Fieldpath

Curriculum

The 30-day plan

60 hours. Each cell is a full lesson with concepts, a session clock, drills, and checks — not a topic title waiting for another course.

Week 1

Speak the language

Become fluent in how modern AI actually works — models, tokens, prompts, and cost — so you can sit in a technical room without translating through someone else.

0/7 complete

  1. Day 1120m

    The map: where a delivery manager actually lands

    Orientation — pick the game before you train for it

  2. Day 2120m

    How a model actually works (without a PhD)

    Literacy — next token, context, and why it hallucinates

  3. Day 3120m

    The model landscape: what to use, when, and who owns it

    Literacy — vendors, open weights, and a decision you can defend

  4. Day 4120m

    Prompting as a professional skill

    Craft — system, spec, examples, and failure

  5. Day 5120m

    Tokens, cost, and unit economics

    Numbers — the RAID item nobody puts on the RAID log

  6. Day 6120m

    The four interfaces: chat, structured, embeddings, tools

    Architecture — stop saying 'chatbot' for every request

  7. Day 7120m

    Lab: a delivery prompt system you can use on Monday

    Build the week-1 artifact

Week 2

Build enough to be dangerous

Get your hands on the four primitives every AI product is made of: an API call, embeddings, retrieval, and a tool-using loop.

0/7 complete

  1. Day 8120m

    Python just enough to ship a thin slice

    Build — the 20% of the language that shows up in every demo

  2. Day 9120m

    Calling an LLM API like a grown-up

    Build — request, stream, fail, retry, log

  3. Day 10120m

    Embeddings and semantic search

    Build — the retrieve in retrieval

  4. Day 11120m

    RAG: the enterprise pattern

    Build — retrieve, stuff, generate, cite

  5. Day 12120m

    Why RAG fails in production

    Reality — the failure catalog you will walk into

  6. Day 13120m

    Agents and tools: when a loop is worth it

    Build — ReAct, caps, and why 'autonomous' is a smell

  7. Day 14120m

    Lab: design a project-wiki copilot

    Build the week-2 artifact

Week 3

Ship like a delivery lead

Apply the job you already have — RAID, vendors, SLAs, governance, change — to AI workstreams that fail in new ways.

0/7 complete

  1. Day 15120m

    Data, PII, and the governance that actually blocks you

    Ship — the workstream before the model workstream

  2. Day 16120m

    Evaluation: how you know it works

    Ship — acceptance criteria for a probabilistic system

  3. Day 17120m

    Guardrails and human-in-the-loop

    Ship — the control plane around a model that can be wrong

  4. Day 18120m

    Production: latency, reliability, and the ops you already know

    Ship — SLOs for a system that shrugs

  5. Day 19120m

    Build vs buy, vendors, and the POC trap

    Ship — procurement with a spine

  6. Day 20120m

    The AI delivery playbook (your actual job)

    Ship — discovery, scoring, RAID, change, value

  7. Day 21120m

    Lab: the use-case charter and eval plan

    Build the week-3 artifact

Week 4

Land the role

Pick the AI seat that fits a delivery manager, build the portfolio that proves it, and practice the interviews that hire for it.

0/9 complete

  1. Day 22120m

    Pick the seat: a real target, not a vibe

    Land — one primary role, one backup

  2. Day 23120m

    Portfolio: the demo story

    Land — problem, slice, measure, expand

  3. Day 24120m

    Portfolio: the delivery artifacts

    Land — charter, RAID, eval, cost on one table

  4. Day 25120m

    Positioning, resume, LinkedIn

    Land — the paper that gets the loop, not the paper that lists tools

  5. Day 26120m

    Interview loops: what they actually run

    Land — screens, cases, technicals, take-homes

  6. Day 27120m

    Scenario drills: the chatbot-by-Friday

    Land — live judgment under a bad request

  7. Day 28120m

    Capstone assembly

    Land — one folder, six artifacts, no orphans

  8. Day 29120m

    Walkthrough: 12 minutes, then questions

    Land — the performance

  9. Day 30120m

    The 90-day plan and the job operating system

    Land — after the month, the machine that gets the offer