Top all-time · #18141
Arcade Blog
Company blog · blog.arcade.devaiprogramming
Arcade Blog is the company blog at blog.arcade.dev, writing about ai and programming. Since 2025, 4 different Hacker News readers have linked it 10 times. It is still writing: the last post was on 2026-10-29, and you can follow it by feed.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
Linked posts cover building LLM agent tools safely, including how agentic SQL tools can leak database contents and a catalogue of 54 patterns for agent tools. The comments come from the blog's own staff.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Read the latest insights, tutorials, and news on AI agent development, MCP, and tool-calling. Start building better AI with Arcade.
What Hacker News says?
Developer Advocate at Arcade.dev here When building LLM-powered apps, it's critical to always think about boundaries around the data. A common pattern I observe from people building agents is to treat the LLM as a trusted component of the system. This is NOT how to think about LLMs generally. They are inherently gullible and optimized to be agreeable. I've written about agentic SQL tools recently [1]. The gist is th…
Comment linking /text-to-sql-2-0
on “Supabase MCP can leak your entire SQL database”Submitted The Birth of Machine Experience Engineering as a story · 5 points
HN discussionAuthor here (Guru, Arcade). Growing up as an integration engineer, I built my career religiously reading the Enterprise Integration Patterns book from Gregor Hohpe. Content-Based Router, Dead Letter Channel, Claim Check these weren't just patterns, they were how I thought about systems. That book shaped an entire generation of us who built middleware, ESBs, and messaging infrastructure. Two decades later, I found my…
Comment linking /mcp-tool-patterns
on “Agentic Tool Patterns – 54 patterns for building tools LLM agents can use”Submitted We just taught AI agents to complete real purchases as a story · 3 points
HN discussionAnthropic recently introduced Tool Search, which is supposed to let models discover which tool to call without loading thousands of tool definitions into context. We wanted to understand how this behaves under something closer to a real production environment, not a demo with 10–20 tools. So we loaded 4,027 tools (Google Workspace, Slack, GitHub, Salesforce, ClickUp, HubSpot, etc.) and ran 25 simple, unambiguous tas…
Comment linking /anthropic-tool-search-4000-tools-test
on a deleted threadSubmitted Agentic Tool Patterns – 54 patterns for building tools LLM agents can use as a story · 2 points
HN discussionAnthropic recently introduced Tool Search, which lets Claude look up tools dynamically instead of loading everything into the context window. It’s a promising idea, especially if you’re working with large tool catalogs. We maintain ~4,000 agent-optimized tools at Arcade.dev (Gmail, Slack, GitHub, Drive, Zendesk, Salesforce, etc.), so we ran a simple evaluation: 25 straightforward tasks that normally achieve ~100% re…
Comment linking /anthropic-tool-search-4000-tools-test
on a deleted threadSubmitted MCP is missing secure auth as a story · 1 points
HN discussionAnyone who's tried to build a serious AI agent has run into the same blocker: external authorization. Not “is this client allowed to talk to the MCP server?” That’s a different problem. I mean the harder part: How does an agent securely obtain user-level OAuth credentials for systems like Gmail, Slack, Outlook, Jira, Salesforce, etc.? Until now, MCP had no standard way to do this safely. Every real agent demo quietl…
Comment linking /https-arcade-dev-blog-mcp-url-elicitation-production-authorization
on a deleted threadSubmitted Designing SQL Tools for AI Agents as a story · 1 points
HN discussion