← Back to all playbooks

Paula

PAULA DOZSA: iOS app with zero experience
Start: 03:31:00
Sketch note for Paula's session
TL;DR

Transition from 'vibe coding' prototypes to production-grade engineering by treating LLMs as onboarded teammates through structured markdown 'skills,' automated build-and-fix agents, and multi-model review pipelines.

Key Insights

Physics-Aware UI via Asset Prompting

03:36:02

Claude can generate complex SpriteKit animations by processing raw image assets and Figma screenshots; it successfully handles physics-based rotations and easing that often exceed the fidelity of the original design.

The 'Tribal Knowledge' Markdown Strategy

03:49:53

Prevent generic, incompatible AI code by encoding architectural patterns (dependency injection, GraphQL conventions, specific Swift flavors) into markdown 'skills' files that act as a permanent onboarding manual for the LLM.

Multi-Model Tiered Review Pipelines

03:52:31

Optimize review accuracy by assigning specific models to specialized agents: use Opus for high-level logic review and Sonnet for lower-level pattern and syntax consistency.

Non-Engineer Production Contributions

03:46:37

By integrating Claude with Slack and GitHub, designers can open functional PRs; the system's pre-defined 'skills' and review agents ensure the code meets production standards before an engineer ever sees it.

Systems

The PR Shepherd Workflow

  1. Tag Claude in Slack with a task or Linear ticket link.
  2. Claude identifies the repo (iOS or Backend) and opens a PR.
  3. Logic Review Agent (Opus) and Pattern Review Agent (Sonnet) automatically comment on the PR.
  4. Shepherd Agent reads the comments, refactors the code, and re-commits until review bots are satisfied.
  5. Human engineer performs the final sanity check and merge.
Tools: Claude, GitHub, Slack, Linear

The Build-Fix Loop Agent

  1. Configure an agent with access to the local or CI build environment.
  2. Agent triggers a build command after code generation.
  3. Agent captures the compiler error logs and stack traces.
  4. Logs are fed back to Claude to identify the specific line and logic failure.
  5. Claude iterates on the fix and re-triggers the build until success.
Tools: Xcode/Swift, Claude, CI/CD Runner

Tools

Claude (Opus & Sonnet)SpriteKitUnityGraphQLApolloGitHubLinearSentryFigmaDatadogPostHogSlack