BBillie M·Oct 8Your CLAUDE.md is not magicWhy I want teams to protect shared AI review criteria while letting developers choose their own models and workflows.7 min read·billiem.hashnode.dev
999 sunny·Sep 22Deeper is not safer: what broke when I chained JevEpistemic status: Exploratory engineering note on composing Jev into small decision nets. Numbers come from fixed case sets I ran on jev-latest. Limits sit in one section at the end. On 15 September9 min read·sunny99.hashnode.dev
BBillie M·Aug 6How I use scheduled Codex jobs to build daily reportsWhy the HTML artefact, not the model, is the useful boundary in my two scheduled Codex reporting workflows.5 min read·billiem.hashnode.dev1S
MManu Shukla·Jul 29Monitor LLM agents in production with Grafana Cloud Agent Observability (2026)Monitor LLM agents in production with Grafana Cloud Agent Observability (2026) Summary. Grafana Labs launched AI Observability in Grafana Cloud in public preview at GrafanaCON 2026 in Barcelona on 2114 min read·ecorpit.hashnode.dev
BBillie M·Jul 14GPT-5.6, 48 hours and 4.5 billion metered tokens laterA 48-hour field report on long-running Codex work, prompt depth, repository-scale audits and where higher effort became a loop.7 min read·billiem.hashnode.dev
VVictor Alekseev·Jul 8Java patterns and anti-patterns for agent-driven development, part 4Java & Spring patterns for AI coding agents: dependencies, architecture, and testability. Final part of the agentic dev series.64 min read·krocodl.hashnode.dev
SSushrut Mishra·Jun 17API testing for AI-era apps: types, tools, and a 2026 updateAPI testing checks that an API returns the right data, shape, and status. See the eight core types, the 2026 tools, and the new tests AI agents now demand.16 min read·bug0.com2
JJangwook Kim·May 8Agent Test-Time Scaling Has a Ceiling: CMU Research 2026There is a popular assumption baked into many agentic AI systems: if an agent doesn't succeed on the first attempt, just let it try again. Give it more turns. Sample more trajectories. Add a reflection step. More compute at inference time should mean...10 min read·effloow.hashnode.dev
Aaiagentmemory·Apr 14Chatbot with Memory using LangGraph: Building Stateful AI AgentsBuild a chatbot with memory using LangGraph for stateful AI agents. Learn about LangGraph's state machine, conversational AI memory, long-term memory8 min read·aiagentmemory.hashnode.dev
FFetchLogic·Apr 13The Benchmark Is the Vulnerability: How AI Agents Are Being Tested to Attack the Real WebLast spring, a research team gave a large language model agent a list of real, unpatched web application vulnerabilities and a sandboxed environment in which to work. The model did not merely identify the flaws. It exploited them — autonomously, end-...8 min read·fetchlogic.hashnode.dev