Home/Blog/Show HN: I made a guardrail against AI outreach slop (API/MCP)BackendShow HN: I made a guardrail against AI outreach slop (API/MCP)Hacker News Show2026-11-07 21:480 viewsArticle URL: https://maildignity.com/ Comments URL: https://news.ycombinator.com/item?id=50404494 Points: 3 # Comments: 0Source:https://maildignity.com/My favoritesPreviousShow HN: Chrome extension to block sites and increases attention spanNextThe Second Photonic Shock: A ModelRelated postsEliminating Support Escalations Through Human-in-the-Loop Feedback Loops and Persistent State MemoryBy Hari Krishnan, Lead Orchestration and Autonomous Agent Engineer, Autofix-AI About the Author Hi, I'm Hari Krishnan. O0dev.toWho's Allowed to Add Work to Your Agent's Queue?I once handed an agent thirty seed URLs and a crawler and went to make coffee. It came back with four thousand. Nothing 0dev.toAllowed to view the Location, handed the Device: a GraphQL permission gap in Nautobot (GHSA-mfwj-pjgx-22v2)TL;DR What: Nautobot 's GraphQL API enforced object permissions at the root of a query but not when a query traversed in0dev.toHow Hindsight Changed My SEO Optimisation WorkflowHow Hindsight Stopped My SEO Agent From Tanking CTR Most software regressions break a test suite or trigger a 500 alert 0dev.toBuilding an Agent-Aware LLM Gateway from First Principles in Node.js🔗 GitHub Profile: github.com/sawastik7-bit 🚀 What I’m Building Right Now Instead of relying on out-of-the-box abstractio0dev.toFree restaurant software with a 1% fee: where Thmenu stands after two months, in numbersThmenu is a restaurant platform with one pricing rule: every feature is free, and the only revenue is 1% of the payments0dev.to