Skip to content
All paths
Forward Deployed EngineerFlagship path

Take AI from a demo to a customer's production.

Start free with how language models work, build the Applied AI core, and run your first customer discovery call early. Then get fluent on Claude, OpenAI and Gemini, ship on the customer's infrastructure, and learn the field skills: scoping, enterprise integration, a two-week pilot and the executive readout. It ends with interview prep for AI labs and consultancies.

Start the first lessonSee pricing

69 lessons in 10 milestones, plus 15 optional electives, about 44 h in all. Starts free; the full path needs the Mastery plan.

By the end you can
  • Run discovery with a customer's team and find the real problem
  • Fit into their SSO, network, data permissions and security review
  • Run a two-week pilot against success criteria agreed up front
  • Build on Claude, OpenAI or Gemini behind one abstraction layer
  • Explain results and trade-offs to executives and get the rollout signed
  • Walk into an FDE interview loop with a practised build, case and story bank

The roadmap

Work through it in order, or jump to what you need. Open a milestone to see its lessons.

Choose your starting pointyou can change it any time
What do you already know?
  1. Level 1 of 4

    Foundation

    You can explain how a language model works and call one safely.

  2. AI foundations

    Explain how a language model works, call one, and spot when it's making things up.

    Start: What AI Actually Is
    8 lessons · about 5 h 10 min
    1. What AI Actually Is
    2. Inside a Language Model
    3. Tokens, Context & Embeddings
    4. Prompting Basics
    5. Calling a Model
    6. Limits & Hallucination
    7. The Modern AI Toolkit
    8. Evaluating & Choosing Models
  3. Level 2 of 4

    Junior FDE

    You can build tool-using, retrieval-backed features and run a discovery call.

  4. The Applied AI core

    Applied AI plan

    Build the LLM features customers actually ask for: tools, reasoning, retrieval.

    Start: Software Engineering Practices
    10 lessons · about 5 h 5 min
    1. Software Engineering Practices
    2. Prompt Engineering & Structured Output
    3. LLM APIs & Model Integration
    4. Tool Use & Function Calling
    5. Basic Reasoning Techniques
    6. Vector Embeddings & Semantic Search
    7. RAG Pipelines
    8. Memory Management & Context Engineering
    9. Knowledge Bases & Vector Databases
    10. Data Ingestion & Preprocessing

  5. Your first customer conversation

    Mastery plan

    Run a discovery call and find the real problem behind what the customer asks for.

    Start: Customer Discovery
    1 lesson · about 50 min
    1. Customer Discovery
  6. Level 3 of 4

    Mid FDE

    You can ship on the customer's stack, platform and cloud, and pass their security review.

  7. Agents in a customer's stack

    Applied AI plan

    Design agents and integrations that fit someone else's systems.

    Start: Workflow Orchestration & Routing
    5 lessons · about 2 h 30 min
    1. Workflow Orchestration & Routing
    2. Planning, Reflection & Multi-Step Reasoning
    3. Single & Multi-Agent Systems
    4. Model Context Protocol (MCP) & Tool Ecosystems
    5. Parallelization & Resource-Aware Execution

  8. Fluent on every frontier platform

    Mastery plan

    Build on Claude, OpenAI and Gemini, and hide them behind one layer that fails over.

    Start: Multi-Provider Abstraction Layers
    5 lessons · about 4 h
    1. Multi-Provider Abstraction Layers
    2. The Claude Platform
    3. The OpenAI Platform
    4. Google Gemini & Agent Platform
    5. MCP Apps for Customers

  9. Earn the customer's trust

    Applied AI plan

    Pass a security review and prove quality with evals and guardrails.

