The FDE curriculum
The question bank answers what to practise. These answer what to learn, and in what order. Each course is a reading path through the work a Forward Deployed Engineer actually does, with the questions and concepts that go with it. Free lessons in every course, no card needed.
Grounded in real Forward Deployed Engineer interview loops and written to a senior-engineer editorial bar.
The main path
Work these in order.
beginner11 modules · 35 lessons · ~27.5 hours10 free to read
Foundations of Forward Deployed Engineering
What a forward deployed engineer actually does, and the first week of an engagement done properly: finding the real problem, reading a system you did not build, scoping something shippable, and saying it clearly to the person paying for it.
View syllabus & course details →
Preview the 11 modules
- 01The role3/3 free
- 02Discovery3/4 free
- 03Reading systems3/3 free
- 04Code that survives in someone else's system1/3 free
- 05Data that fights back4
- 06Modelling their world3
- 07The proof of concept3
- 08Your first AI feature4
- 09Operating what you shipped3
- 10Saying it3
- 11Capstone2
advanced11 modules · 35 lessons · ~26 hours3 free to read
The FDE Engagement
Run a customer engagement end to end: technical discovery with a buyer in the room, an integration that survives their systems, a deployment somebody else can operate, a security review you pass, a production AI feature behind an eval harness, and the value conversation that decides whether any of it mattered.
View syllabus & course details →
Preview the 11 modules
- 01Technical discovery2/3 free
- 02Enterprise integration1/3 free
- 03A model of their world4
- 04Deploying in their environment4
- 05The security review3
- 06The model in production3
- 07When the answer is a model3
- 08Agents with authority4
- 09Proving it was worth it4
- 10The craft around the work3
- 11Capstone1
Going deeper
Take these when the work demands them.
intermediate7 modules · 25 lessons · ~18 hours3 free to read
Production AI Agents for FDEs
Build production AI agents in Python through 25 lessons and ten projects. Practice tool permissions, crash recovery and evaluation. Start with three free lessons.
View syllabus & course details →
Preview the 7 modules
- 01Contract and baseline2/3 free
- 02Evidence and context3
- 03Tools and authority3
- 04Durable actions3
- 05Evaluation and improvement1/5 free
- 06Post-training agents5
- 07Release and ownership3
advanced10 modules · 44 lessons · ~31 hours8 free to read
Harness Engineering for FDEs
Build coding and domain-specific agent harnesses through 44 lessons and ten projects. Practice tools, context, recovery, verification and graphs. Start free.
View syllabus & course details →
Preview the 10 modules
- 01Choose the work and its proof3/5 free
- 02Make the workspace inspectable1/4 free
- 03Constrain every action1/4 free
- 04Keep evidence usable4
- 05Resume from durable facts1/4 free
- 06Verify the customer outcome1/4 free
- 07Keep autonomous work bounded4
- 08Coordinate dependent work5
- 09Study four runtime designs4
- 10Adapt and operate the harness1/6 free
expert10 modules · 36 lessons · ~35.5 hours2 free to read
Hard Deployments
The deployments that break people: open-weight models on hardware you did not buy, environments with no internet, one platform serving tenants who must never see each other, an engagement already on fire when you arrive, and the arithmetic that decides all of it. The hardest material on this site.
View syllabus & course details →
Preview the 10 modules
- 01Serving on hardware you did not choose1/5 free
- 02The air gap3
- 03One platform, many customers4
- 04Cost and latency across a portfolio3
- 05Autonomy over long horizons3
- 06Rescue engineering1/4 free
- 07Reliability across a portfolio3
- 08Extracting a platform from field code3
- 09The practice7
- 10Capstone1