AiFDE School: Where AI gets real.

FDE course · Synchronous online

Forward Deployed Engineering (FDE): from demo to production, in six weeks.

A synchronous, hands-on course that starts from fundamentals and takes you to complex, real-world production systems, so you leave with the core skills to handle real production issues at a customer.

Weekend cohort
From Sat, Dec 5
Weekday cohort
From Mon, Dec 14
Length
6 weeks · 54 hours
Price
$3,900
A forward deployed engineer walking a clinic's front-desk team through an approval queue
You build a healthcare front-office system

01 · Why the FDE course

Built the way forward deployed engineers actually work.

Open FDE roles at tech companies grew 4.6× in a year, to 1,450 in October 2026 (TrueUp). See the job data.

Fundamentals first, production by the end

Start with how LLMs work: tokens, embeddings, transformers and training. Finish by shipping an agent with monitoring, evaluation, security testing and cost control.

One real-world system, built session by session

No throwaway demos. You build a healthcare front-office system that becomes more capable and more production-ready every session.

Built the way FDEs work

Every project follows the full FDE arc: Discovery, Goal, Prototype, Productionize, including approval rules, before-and-after metrics and handover.

Production problems, on purpose

Debug planted bugs, defend against prompt-injection and tool-poisoning attacks, survive a malicious tool server, and stop bad changes with quality gates.

Safety and cost from day one

Guardrails, human approval for actions, cost tracking and model choice run through the whole course, not just one final module.

Works with any model

The same code runs on commercial and open models, as customer environments require.

Interview-ready

Every class ends with in-class practice on 10 FDE interview questions, plus the customer conversations FDEs face: security reviews, scope changes and cost questions.
38hands-on labs
10reference projects
220interview questions
25+frameworks and tools

02 · Schedule

Two cohorts. Same course. Pick your week.

Weekend cohort

Saturday and Sunday

8 AM–12 PM ET

First class
Sat, Dec 5, 2026
Last class
Sun, Jan 17, 2027
Hackathon
Sun, Jan 24, 2027
CT 7–11 AMMT 6–10 AMPT 5–9 AM

Two sessions each day, so each weekend covers one full module. No class Dec 26–27.

Weekday cohort

Monday to Thursday

8–10 PM ET

First class
Mon, Dec 14, 2026
Last class
Thu, Jan 21, 2027
Hackathon
Sun, Jan 24, 2027
CT 7–9 PMMT 6–8 PMPT 5–7 PM

22 two-hour sessions. No class Dec 24 or Dec 31. Class runs on Martin Luther King Jr. Day (Jan 18).

03 · Curriculum

22 sessions. Six modules. One production system.

Show dates for
Module 1The FDE role and how LLMs workDec 5–6
  1. 01Sat Dec 5

    The FDE role and GenAI vs traditional programming

    What an FDE is and why FDEs matter; stages of FDE work; FDE vs other roles; when not to use AI

    LabsSupport-ticket router

  2. 02Sat Dec 5

    How LLMs work

    Tokens and token inflation; embeddings; transformers; mixture of experts; pre-training and post-training

    LabsToken explorer; embeddings

  3. 03Sun Dec 6

    Model selection and inferencing

    Model landscape; open vs commercial models; benchmarks; inference

    LabsModel bake-off

  4. 04Sun Dec 6

    Prompt engineering and prompts as code

    Anatomy of a prompt; few-shot; chain of thought vs reasoning models; prompt caching

    LabsFew-shot router; versioned prompts with evaluation

Module 2Structured output, context and retrievalDec 12–13
  1. 05Sat Dec 12

    Structured output and tool calling

    Why free text breaks; structured output; constrained decoding; tool calling

    LabsData extraction; tool-calling round trip

  2. 06Sat Dec 12

    Context engineering and memory

    Context as a budget; write, select, compress, isolate; short- and long-term memory

