How I Trained 100+ Engineers to Code with AI Agents (Cursor + Claude)

Why Agentic AI, Not Just Autocomplete

Most engineers think "AI coding" means autocomplete on steroids. That's table stakes. What actually moves the needle is agentic AI — where the AI understands your codebase, plans multi-file changes, runs commands, reads test output, and iterates until it's done.

At Octdaily, I set out to train 100+ engineers not just to use AI tools, but to build entire daily workflows around them.

The Three-Layer AI Stack We Use

Layer 1 — Cursor IDE (Primary Workspace)

Cursor is our standard IDE. Every engineer uses it because:

• The codebase is indexed and semantically searchable by the AI
• Agent mode can make changes across dozens of files, run builds, and fix its own errors
• Project-level rules (.cursorrules) enforce our coding standards automatically

Layer 2 — Claude (Anthropic) for Complex Reasoning

Claude handles tasks that require multi-document reasoning:

• Breaking a Jira epic into technical sub-tasks with code stubs
• Reviewing architecture decisions against HIPAA and FHIR compliance
• Generating comprehensive test plans from acceptance criteria

Layer 3 — GitHub Copilot for Line-by-Line Assistance

Still valuable for fast completions within a file — especially for boilerplate-heavy areas like FHIR resource mapping and Angular form generation.

The Daily Workflow Playbook

Morning: AI-Assisted Sprint Planning

1. Paste Jira story into Claude:
   "Break this user story into .NET 8 API + Angular 17 tasks.
    Output: file paths to create, interfaces to define, test cases."
 
2. Claude outputs a structured task list with:
   - Files to create/modify
   - Interface contracts
   - Edge cases to handle
   - FHIR resources involved
 
3. Engineer reviews and turns this into a Cursor session

During Development: Cursor Agent Mode

Our .cursorrules file includes FHIR-specific context:

# .cursorrules
- All patient data models must implement IFhirResource
- Use Azure.Health.DataServices SDK for FHIR operations
- Every API endpoint must have a corresponding FHIR capability statement entry
- PHI fields must be annotated with [SensitiveData] attribute
- Tests use xUnit + NSubstitute, follow AAA pattern

The agent follows these rules automatically across every generated file.

PR Review: AI Pre-Review Before Human Review

Before any PR is assigned to a human reviewer, our CI pipeline runs:

# .github/workflows/ai-review.yml
- name: Claude PR Review
  run: |
    gh pr diff $PR_NUMBER | \
    claude review \
      --check-hipaa-compliance \
      --check-fhir-standards \
      --suggest-tests \
      --output pr-review.md
    gh pr comment --body-file pr-review.md
  env:
    PR_NUMBER: ${{ github.event.pull_request.number }}

This catches 70% of issues before a human even opens the diff.

Training Program Structure

Week 1 — Foundations

• Prompt engineering for code tasks
• How LLMs "see" a codebase (context windows, embeddings)
• Cursor agent mode: what it can and can't do

Week 2 — Daily Workflow Integration

• AI-first story breakdown
• Pair programming with AI (you drive, AI co-pilots)
• When NOT to use AI (security-sensitive, PHI-handling code needs extra review)

Week 3 — Advanced Patterns

• Multi-agent orchestration (AI generates tests, AI fixes failures, AI documents)
• Custom cursorrules for your team's patterns
• Building your personal AI prompt library

Measured Outcomes

• 40% reduction in average feature delivery time
• 60% fewer back-and-forth PR comments (pre-review catches them)
• 3x faster onboarding for new engineers (AI explains the codebase)
• Zero HIPAA/FHIR standard violations slipping into production since the program started