks with a customer, such as file drops, loads that only take what changed, safe write-back, a corporate proxy and a security questionnaire, all on one customer from the first meeting to the handover.
If you learn best with a live teacher and a group around you, a live programme may suit you better. If you want to practise the work yourself and keep what you build, this format fits.
Where to go next
Everything on this page comes from Become a Forward Deployed Engineer: Ship AI for Real Customers. 8 lessons are ready to study today, about 6 hours of learning, with 4 hands-on labs, 3 of them in your own AWS account, and more than 150 diagrams and real screenshots. New lessons are added as they are finished, and you get every one. Start with the free lessons before you decide.
These questions are a start. The interview asks more.
Get all 100 questions in the Forward Deployed Engineer pack
Each question has why it is asked, a full answer, what the interviewer listens for, the follow-ups, the common mistakes and a diagram (127 diagrams in all). A PDF you keep, junior to staff level.
Pay by UPI, cards or netbanking through Razorpay. Pay by card or PayPal, in US dollars. Download at once from My packs.