    LabsContext budget meter; chat with memory

  3. 07Sun Dec 13

    RAG I: retrieval design and RAG types

    Parsing and chunking; embeddings and vector stores; RAG types

    LabsChunking strategies; index and ask

  4. 08Sun Dec 13

    RAG II: advanced retrieval and grounded generation

    Why naive RAG fails; hybrid search and reranking; grounded generation

    LabsRetriever comparison; grounded, cited answers

Module 3RAG evaluation and AI agentsDec 19–20
  1. 09Sat Dec 19

    RAG III: RAG evaluationProject 1 demos

    What to measure; building an evaluation set

    LabsNaive vs grounded RAG

  2. 10Sat Dec 19

    AI agents I: foundations

    What an agent is; workflow patterns; an agent from scratch

    LabsA workflow; front-desk agent

  3. 11Sun Dec 20

    AI agents II: loop, tools, planning and approval

    The ReAct loop; designing tools; planning and approvals; agent frameworks

    LabsFramework agent; human approval for changes

  4. 12Sun Dec 20

    AI agents III: guardrails and reliabilityMini project demos

    Guardrails; retries and fallbacks; RAG for agents

    LabsHardened agent

Module 4MCP and the email agentJan 2–3
  1. 13Sat Jan 2

    MCP I: why MCP and your first server

    Why MCP; architecture; tools, resources and prompts

    LabsFirst MCP server; scheduling server

  2. 14Sat Jan 2

    MCP II: agents over MCP

    Clients and hosts; a knowledge server; control in the host

    LabsTwo servers, one agent

  3. 15Sun Jan 3

    MCP III: remote servers, security and deployment

    Remote MCP; MCP security; MCP in production

    LabsAttack and defend; deploy a remote server

  4. 16Sun Jan 3

    Project 2: the email agentProject 2 demos

    Discovery to goal; design; build; approval queues and outcomes

    LabsEmail agent build

Module 5Multi-agent systems, observability and evaluationJan 9–10
  1. 17Sat Jan 9

    Multi-agent systems and A2A

    When to use more agents; multi-agent patterns; the A2A protocol

    LabsSupervisor agent; billing agent over A2A

  2. 18Sat Jan 9

    The AI harness, agent memory and deep agents

    The AI harness; agent memory; deep agents

    LabsAgent memory; deep agent

  3. 19Sun Jan 10

    Observability: logs, metrics and tracing

    Logs, metrics and traces; OpenTelemetry; dashboards and alerts

    LabsTrace an agent; dashboard, alerts and bug hunt

  4. 20Sun Jan 10

    Evaluation I: judges, RAG and agent evals

    Evaluation fundamentals; datasets and graders; LLM-as-judge

    LabsAgent evaluations; judge calibration and RAG metrics

Module 6Production evaluation, security and costJan 16–17
  1. 21Sat Jan 16

    Evaluation II: production evals and reliability

    Production evaluation; reliability at scale; evaluation gates in CI

    LabsOnline evaluator; GitHub Actions quality gate

  2. 22Sun Jan 17

    Security, cost and performance

    Threat modelling (OWASP); red-teaming; model routing and caching

    LabsRed-team test suite; cost and latency benchmark

Capstone Hackathon · Sun, Jan 24, 2027 · 8 AM–6 PM ETBoth cohorts together. One brief, one day, design to demo.

No class Dec 24–27 or Dec 31. The weekday cohort has class on Martin Luther King Jr. Day (Jan 18). Each class is two hours of teaching, followed by interview practice.

04 · What you build

Three projects, a capstone, and ten reference builds.

Project 1: RAG knowledge assistant

An assistant that answers from clinic documents with citations, measured against an evaluation set.

Mini project: hardened agent

An agent with guardrails, retries, fallbacks and document search.

Project 2: email agent

An agent that reads patient email, routes it by intent, prepares changes and drafts replies for staff approval, with outcomes measured against the old process.

Capstone Hackathon

Design, build, evaluate and present an end-to-end FDE solution in one 10-hour day.

Reference projects

Together they form one production-grade system for a healthcare front office.

