{"id":9199,"date":"2026-01-29T21:16:04","date_gmt":"2026-01-30T05:16:04","guid":{"rendered":"https:\/\/visualgdb.com\/w\/?p=9199"},"modified":"2026-01-29T21:16:04","modified_gmt":"2026-01-30T05:16:04","slug":"getting-started-with-ai-edits","status":"publish","type":"post","link":"https:\/\/visualgdb.com\/tutorials\/ai\/quickstart\/","title":{"rendered":"Getting Started with AI Edits"},"content":{"rendered":"

This tutorial shows how to quickly try out the AI editing functionality in VisualGDB with a basic project. We will create the basic USB CDC device from template, and will demonstrate some code writing and refactoring.<\/p>\n

Before\u00a0 you begin, follow this tutorial<\/a> to create a project for a basic USB device, but don’t modify the original template yet.<\/p>\n

    \n
  1. Move the declarations for VCP_read<\/strong>, VCP_write,<\/strong> etc to the usb_cdc_if.h<\/strong> file, so that they match the usb_cdc_if.c<\/strong> file where they are defined. This will allow the AI to place the new functions in the correct file without explicitly asking it to:\"\"<\/a><\/li>\n
  2. Go to the main() function and click the AI edit icon:\"\"<\/a><\/li>\n
  3. Currently, main()<\/strong> reads the USB input one character at a time. Let’s change it to read it line-by-line. Write the following prompt:\n
    +VCP_ReadLine after read & use it<\/pre>\n
    Select the GLM model from the list and click “Go”:\"\"<\/a><\/li>\n
  4. A few seconds later, the model will suggest changing main()<\/strong> itself, adding a declaration to the header file where VCP_read()<\/strong> was defined, and also adding the implementation to the .c file, so that the main loop now works line-by-line:\"\"<\/a>Smaller models (e.g. Qwen or GPT-OSS-128B) would do it even faster (2-3 seconds), but they normally need a bit more specific prompts (e.g. “in @usb_cdc_if.c after VCP_read” rather than just “after read”).<\/li>\n
  5. Let’s refine the edit through another prompt:\n
    +enum ReadLineFlags (rlCR, rlLF, rlEcho). Pass CR+LF.<\/pre>\n
    \"\"<\/a>The model very quickly expands it to adding an enum in the correct place, modifying the declaration, body, and calls to VCP_ReadLine()<\/strong> accordingly.<\/li>\n
  6. Now we will show how the automatic reference updating works. Click “Accept all” and complete the editing session. Then start another one for VCP_ReadLine() and use this prompt:\n
    take maxLen + flags; @malloc , read, return, callers free.<\/pre>\n
    \"\"<\/a><\/li>\n
  7. This was sufficient to change the semantics of VCP_ReadLine(), update declaration, body, and the call in another few seconds:\"\"<\/a><\/li>\n<\/ol>\n
    Unlike the classic AI tools that work on file level, VisualGDB works with individual symbols. Whenever you ask to edit main()<\/strong> that uses VCP_read(),<\/strong> VisualGDB automatically pulls it into the context window. If the AI changes the signature of VCP_ReadLine(), VisualGDB detects it and runs another pass with all references. This works really fast and doesn’t break for large projects with huge files.<\/p>\n
    If you would like to see more real-world examples, check out our tutorial series<\/a> where we used AI to turn an open-source HTTP server for Raspberry Pi Pico into a Web-controlled thermostat.<\/p>\n","protected":false},"excerpt":{"rendered":"
    This tutorial shows how to quickly try out the AI editing functionality in VisualGDB with a basic project. We will<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[253],"tags":[254,61],"_links":{"self":[{"href":"https:\/\/visualgdb.com\/w\/wp-json\/wp\/v2\/posts\/9199"}],"collection":[{"href":"https:\/\/visualgdb.com\/w\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/visualgdb.com\/w\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/visualgdb.com\/w\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/visualgdb.com\/w\/wp-json\/wp\/v2\/comments?post=9199"}],"version-history":[{"count":1,"href":"https:\/\/visualgdb.com\/w\/wp-json\/wp\/v2\/posts\/9199\/revisions"}],"predecessor-version":[{"id":9207,"href":"https:\/\/visualgdb.com\/w\/wp-json\/wp\/v2\/posts\/9199\/revisions\/9207"}],"wp:attachment":[{"href":"https:\/\/visualgdb.com\/w\/wp-json\/wp\/v2\/media?parent=9199"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/visualgdb.com\/w\/wp-json\/wp\/v2\/categories?post=9199"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/visualgdb.com\/w\/wp-json\/wp\/v2\/tags?post=9199"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}