70 stories
Two statements about Claude Code mods, both true, both from Anthropic's own docs: The module runs in a sandbox of its own, with no DOM and no Node. "Mods aren't sandboxed." The first two days of the mods launch have been one long argument about which of these is the lie. Neither is.
Originally published at AI Agent Security: The Runtime Surface Around Every Tool Call on smartgate.network. A shorter version of "AI Agent Security: The Runtime Surface Around Every Tool Call" — the full piece lives at smartgate.network.
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content What I Built A few weeks ago, I was checking my DEV.to dashboard and noticed something weird in the Traffic Sources panel.
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content What I Built True Oath is a political accountability ledger starting with Australia and designed to expand to other countries.
I run a handful of agents on my laptop. One files notes for me, one answers questions about my projects, one watches news and tells me when something matters. Each of them is fine on its own. Together they are forgetful in a way that took me a while to name.
Last Friday, while cross-debugging a payment refactoring branch, I had Cursor open on my left monitor for frontend reviews and Claude Code running in my terminal on the right. To let both AI assistants inspect database schemas and query logs, I hooked up 4 MCP servers to each environment.
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content What I Built Let me introduce you to Ananya. She's made up, but you probably know someone exactly like her. She's 31, works in Pune, and has spent eight years saving for her first flat.
When I work with coding agents I usually have a few things going at once, and after a couple of sessions I no longer know what's finished, what's half done and what's waiting on me. I tried a TODO.md, but I never looked at it. Jira or Linear felt silly for a one-person project.
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content. What I Built I started this challenge knowing almost nothing about Sanity. Eurorack was new to me too.
Threat Modeling the Model Context Protocol: Securing Agentic Tools with mcpscan The Model Context Protocol (MCP) has emerged as an open standard connecting LLM interfaces (such as Claude Desktop and Claude Code) to local and remote execution environments.
The Model Context Protocol solved the server-side fragmentation problem so thoroughly that a client-side one replaced it: six popular AI tools now speak MCP, and each one has its own config file, its own UI path, its own rules about where environment variables may come from, and its own tolerance…
Testing an MCP server through an AI client is a slow way to work. You type a natural-language prompt, hope the model picks the right tool, watch it fill in arguments, and if anything fails you cannot tell whether the bug is in your server, the model's reasoning, or the prompt.
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content What I Built Ask most award-travel tools "what's the cheapest way to fly SFO to Tokyo in business with my points?" and you get a confident number. Ask where the number came from and things get vague.
This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange. What I Built Veyd is a project workspace for researching documents with a clear path back to the source.
The first week of using a coding agent against your company's API is always the same: paste the docs URL into the prompt, correct the base path, correct the auth header, correct the pagination type, correct the envelope wrapper, repeat in every new session and every new tool.
When teams start connecting APIs to AI agents, three terms arrive together and get used interchangeably: function calling, ChatGPT plugins, and the Model Context Protocol (MCP).
You have a topic. You open your AI assistant and start typing. First you explain your blog: who reads it, how you write, what you covered last month. Then the topic. The draft comes back sounding like every other draft. You ask for a title. Then a summary. Then a search description and some tags.
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content What I Built Imagine remembering clearly that you left your keys on the kitchen counter, only to find that they aren't there. Someone tells you that you never left them there, but you remember doing it.
Showing 36 of 70 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news from Dev.to AI
Join 15,000+ AI enthusiasts