  1. 01Front-desk booking agent with human approval for changes
  2. 02RAG knowledge base with hybrid search, reranking and cited answers
  3. 03Scheduling server on MCP, deployed remotely
  4. 04Knowledge-base server on MCP
  5. 05Mailbox server on MCP
  6. 06Automated email agent with a role-based staff approval queue
  7. 07Billing agent that a supervisor agent calls over A2A
  8. 08Long-running deep agent with memory and planning
  9. 09Monitoring: tracing, dashboards and alerts
  10. 10Release pipeline: automated evals, a CI quality gate and a security test suite

05 · Frameworks and tools

The stack FDEs use in the field.

Agents

LangChain, LangGraph, LangSmith, Deep Agents

Tool and agent protocols

MCP (FastMCP, LangChain MCP adapters), A2A

Retrieval (RAG)

Chroma, Pinecone, pgvector, BM25 hybrid search, cross-encoder reranking

Observability

OpenTelemetry, Arize Phoenix, LangSmith tracing

Evaluation and release

LangSmith evaluations, LLM-as-judge, RAGAS, GitHub Actions

Models

OpenAI, Anthropic Claude, open models via Ollama and Hugging Face

Developer tools

Cursor, Claude Code, Streamlit, SQLite, Pydantic

How classes run

Synchronous classes. Never prerecorded.

Most online courses are self-paced, prerecorded videos. Ours are synchronous: you, your classmates and your instructor log in at the same scheduled time, cameras on, and learn together like an in-person class.

Same time, every class

Everyone logs in together at a scheduled time: weekday evenings or weekend mornings, Eastern time.

Cameras on, like a classroom

You see your instructor and classmates, and they see you. Need a short break from the camera? Tell your instructor before class.

Instructor-led and hands-on

Your instructor teaches, then you build in class while they watch, answer and fix problems with you.

Attendance counts

Attend at least 18 of the 22 sessions for your certificate. Classes are not recorded, just like a university classroom. Missed a class? Join the same session in the other cohort if it is still ahead, or catch up with that session's lab code and notes and bring your questions to office hours. Miss more than 4 classes and you can move once, free, to the next cohort of the same course.

Self-paced video course (asynchronous)WebinarAI FDE School: synchronous
When you learnWhenever you likeAt a set timeAt a set time, with the same classmates all course
CamerasNoneUsually only the presenterEveryone, cameras on
Hands-on workAlone, after the videoRarelyIn every class, with your instructor watching
QuestionsForum, answered laterChat box, if time allowsAsk out loud, answered on the spot
AttendanceNot trackedNot trackedExpected: 18 of 22 sessions for the certificate
RecordingsThe videos are the courseOften recordedNot recorded, like a university classroom

Included with every seat

More than the synchronous classes.

Live office hours + 1-on-1s

Live group office hours twice a week, plus two 20-minute 1-on-1 sessions with your instructor per course.

24/7 help channel

Ask anytime, 24/7. Your instructor replies within 24 hours.

LCAE exam prep, fee back on a pass

Prep for the LangChain Certified Agent Engineer (LCAE) exam: LangChain, LangGraph and LangSmith. Pass within 3 months and we reimburse the exam fee. Claude certification prep too: if your employer is a Claude Partner Network member, you can take Anthropic's Claude exams, and we reimburse those on a pass as well.

Certificate of course completion

Attend at least 18 of the 22 synchronous sessions and submit the projects.

06 · Price

$3,900

Synchronous online classes, never prerecorded. US dollars. One price for the full course. Or 3 monthly payments of $1,350 ($4,050 in total), and employers can pay by invoice.

