Start here · The map before the archive
This is the shortest path into the site's thinking.
chudi.dev is a living knowledge system about AI product development, bug bounty automation, and neurodivergent systems design. Use this page if you want the map before the archive.
§1 · Three journeys · Pick the one that matches why you came
- 01 AI Visibility Engineering Engineer entity graphs, schema, and retrieval surfaces for sub-DR-20 brands. Optimize for AI citations first, SERP rank second.
- 02 AI Product Development Claude Code, WebMCP, RAG, verification, and micro-SaaS execution patterns for builders who want production-grade AI systems instead of prompt theater.
- 03 Neurodivergent Systems ADHD cognition as a systems advantage: pattern recognition, resilient workflows, and engineering scaffolds that actually fit the way your brain operates.
§2 · Best entry points by intent
If you are here for a specific outcome, start with these.
Build AI systems that survive contact with production
Start with Claude Code workflows, then move into WebMCP, context control, and verification loops.
Claude Code Best Practices 2026: What the Official Docs Don't Cover
Claude Code best practices for 2026, field-tested across 36K lines of shipped code: quality gates, multi-agent orchestration, and the workflows the official docs don't teach.
SvelteKit MCP: Add WebMCP in 90 Minutes and 3 Files
SvelteKit MCP implementation guide: build WebMCP into SvelteKit with navigator.modelContext. Polyfill setup, tool schemas, and verification, in 90 minutes and 3 files.
How to Test AI-Generated Code Before Shipping: 57 Bugs Caught
How to test AI-generated code before shipping it: the evidence-based verification gates that caught 57 bugs. Forced evaluation beats "it should work", 84% compliance vs 20% for passive checks.
Automate security research without automating away judgment
Use the bug bounty system sequence if you care about evidence, false-positive control, and human-in-the-loop design.
Bug Bounty Automation Framework: Zero False Positives
A bug bounty automation framework that cuts false positives to zero: the 4-agent evidence-gating architecture, what it costs to run, and what it takes to build one for your own security program.
Human-in-the-Loop AI: Why It Beats Full Automation for Security Tools
Keep humans in control when building AI security tools. Full automation sounds impressive until your reputation tanks from false positives.
Use ADHD cognition as a systems advantage
The neurodivergent track reframes pattern recognition, abstraction, and chaos resilience as engineering leverage.
GTD for ADHD Doesn't Work: The Energy-Based System I Built Instead
GTD doesn't work for ADHD brains. The energy-aware productivity system I built instead, hyperfocus scheduling, AI processing, and the workflow I use to ship.
I Have 73 Browser Tabs Open. ADHD Made Me a Better Architect.
Five ADHD cognitive traits mapped to real systems architecture patterns: pattern recognition, parallel processing, novelty seeking, and chaos resilience.
Claude for ADHD: There's No Plugin, Here's My Workflow
No, Claude has no built-in ADHD mode or plugin. The 5-step workflow I use instead to beat task-initiation paralysis and context-switching.
§3 · The visibility stack
If you came for the machine surfaces, they are all public.
Every machine-readable surface on chudi.dev is listed, live, and inspectable. This is the working model the writing documents.
Want the tools instead? See the products · Want help applying the patterns? Work with me
- How ChatGPT and Perplexity Decide Which Sources to Cite The six measurable factors answer engines use to pick sources, with 2026 platform data on how ChatGPT and Perplexity actually cite, and how to fix each one.
- Get Cited by ChatGPT and Perplexity: 5 Concrete Steps Yes, ChatGPT, Claude, and Perplexity can crawl your site: here are the exact crawler user-agents to allow in robots.txt and how to verify it worked.
- llms.txt for AI Crawlers: Why robots.txt Is Not Enough robots.txt was built for search engines, not AI crawlers. llms.txt gives LLMs structured context about your site that robots.txt can never provide.
Subscribe once. Get the guided version of the site.
The newsletter is the shortest path to the newest systems notes, strongest essays, and the next recommended reading path.
- ADHD and Claude Code workflow systems that actually hold up
- AI systems and Claude Code implementation notes
- Bug bounty automation architecture and failure loops