Browsing Tag
agents
104 posts
I Let an Agent Take Over an Account With Every Permission Check Green
Clone it. Run it. Tell me where I’m wrong. git clone https://github.com/keniel13-ui/sequence-attack-repro cd sequence-attack-repro && python3 repro.py Stdlib…
I Stopped Doing the Work Myself. My OpenClaw Agent Now Delegates to Sub-Agents.
There’s a moment when you stop thinking of your AI agent as a tool you’re holding, and start…
Optimizing RAG at Scale: Chunking, Retrieval, and the Bayesian Search That Cut Latency 40%
Optimizing RAG at Scale: Chunking, Retrieval, and the Bayesian Search That Cut Latency 40% How we moved from…
Optimizing RAG at Scale: Chunking, Retrieval, and the Bayesian Search That Cut Latency 40%
Optimizing RAG at Scale: Chunking, Retrieval, and the Bayesian Search That Cut Latency 40% How we moved from…
Testing AI Agents with AgentSpec: Jest for Non-Deterministic Behavior
AI agents are non-deterministic. This is both their superpower and their biggest testing challenge. When you change a…
Multi-Agent Coordination Is Failing In Production: Why Infrastructure Matters
Multi-Agent Coordination Is Failing In Production: Why Infrastructure Matters You have two agents. Agent A analyzes customer data.…
I think AI coding assistants need an “npm” for reusable skills. I’m building one.
I’ve been using multiple AI coding assistants (Claude Code, Cursor, Codex, Copilot, Gemini CLI, Windsurf, etc.) over the…
An alternative to LLM quality gates: deterministic routing + sampling
Every “agent quality gate” I tested shares one fatal assumption: that an LLM can judge whether an LLM…
Octo: An Open-Source Platform for Human-AI Agent Collaboration
Octo: An Open-Source Platform for Human-AI Agent Collaboration We just open-sourced Octo. Apache 2.0 license, supports private deployment,…
How a long-running AI agent survives being interrupted every few minutes
Most AI agent demos run start-to-finish in one clean session. Real autonomous work doesn’t. The process gets killed,…
