Ahmed Rehan
Agents
Stop guessing what to build. The 2026 AI-startup playbook with receipts: 111 cited sources (Sequoia, YC, NVIDIA, Anthropic, Carta, OpenAI) distilled into a decision system — the autopilot thesis ($6 of services behind every $1 of software), Greg Isenberg's 21 agent-startup categories, GEO/agent-readability, sovereign AI, and the real model-reasoning debate. Ships the evidence, a working idea evaluator, 7 templates, and 25 QA evals.
Design Systems Engineering gives AI agents a disciplined, human-centered workflow for UI/UX, design systems, accessibility, motion, dashboards, design-to-code, and technical handoffs. It is built for real product work where structure, ergonomics, and implementation realism matter more than generic visual taste.
Expert in end-to-end AI-assisted software delivery, from design engineering and design systems to shipping: design engineering, design system automation, technical documentation, spec-driven planning, polyglot code quality, systematic QA, release auditing, LLM context engineering, and Astro frontend optimization. Built for agent-agnostic workflows across the full 9-skill delivery lifecycle.
GSD is a spec-driven, context-engineering workflow for AI coding agents that prevents context rot & ships via the 5-step Discuss→Plan→Execute→Verify→Ship loop closed by /gsd-ship. Backed by a source-verified surface of 65 concrete commands across 6 namespace routers (/gsd-workflow, /gsd-project, /gsd-quality, /gsd-context, /gsd-manage, /gsd-ideate), with optional OpenGSD companions (gsd-pi, gsd-graph + MCP, gsd-loop, gsd-browser). & a `.planning/` directory that the agent reads across sessions.
Built from hands-on work optimizing production Astro sites across static, hybrid, and SSR output modes. Covers the full performance stack: native image optimization with the Astro Image component, View Transitions API integration, prefetch strategies, Dev Toolbar audit workflows, accessibility fixes aligned to WCAG, and Core Web Vitals improvements. Grounded in Astro 3/4/5/6+ internals and real optimization cycles — not generic web performance advice.
Production-grade code quality standards for AI coding agents: no-hacks policy, core values hierarchy, universal clean code principles, language-agnostic pitfalls, multi-stack security checks, and TypeScript-first depth with coverage-gap patterns. Grounded in real production failure modes, with standards and tooling spanning 19 languages.
Generate, audit, co-author, and maintain software documentation. Covers API references, READMEs, changelogs, architecture docs, wikis, comprehensive technical manuals from codebases, co-authored specs/RFCs/design docs/proposals, and agentic spec folders for spec-driven development. Works across software, hardware, firmware, and embedded projects in any language or runtime.
Systematic QA of CLI tools and pipelines across multiple real workspaces using SFDPOT heuristics. Executes structured test flows, evaluates consistency oracles, collects evidence, and produces a structured bug report with P1/P2/P3 priorities and a release readiness verdict.
Verify a versioned software release is genuinely complete — tickets actually implemented (not just closed), docs discoverable (not just present), CI green on all matrix platforms, coverage gated, security scan clean, rollback path tested, and version metadata consistent. Produces a structured READY / NOT READY / BLOCKED report with evidence-backed findings and action items.
Structure project docs as modular memory + reasoning files so AI agents load only what they need — cutting token usage by 70–96% per query. Grounded in Anthropic, LangChain, and Crawl4AI's production llm.txt research. Implements write/select/compress/isolate context engineering strategies.
Connect any MCP-compatible AI agent (Claude, Cursor, Copilot, Codex, Windsurf, Amp, Cline) to Penpot to create, audit, and maintain design systems — tokens, flows, interactions, animations, and design-to-code export to HTML/CSS/React.