Navigate

Built with Eiffel + AI + DBC

WORKFLOW

The Human-AI Workflow

You're the pilot. Here's how the collaboration actually works.

The Metaphor: Your Airplane / My Airplane

In aviation, pilots explicitly transfer control:

AI-assisted development works the same way:

Human ("My airplane")

  • • Setting direction and goals
  • • Architectural decisions
  • • Validating proposals
  • • Course corrections
  • • Final approval

AI ("Your airplane")

  • • Code generation
  • • Pattern application
  • • Documentation
  • • Test creation
  • • Bulk operations

You're always pilot-in-command. But workload shifts based on the task.

A Real Session

Here's an actual exchange from building simple_htmx:

HUMAN: "Build a fluent HTML builder for HTMX attributes."
AI: "I'll create an HTMX_ELEMENT base class with attribute storage via hash table, fluent methods returning 'like Current', HTML escaping for security..."
HUMAN: "Use TEST_SET_BASE for tests, not EQA_TEST_SET."
AI: [Adjusts approach, generates code]
COMPILER: "VKCN(1): Function used as statement"
AI: "Adding .do_nothing to fluent chains to satisfy compiler."

Result: 34 classes, 40 tests, 4 hours.

See It In Action

Watch real development sessions:

The Reference Documentation System

AI works best with context. We maintain living documentation:

When AI reads these first, accuracy goes from ~60% to ~95%.

The documentation captures institutional knowledge. AI gets smarter with every session. Mistakes don't repeat.

The Verification Layer

AI writes code. But who checks AI?

Layer 1: Compiler Type errors caught immediately
Layer 2: Contracts Runtime verification of correctness
Layer 3: Tests Specific scenarios validated
Layer 4: Human Final review and approval

Most AI errors are caught at Layers 1-2. Before human review. Before production.

What Makes It Work

1

Clear Direction

AI needs to know what you want

2

Reference Context

AI needs to know your patterns

3

Rapid Feedback

Compiler/contracts catch errors fast

4

Iteration

Build incrementally, verify continuously

5

Human Judgment

You're always the decision-maker

Productivity Results

40-80x
Measured multiplier
Days
vs. traditional months

This isn't hype. This is measured output.

See the Competitive Analysis