{
  "id": 15350297,
  "title": "Why I Want My AI Coding Assistant to Ask Before It Acts",
  "url": "https://urgent.news/2026/10/18/why-i-want-my-ai-coding-assistant-to-ask-before-it-acts",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-18T04:53:21.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/arcwrightai/why-i-want-my-ai-coding-assistant-to-ask-before-it-acts-30eo"
  },
  "original_language": "en",
  "account": "AI coding assistants promise speed, but their rapid action can come at a cost. These tools often edit files unexpectedly, delete crucial elements, or execute commands without explicit permission. The result is time spent undoing work that wasn't approved. While this may be acceptable for simple scripts, it's problematic for substantial codebases.\n\nThe issue isn't dramatic but insidious: a helper function might be \"cleaned up,\" causing subtle breakdowns, or a config file could be rewritten with different values, rendering everything useless the following day. What I desire is an assistant that considers my codebase as belonging to someone else. This means asking before writing, showing the change for approval, and displaying detailed diffs instead of vague summaries.\n\nWhen updating auth logic, a simple message like \"I updated the auth logic\" doesn't provide enough information. A detailed diff, on the other hand, reveals the changes comprehensively. Moreover, every step should have checkpoints. If step 4 goes wrong, it's preferable to rewind to step 3 rather than starting over. Granting permission for shell commands should be closely monitored, as they are the most powerful actions an AI can perform.\n\nAlthough this approach may be slower per action, it's much faster per outcome, as I won't waste time fixing unapproved changes. For Windows users seeking an AI editor that operates this way, Arcwright offers a free solution. However, the principle can be applied to any tool: the AI should earn trust through approved changes, one at a time.",
  "summary": "Most AI coding tools are built around one promise: speed . Type a prompt, get code, move on. But after a while I noticed the speed was costing me something. The AI would edit files I didn't expect, delete things I still needed, or run a command I hadn't read. I'd spend the next hour undoing work I never approved. The problem with \"just do it\" AI When an AI agent has full permission to write,…",
  "key_points": [
    "AI coding assistants act without permission, causing time loss.",
    "Detailed diffs and checkpoints prevent widespread code damage.",
    "Arcwright provides a free AI editor that asks before acting."
  ],
  "editors_take": "Prioritizing granular oversight and explicit permission over sheer speed transforms the AI coding experience from a risky automation process into a reliable partnership built on verifiable developer control.",
  "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."
}