Feb 16 – 22, 2026
7 days. 135 commits. One human steering.
cre8 is a real-time collaborative whiteboard built in a single week — Claude Code generated the code while a human drove architecture, design, and debugging decisions.
Claude Code wrote ~90% of the codebase — but the direction was entirely human-driven. The most valuable human contributions were architectural: choosing zustand over Redux, separating RTDB (high-frequency cursors) from Firestore (persistent objects), and designing the "AI describes, layout engine positions" pattern for architecture diagrams.
47% of sessions were bug fixes, not new features. The real value of AI coding isn't "build faster" — it's "fix faster." Claude excelled at reading 10+ files, understanding state interactions, and finding root causes across multi-file codebases.
Claude Code Messages
Sessions
Lines Written
Files Touched
Median Response Loop
Goals Achieved
Primary dev agent — ~90% of code
Architecture planning sessions
AI observability — every LLM call traced
Codebase compression for AI analysis
AI command cost dropped from $0.014 to $0.004/call by trimming the system prompt from ~8K to ~1.9K input tokens. Same model (Haiku 4.5), just less wasted context.
Switching AI commands from Sonnet to Haiku cut cost per call from $0.051 to $0.006. Quality was sufficient for tool-use tasks — simpler output, but good enough.
Natural language board manipulation
GitHub repo → architecture visualization
Still in active development — feature launched today. Uses Repomix + Sonnet 4.6 to analyze any GitHub repo and generate a visual architecture diagram on the canvas.
$0.004/cmd · projected monthly cost by user scale
"Review PRD.md. We're missing a core feature: Connector.tsx — lines and arrows between objects. This needs to work correctly on the first attempt without introducing bugs. The UX should feel smooth and intuitive like Figma — users click and drag an arrow to connect two elements. Establish a plan and implement it."
Working connectors with endpoint snapping, shipped in a single session with zero regressions
"Review the current implementation and analyze progress. Determine a readiness score (1-10) for implementing the final major feature — AI collaboration. Write a phased plan to implement the AI features in a way that builds on existing architecture."
Scored 8/10 readiness. Delivered a phased plan: tool schemas → simulate function → API route → chat UI
"Build a feature that takes a GitHub repo URL and generates an architecture diagram on the canvas. Use Repomix to compress the repo, Claude Sonnet to analyze the structure, and a deterministic layout engine to position everything. The AI should only describe the architecture — the layout engine handles all positioning."
Clean separation of concerns — Claude describes, layout engine positions. Same repo always produces the same diagram.
Seven days of AI-first development surfaced a clear pattern: the mistakes and wins are two sides of the same coin. Every failure pointed directly to a working principle.
Day 4 burned the most tokens but was the least productive. Vague instructions like "make it faster" produced sprawling, broken changes.
Breaking the same refactor into focused, sequential steps with verification between each produced working code. Feed Chrome DevTools traces, not symptom descriptions.
Development became reactive — fixing whatever felt urgent instead of building against the spec. Features drifted from the original plan.
53 wrong-approach redirects across 76 sessions. AI agents over-engineer constantly. The human value is catching bad paths early — 72% of sessions still hit their goal through active course correction.
119 unit tests but no Playwright tests. Fixing one bug would unknowingly break another. Even 5 integration tests would have saved hours.
Wiring Langfuse on day 3 gave visibility into token counts, latency, and cost per trace. That data drove the Sonnet → Haiku migration with confidence instead of guesswork.
The architectural takeaway: separate AI judgment from deterministic logic. Architecture diagrams work because Claude only describes the structure while a layout engine handles positioning — nondeterministic reasoning paired with deterministic rendering produces consistent output every time.