  • 22 synchronous, instructor-led sessions (44 hours), cameras on, never prerecorded
  • 10-hour Capstone Hackathon with prizes
  • 38 labs, 3 projects and 10 reference builds
  • 220 FDE interview questions practised in class
  • Live group office hours twice a week
  • Two 20-minute 1-on-1s with your instructor
  • 24/7 help channel (instructor replies within 24 hours)
  • LangChain LCAE certification prep; exam fee reimbursed when you pass (Claude exams too, if your employer is a Claude partner)
  • Certificate of course completion
  • Weekday or weekend cohort
  • Full refund within your first 16 class hours: until Sun, Dec 13 (weekend) or Mon, Dec 28 (weekday) (Refund Policy)
Book a free info session

Capstone Hackathon

One day. One real brief. $10,000 in prizes.

Sunday, January 24, 2027, 8 AM–6 PM Eastern. Both cohorts design, build, evaluate and present an end-to-end FDE solution.

1st$5,000
2nd$3,000
3rd$2,000

Open to enrolled FDE students, alone or in teams of up to four. Official rules will be published before the event. About the hackathon

07 · Questions

About the FDE course.

Which cohort should I choose?
Pick the one that fits your week. The weekend cohort meets Saturday and Sunday, 8 AM to 12 PM Eastern, from December 5. The weekday cohort meets Monday to Thursday, 8 to 10 PM Eastern, from December 14. Both cover the same 22 sessions and join for the Capstone Hackathon on January 24.
How many hours is the course?
44 hours of synchronous class (22 two-hour sessions) plus the 10-hour Capstone Hackathon, 54 hours in total.
Who is it for?
Software and data engineers, solutions and customer engineers, and technical consultants who want to take AI from a demo to production inside a customer's business.
Do I need AI experience already?
The course starts from fundamentals, with how LLMs work, and builds up to production systems. You should be comfortable writing code.
Which AI models will I use?
OpenAI and Anthropic Claude models, plus open models through Ollama and Hugging Face. The same code runs on each.
What if I need to cancel?
You can request a full refund until 11:59 PM ET on the day of your 8th class session (16 class hours): Sun, Dec 13 for the weekend cohort and Mon, Dec 28 for the weekday cohort. Before your first class, you can also move once, free, to a later cohort. See the Refund Policy.
Is this a certificate or degree?
No. It is non-credit skills training, not a degree, and earns no academic credit. Students who attend at least 18 of the 22 synchronous sessions and submit the course projects receive an AI FDE School certificate of course completion. AI FDE School does not guarantee employment, salary or any other outcome.
Are classes synchronous, or self-paced videos?
Synchronous, never prerecorded. Everyone, your instructor and your classmates, logs in at the same scheduled time, with cameras on, just like an in-person class. You build during class while your instructor watches and helps, and you ask questions as they come up. There is no self-paced video library. Classes are not recorded, just like a university classroom. Missed a class? Join the same session in the other cohort if it is still ahead, or catch up with that session's lab code and notes and bring your questions to office hours. Miss more than 4 classes and you can move once, free, to the next cohort of the same course.
Is there help between classes?
Yes. Live group office hours twice a week, two 20-minute 1-on-1 sessions with your instructor per course (for example a project review and interview or certification prep), and a help channel open 24/7 where your instructor replies within 24 hours.
Do you help with industry certifications?
Yes. We prepare you for the LangChain Certified Agent Engineer (LCAE) exam, which covers LangChain, LangGraph and LangSmith and is open to anyone: a guide that maps each exam topic to our sessions, practice questions and a prep office hour. You register and pay the exam fee yourself with LangChain. If you pass within 3 months of your course's last class, we reimburse the exam fee (one attempt per exam; send us your pass result and receipt). We help you prepare, but we can't promise a pass. We also teach the material behind Claude certifications (Anthropic). Anthropic currently offers its Claude exams only to people at Claude Partner Network companies. If your employer is a member, you can take one, and the same reimbursement applies. The exams are run by LangChain and Anthropic, which are not affiliated with AI FDE School.
Can I join from outside the USA?
Not yet. Courses are open only to people living in the United States.

Seats are limited. Start Dec 5 or Dec 14.

Join a free, live info session to see if the FDE course fits you, and ask the trainers anything.