Forward Deployed Engineer

2 h kickoff + 48 sessions × 2 h + 2 h showcase = 100 hours

1. Kickoff2 hoursSunday, November 1

   Kickoff and setup

   Meet the cohort, see how classes run, set up your development environment and accounts, tour what you will build, and make a first working call to an AI model.

2. Week112 hoursNov 2–7

   The FDE role and discovery

   1. What an FDE does and how the work is structured
   2. Stakeholder interviews: listening for the real problem
   3. Mapping a customer's workflow from start to finish
   4. Defining success and how to measure it
   5. Scoping: what to build first, and what not to
   6. Writing the discovery brief

   Project A discovery brief for an example scenario, such as faster insurance claims handling.

3. Week212 hoursNov 9–14

   Rapid prototyping

   1. Calling AI model APIs from a prototype
   2. Structured outputs for real workflows
   3. Building a working demo in days
   4. Demoing and collecting reactions
   5. Managing expectations early
   6. Iterating from feedback

   Project A working prototype built from your discovery brief.

4. Week312 hoursNov 16–21

   Integration, part 1

   1. Reading and working in an unfamiliar codebase
   2. REST APIs, authentication and webhooks
   3. CRMs and other business systems
   4. SQL and data warehouses for FDEs
   5. Environments, secrets and configuration
   6. Version control and pull requests in a customer's repository

   Project Connect your prototype to a sample business system.

5. Week412 hoursNov 23–28

   Integration, part 2: messy reality

   1. Cleaning and mapping messy data
   2. Documents, spreadsheets and email as inputs
   3. Working around older systems
   4. Batch jobs, queues and pipelines
   5. Permissions and data access rules
   6. Failures and edge cases

   Project Make the integration robust against realistic bad data.

6. Week512 hoursNov 30–Dec 5

   Retrieval and agents for customer workflows

   1. Grounding models in a customer's own data
   2. Retrieval with citations
   3. Agents that use a customer's tools
   4. Human approval steps in a workflow
   5. Error handling and fallbacks
   6. Choosing the simplest design that works

   Project A workflow assistant grounded in the customer's data.

7. Week612 hoursDec 7–12

   Evaluation, security and trust

   1. Agreeing acceptance criteria with the customer
   2. Building an evaluation set from real cases
   3. Security review basics, and working with IT teams
   4. Privacy, sensitive data and audit trails
   5. Access control and least privilege
   6. Reporting quality honestly

   Project An evaluation report and a security checklist.

8. Week712 hoursDec 14–19

   Rollout

   1. Deploying to a production environment
   2. Monitoring and alerting
   3. Training users and supporting adoption
   4. Documentation and handoff runbooks
   5. Incidents and support requests
   6. Planning the transition of ownership

   Project A rollout plan and a runbook.

9. Week812 hoursDec 21–26

   Communication and capstone

   1. Running demos for executives and end users
   2. Status updates and managing scope
   3. Saying no, and negotiating priorities
   4. Turning what you learn in the field into product feedback
   5. Capstone engagement sprint
   6. Presentation practice

   Project Capstone: a simulated end-to-end customer engagement.

10. Showcase2 hoursSunday, December 27

    Final showcase

    Present your capstone to the group, get feedback from trainers and classmates, and plan what to build and learn next.