Full-text search across 60185 articles. Combine with topic and date filters; results sorted by relevance.
Developers are adopting hybrid retrieval strategies that combine semantic vector search with lexical keyword matching to overcome the limitations of pure vector search in production-grade RAG systems. A new no-code Memor…
A developer describes shifting from using LLMs as occasional third-party dependencies to adopting an agent-driven execution model where the agent loop serves as the primary environment, relegating deterministic code like…
Anthropic has released Dynamic Workflows for Claude Code, a research preview feature that enables the AI to coordinate multiple agents in parallel for complex software engineering tasks. The system automatically generate…
A developer building an AI-powered video editing tool implemented silent self-correction for LLM-generated code failures, achieving a 90%+ success rate. Instead of showing users raw Python tracebacks, the system feeds er…
A developer built a Claude Code plugin that enforces brand voice rules by automatically scanning drafts for banned terms, em-dashes, and AI tells before publication. The plugin caught 31 em-dashes, 9 banned words, and 4 …
A developer argues that the key to improving AI coding agents is not crafting larger prompts but building a small context system around them. The approach leverages context engineering and the Model Context Protocol (MCP…
A developer created the open-source tool `@mongez/agent-kit` to solve the fragmentation of AI coding agent instructions across different tools. The CLI and TypeScript library derives per-agent files—including `CLAUDE.md`…
A developer released a tool that prevents parallel AI coding sessions from overwriting each other's handoff files. The solution uses a PreToolUse hook that enforces ownership markers on handoff files, blocking writes fro…
A developer has outlined a method for restricting PostgreSQL permissions when connecting AI coding tools like Cursor, Claude, and Copilot to databases. The approach involves creating a dedicated PostgreSQL role with only…
Lisa Lin, a 33-year-old non-technical operations professional and new mother, used the AI app builder Lovable to create Nutribabe, a nutrition app that provides daily checklists for introducing solid foods and allergens …
Researchers have introduced Agyn, an open-source platform designed to deploy and operate AI agents at scale in production environments. The platform provides a signal-driven, stateful serverless runtime on Kubernetes, a …
A child used the AI-assisted tool Vibe Coded to learn math, marking a practical classroom application of large language model technology. The case highlights ongoing friction for teachers and professors who struggle to i…
LogiFlow completed a 15-week technical overhaul, surviving Black Friday without a single alert while reducing infrastructure costs by 60%. The team formalized "The LogiFlow Engineering Manifesto," establishing that AI ca…
A developer pushed a cleanup to production targeting background worker performance issues, enforcing strict log rotation and terminating stagnant threads. To power a data pipeline for fast cryptocurrency trades, the deve…
A team building a self-improving knowledge base called Morsel developed a method to structure technical documentation for use by local AI coding agents. The process classifies pages using rules and a local LLM, embeds co…
A developer has created a "harness engineering" approach to eliminate the need for re-prompting coding agents in every new session. Instead of relying on session-scoped prompts that disappear, the method stores durable a…
Federico Viticci of MacStories launched Shortcuts Playground, a plugin for Claude Code and Codex that generates Apple Shortcuts automations from natural language prompts. The tool allows users to create any shortcut by s…
Trend of "vibe-coded" solutions, which are AI-generated or AI-wrapped fixes that address problems that do not actually exist. It criticizes this approach as a superficial application of technology, where common sense is …
A common bug in their coding agent where the system remembered the conversation session but not the actual work task, causing failures when users switched channels or followed up on previous jobs. To solve this, they red…
In the 51st episode of the Software Freedom Podcast, the FSFE discusses challenges for Free and Open Source Software in public administration with guests from the Nordic Institute for Interoperability Solutions (NIIS), f…