Overview
Half the job is code. The other half is working out what to build and getting an organisation to actually use it. This course teaches both, through one customer engagement that runs for twelve weeks, from the first day on site to the check one month after you leave: Larkfield Systems, your employer, deploying an AI claims assistant at Harbourline Freight, a regional carrier. Both companies are fictional; every lesson also opens with a real, cited case.
What you will learn
- 85 written parts, yours for good
- 18h 15m of reading, measured not estimated
- Written for the intermediate level
- Every future revision included
- UPI, cards and netbanking
Prerequisites
- A Google account, to run code in Google Colab. Nothing to install.
- One free API key, from Groq or Google Gemini, to use in Colab. Or no key at all, if you run a model on your own computer with Ollama and work in a code editor.
- For a few lessons (a React interface, Docker, a VPN), your own computer. Those lessons say so.
Curriculum
16 sections · 85 parts · 18h 15m2h 31m free to read · 15h 44m with the course
01Course guide5 parts · 51 min
- Forward Deployed Engineer: The Complete CoursePreview4 min
- How This Course WorksPreview6 min
- Setup: Colab, Your Model Provider, and Running LocallyPreview8 min
- The Engagement: Larkfield at Harbourline FreightPreview15 min
- Shared Harbourline DataPreview18 min
02Module 1: Engineering Floor7 parts · 100 min
- Module 1: Engineering FloorPreview1 min
- Lesson 1: The core toolkit you bring on sitePreview16 min
- Lesson 2: The backend behind one late claimPreview20 min
- Lesson 3: A screen the claims team can trustPreview20 min
- Lesson 4: Infrastructure: getting the claims tool off your laptopPreview16 min
- Lab: The claims service skeleton, end to endPreview18 min
- Incident: Stolen CI secrets that never expiredPreview9 min
03Module 2: Speed of Delivery5 parts · 65 min
- Module 2: Speed of Delivery1 min
- Lesson 1: A working prototype by Wednesday19 min
- Lesson 2: Saying what it is before someone else does19 min
- Lab: From vague request to labelled prototype16 min
- Incident: A rushed model, conditions nobody checked10 min
04Module 3: Discovery and Problem Framing5 parts · 65 min
- Module 3: Discovery and Problem Framing1 min
- Lesson 1: Watch the work before you build anything18 min
- Lesson 2: From a vague ask to a measured scope21 min
- Lab: Discovery from Joan's desk to signed scope16 min
- Incident: The wrong number measured, very accurately9 min
05Module 4: Their Data6 parts · 81 min
- Module 4: Their Data1 min
- Lesson 1: Getting Harbourline's data into your hands19 min
- Lesson 2: Turning Harbourline's raw export into trusted data17 min
- Lesson 3: Handling Harbourline's data so Viktor can defend it17 min
- Lab: One night's export, from arrival to trusted table17 min
- Incident: The hidden worksheet that published a workforce10 min
06Module 5: AI and LLM Application Work5 parts · 75 min
- Module 5: AI and LLM Application Work1 min
- Lesson 1: A triage assistant that reads untrusted email21 min
- Lesson 2: Deploying the assistant where Harbourline can trust it20 min
- Lab: Ship the triage assistant Harbourline would run22 min
- Incident: Invented citations, signed without checking11 min
07Module 6: Enterprise Integration6 parts · 77 min
- Module 6: Enterprise Integration1 min
- Lesson 1: Who is asking, and what may they touch?19 min
- Lesson 2: Shipping into a network you do not control17 min
- Lesson 3: Mapping the systems your tool will lean on18 min
- Lab: Taking the claims tool through Harbourline's gates15 min
- Incident: A retired key that still signed in7 min
08Module 7: Security and Compliance5 parts · 65 min
- Module 7: Security and Compliance1 min
- Lesson 1: The security baseline, traced through one claim19 min
- Lesson 2: Answering Viktor's questionnaire without overpromising18 min
- Lab: Taking the claims tool through security review19 min
- Incident: A changed script nobody was watching8 min
09Module 8: Domain Immersion5 parts · 71 min
- Module 8: Domain Immersion1 min
