{"id":409,"date":"2026-07-26T02:18:47","date_gmt":"2026-07-26T02:18:47","guid":{"rendered":"http:\/\/www.sugata.in\/?p=409"},"modified":"2026-07-26T02:18:47","modified_gmt":"2026-07-26T02:18:47","slug":"ai-coding-assistants-wafs-and-the-critical-need-for-quality-control","status":"publish","type":"post","link":"http:\/\/www.sugata.in\/index.php\/2026\/07\/26\/ai-coding-assistants-wafs-and-the-critical-need-for-quality-control\/","title":{"rendered":"AI Coding Assistants, WAFs, and the Critical Need for Quality Control"},"content":{"rendered":"

My first attempt at programmatically drafting a modern wordcloud analysis on this site was a valuable exercise in pairing AI agents with real-world deployments. While the initial draft showcased the power of autonomous AI development, it also revealed a series of unexpected hurdles\u2014highlighting the critical importance of Quality Control (QC)<\/strong> and iterative human-in-the-loop review.<\/p>\n

The Deployment Hiccups<\/h3>\n

Deploying code in isolation is easy, but placing it into a live environment with firewalls and active configurations rarely goes perfectly on the first try. Here is what we ran into:<\/p>\n

    \n
  1. Firewall (WAF) Interception:<\/strong> When attempting to save the post HTML containing the Python script via Gutenberg’s REST API, the server’s LiteSpeed Web Application Firewall (WAF) threw a 403 Forbidden<\/code> error. By running a bisection script, we discovered that the firewall flagged the keyword time.sleep<\/code> in the python code block as a signature for a potential SQL injection or DOS exploit. Removing this single line allowed the content to save natively.<\/li>\n
  2. Broken Image Paths:<\/strong> The uploaded assets were originally linked using absolute URLs. Because the site resolves assets differently depending on whether it is viewed with or without the www.<\/code> prefix, the browser blocked the image rendering. Switching to root-relative paths (e.g. starting with \/wp\/wp-content\/uploads\/...<\/code>) resolved the rendering across all domain configurations.<\/li>\n<\/ol>\n

    The Stale Data Problem: Blindly Trusting Feeds<\/h3>\n

    Perhaps the most significant lesson came from the generated CNN wordcloud itself. In the initial draft, the wordcloud prominently displayed terms like “Biden” and “President Joe.” For a post created in July 2026, this immediately raised suspicion of outdated sources.<\/p>\n

    Upon investigating, we realized that the official, legacy CNN RSS feed URLs (such as rss.cnn.com\/rss\/cnn_topstories.rss<\/code>) are no longer actively maintained. Rather than failing with a 404, CNN’s servers serve a frozen XML file from April 2023<\/strong>. The AI agent, when instructed to fetch the feed, parsed it successfully and generated a wordcloud based on news from three years ago, completely unaware that the data was stale.<\/p>\n

    QC and Iterative Refinement<\/h3>\n

    This discrepancy underscores why AI-generated outputs must undergo quality control. Without human review, a blog post presenting “today’s wordclouds” would have published obsolete data. To correct this, we iterated on the process:<\/p>\n

      \n
    1. Live Feed Correction:<\/strong> We updated the CNN data source to fetch live news search feeds from Google News (targeting site:cnn.com<\/code>), which indexes real-time articles from today (July 2026).<\/li>\n
    2. Stopword Filtering:<\/strong> The first set of wordclouds was cluttered with common filler words like “will,” “say,” “said,” and others. We implemented a much more restrictive stopwords dictionary to filter out these auxiliaries, leaving only the key thematic news terms.<\/li>\n<\/ol>\n

      The Refined Wordclouds (Today)<\/h3>\n

      Here are the corrected, live wordclouds generated using the updated crawler and restrictive filtering:<\/p>\n

      \n
      \n

      Live CNN Wordcloud (Today’s Real-time News)<\/h4>\n

      \"Refined<\/p>\n<\/div>\n

      \n

      Live BBC Wordcloud (Today’s Real-time News)<\/h4>\n

      \"Refined<\/p>\n<\/div>\n<\/div>\n

      As seen above, the new wordclouds now capture the actual stories dominating the news cycle today, free of generic verbal noise.<\/p>\n

      \n

      Prompt used to create this post<\/h4>\n

      \"Prompt<\/p>\n

      Prompt used to create this post.<\/p>\n<\/div>\n

      \n

      Note: This post documenting the iteration and quality control process was automatically drafted and published by the Antigravity Coding Assistant<\/strong>.<\/p>\n","protected":false},"excerpt":{"rendered":"

      My first attempt at programmatically drafting a modern wordcloud analysis on this site was a valuable exercise in pairing AI agents with real-world deployments. While the initial draft showcased the power of autonomous AI development, it also revealed a series of unexpected hurdles\u2014highlighting the critical importance of Quality Control (QC) and iterative human-in-the-loop review. The […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"http:\/\/www.sugata.in\/index.php\/wp-json\/wp\/v2\/posts\/409"}],"collection":[{"href":"http:\/\/www.sugata.in\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.sugata.in\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.sugata.in\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.sugata.in\/index.php\/wp-json\/wp\/v2\/comments?post=409"}],"version-history":[{"count":3,"href":"http:\/\/www.sugata.in\/index.php\/wp-json\/wp\/v2\/posts\/409\/revisions"}],"predecessor-version":[{"id":418,"href":"http:\/\/www.sugata.in\/index.php\/wp-json\/wp\/v2\/posts\/409\/revisions\/418"}],"wp:attachment":[{"href":"http:\/\/www.sugata.in\/index.php\/wp-json\/wp\/v2\/media?parent=409"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.sugata.in\/index.php\/wp-json\/wp\/v2\/categories?post=409"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.sugata.in\/index.php\/wp-json\/wp\/v2\/tags?post=409"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}