{
  "id": 10080927,
  "title": "Will It Stack? An agent that knows which Raspberry Pi HATs fight over the same pins",
  "url": "https://urgent.news/2026/09/26/will-it-stack-an-agent-that-knows-which-raspberry-pi-hats-fight-over",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-09-26T22:41:58.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/anur4ag/will-it-stack-an-agent-that-knows-which-raspberry-pi-hats-fight-over-the-same-pins-4kl4"
  },
  "original_language": "en",
  "account": "<Will It Stack? An agent that knows which Raspberry Pi HATs fight over the same pins>\n\nThis interactive tool, called Will It Stack, determines whether various Raspberry Pi add-on boards can share the same 40-pin header. It was created by an autonomous AI coding agent named Claude Code, which wrote the code and built the content model and knowledge base for Sanity. A second AI agent reviewed the work before it was published.\n\nThe tool answers questions about whether specific boards can coexist on a Raspberry Pi's 40-pin header. For example, it shows that a Fan SHIM and Inky pHAT both read physical pin 11 (GPIO 17) simultaneously, causing a conflict. In another case, an AB Electronics ADC Pi and RTC Pi stack together after making a change to the MCP3424 I2C address.\n\nTo determine compatibility, the tool gathers information on each board's header pin usage, I2C addresses, HAT ID EEPROM presence, and physical capabilities of the Raspberry Pi's silicon. It searches for this data using keyword searches over product pages and checks it against a structured record. The verdict is generated based on the information found, not manually generated.\n\nThe tool gathers its data through GROQ queries, deterministic check_stack tools, and a Sanity Knowledge Base. It reads the Knowledge Base for fixes and caveats, such as address jumpers, dtoverlay lines, and Pi model differences. A live demo is available at <https://will-it-stack.vercel.app>.\n\nTo use the tool, simply pick the desired Raspberry Pi board and model, and the agent will run the checker without using any of its tool quota. Every tool call is shown, including the GROQ query, Knowledge Base paths, and a 40-pin header diagram. The agent also flags any citations to Knowledge Base entries it didn't use in the answer. The source code for the tool can be found at <https://github.com/anur4ag/will-it-stack>.",
  "summary": "This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content How this was made: Will It Stack was built end to end by Claude Code, an AI coding agent, running autonomously on @anur4ag 's behalf. It picked the idea, signed into services through their logged-in browser, wrote the code, built the Sanity content model and Knowledge Base, ran the evaluation and…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}