- Lesson 1: Learn how Harbourline makes, loses and argues about money21 min
- Lesson 2: Speak, model and promise in Harbourline's terms17 min
- Lab: Harbourline's claims rules, written as code22 min
- Incident: A rule read literally, applied to everyone10 min
10Module 9: Communication6 parts · 81 min
- Module 9: Communication1 min
- Lesson 1: Writing that gets read and acted on19 min
- Lesson 2: Demos, hard questions and bad news, said out loud17 min
- Lesson 3: Hearing what the meeting did not say16 min
- Lab: One hard week, told to everyone19 min
- Incident: A warning written, then never sent9 min
11Module 10: Stakeholders and Politics5 parts · 57 min
- Module 10: Stakeholders and Politics1 min
- Lesson 1: Drawing the map of who decides what15 min
- Lesson 2: Keeping promises when people want different things15 min
- Lab: Stakeholder work across Rafael's departure17 min
- Incident: The warning that never reached the decider9 min
12Module 11: Delivery Management5 parts · 65 min
- Module 11: Delivery Management1 min
- Lesson 1: Running the engagement from kickoff to handover17 min
- Lesson 2: Landing it so it runs without you16 min
- Lab: Run the engagement's delivery machinery end to end22 min
- Incident: The end date held, the rollout squeezed9 min
13Module 12: Commercial Awareness5 parts · 58 min
- Module 12: Commercial Awareness1 min
- Lesson 1: What to get right before the contract is signed18 min
- Lesson 2: After it: value, case study, renewal and margin15 min
- Lab: The commercial file, from promises to renewal16 min
- Incident: Scaling a price the forecast could not carry8 min
14Module 13: Product Feedback Loop5 parts · 64 min
- Module 13: Product Feedback Loop1 min
- Lesson 1: Which custom work belongs in the product18 min
- Lesson 2: Bringing the field to the product team, without forks19 min
- Lab: The working-day gap, from field note to product18 min
- Incident: A local patch nobody upstream reviewed8 min
15Module 14: Operating in the Field5 parts · 61 min
- Module 14: Operating in the Field1 min
- Lesson 1: Getting in, getting there, getting through17 min
- Lesson 2: Doing this work for years, not weeks18 min
- Lab: Plan and check the go-live week18 min
- Incident: One mistyped input, and no way to say so7 min
16Module 15: Professional Practice5 parts · 59 min
- Module 15: Professional Practice1 min
- Lesson 1: Saying no, saying not yet, and saying it early15 min
- Lesson 2: What you take from the engagement15 min
- Lab: Close the engagement, open the portfolio20 min
- Incident: The system's figure believed over people8 min
Part 1 · freeForward Deployed Engineer: The Complete Course · 4 min
Engineering done inside someone else's organisation, on their data, against their constraints, next to the people whose problem it is.
Half the job is code. The other half is working out what to build and getting an organisation to actually use it. This course teaches both, through one customer engagement that runs for twelve weeks, from the first day on site to the check one month after you leave: Larkfield Systems, your employer, deploying an AI claims assistant at Harbourline Freight, a regional carrier. Both companies are fictional; every lesson also opens with a real, cited case.
Who this course is for
You can already ship software, or you are learning to. You want to do it for customers, in their environment, and be the person who makes a product work in the real world.
Reviews
No reviews yet. The first comes from a reader who finishes the course.
to review this course once you have finished it.
Next to this one
Transformers: From Attention to Trained, Served and Interpreted Models111 parts · 43h 12m · ₹399Retrieval-Augmented Generation: The Complete Course95 parts · 38h 33m · ₹399Large Language Models: The Complete Course103 parts · 34h 48m · ₹399AI Engineering: The Complete Course105 parts · 23h 44m · ₹399Agentic AI Engineer: The Complete Course97 parts · 33h 10m · ₹399
Large Language Models80 parts · 27h 0m · Free
Model Context Protocol83 parts · 14h 44m · ₹199
RAG82 parts · 13h 36m · ₹399
Python79 parts · 7h 28m · Free