    Start: Secrets Management
    12 lessons · about 7 h 15 min · 2 electives
    1. Secrets ManagementSystems
    2. AuthN & AuthZSystems
    3. API Security & SSRFSystems
    4. Prompt Injection & the LLM Attack SurfaceSystems
    5. Sandboxing Untrusted Code & ToolsSystems
    6. Data Leakage & PIISystems
    7. Tenant IsolationSystems
    8. Rate Limiting & Abuse PreventionSystems
    9. Exception Handling, Recovery & Human-in-the-LoopApplied AI
    10. Evaluation Frameworks & MetricsApplied AI
    11. Observability, Monitoring & LoggingApplied AI
    12. Guardrails, Safety & AlignmentApplied AI
    13. Electives: optional, they don't count toward this milestone
      Applied CryptographySystems
    14. Cost Optimization & Latency EngineeringApplied AI

  10. Ship on their infrastructure

    Mastery plan

    Containers, Kubernetes, event streams, tracing and CI/CD: deploy into the customer's cloud, not a demo laptop.

    Start: Deployment & Infrastructure
    7 lessons · about 4 h 20 min
    1. Deployment & InfrastructureApplied AI
    2. CI/CD, Testing & Versioning for AIApplied AI
    3. Docker & Containerization for AIMastery
    4. Kubernetes & OrchestrationMastery
    5. Kafka & Event Streaming for AgentsMastery
    6. OpenTelemetry & Tracing Agent RunsMastery
    7. CI/CD & AutoscalingMastery
  11. Level 4 of 4

    Senior FDE

    You can run a pilot to a signed rollout, make the business case, and clear the interview loop.

  12. Make the business case

    Mastery plan

    Price it, scope it and keep it running after you hand it over.

    Start: Unit Economics & $/Request
    12 lessons · about 7 h 45 min · 13 electives
    1. Unit Economics & $/Request
    2. Token Budgeting
    3. Pricing & Monetization
    4. ROI & Build-vs-Buy
    5. Enterprise Procurement Realities
    6. UX for AI Systems
    7. Communicating Uncertainty
    8. Human-in-the-Loop Design
    9. Fallback & Degradation UX
    10. Provider Outage
    11. Prompt Injection Breach
    12. PII Leakage Incident
    13. Electives: optional, they don't count toward this milestone
      Cost Attribution & FinOps
    14. Infra Budgeting & Margin Analysis
    15. Scaling Cost Curves
    16. Onboarding & Expectation-Setting
    17. Feedback, Correction & the Data Flywheel
    18. Latency UX & Streaming
    19. User Trust & Agent Ergonomics
    20. Vector DB Corruption
    21. Runaway Agent Billing
    22. Queue Backlog Collapse
    23. Latency Cascade
    24. Multi-Agent Deadlock
    25. Hallucinated Finance Response

  13. Field deployment

    Mastery plan

    Run the engagement itself, from scoping to signed rollout.

    Start: Scoping & Success Criteria
    4 lessons · about 3 h 5 min
    1. Scoping & Success Criteria
    2. Enterprise Integration: SSO, VPC & Data Access
    3. Running a Two-Week Pilot
    4. Stakeholders & Executive Updates

  14. Get the offer

    Mastery plan

    Practise the loop: a live build round, graded customer role-plays, system design and your story bank.

    Start: The FDE Interview Loop
    5 lessons · about 3 h 50 min
    1. The FDE Interview Loop
    2. The Live Build Round
    3. Customer Case & Role-Play
    4. System Design for FDEs
    5. Behavioral & Story Bank

  15. Final project

    Ship a real system on real infrastructure. Each project has an architecture diagram and a step-by-step build guide.

    The Provider-Agnostic LLM GatewayYour startup is locked into one model vendor and one outage took down the whole product. Build the internal gateway every team routes through.Production RAG Over Ugly Real DocumentsA law / insurance / clinical firm hands you 500 genuinely ugly PDFs, scans, multi-column, tables, and demands grounded answers with citations and zero hallucination tolerance.Observability + Guardrails for an Agent in ProdAn agent is live and you are on-call for it.

Start where you are.

Your progress is saved as you go, and every lesson you finish counts toward every path that includes it.

Compare paths