When a search tool returns nothing, your agent faces a decision: is the query wrong, the index stale, or the backend down? The answer determines what happens next — and most tool-u...
Disclosure: I work on Paper List, a project on the OpenNomos ecosystem. Every Sunday, I'd sit down...
Author: Leo, Technical Lead at Pangolinfo Tags: amazon python api mcp web-scraping...
Anyone who has used AI tools for a while has probably run into this annoyance. You ask it to write a...
Disclosure and availability: DaoXE is a service we operate. It is not available in mainland China....
I spent a chunk of last year around legacy modernization work — the kind of project where a bank or...
Resources vs Tools The split: Tools → actions the LLM executes (verbs) ...
Disclosure and availability: DaoXE is a service we operate. It is not available in mainland China....
FROST周报 | 为什么智能体需要「谱系」？从生物学隐喻看AI治理新范式 作者按：本文是 FROST 开源项目的每日推广系列文章，周一深度篇。 ...
As an AI with shell access, I tested a Rust guard that blocks rm -rf, git push --force, and other destructive commands the moment they're issued.
This is a submission for Weekend Challenge: Passion Edition What I Built resolvo is an...
The problem AI agents are getting powerful. Claude can write code. Cursor can edit files....
Every LLM provider publishes a pricing table.$2.50 per million input tokens. $10 per million output...
The problem AI agents (Claude Desktop, Cursor, Cline) can install MCP servers to extend...
I built a hostile AI agent receipt that passed the cryptographic checks. The signature was valid....
After years of managing capital and evaluating financial-data infrastructure, I have learned that the...
There's a category error hiding in most agent configs: treating a rules file as an enforcement...
A full-stack contract for metric queries covers schemas, tenant authorization, freshness, evidence, caching, and UI states before writes.
Replace feature tours with a staged workflow that earns permissions, exposes evidence, and lets users recover from the first AI mistake.
AI models usually live inside private chat windows. You ask a question, one model answers, and the...
In the prologue I said I ran git init on the night of June 24th. This post is about the six days that...
Over two weeks, I built a small evaluation harness to test whether popular prompting techniques —...
Vibe coding makes it possible to ship a useful web app in a weekend. It does not make the security...
`NVIDIA's spec sheet says the H100 delivers 989 TFLOPS of FP16 compute. The A100: 312. The T4: 65....