1,108 stories
This release introduces the built-in MCP Server, Extensible Tokenizers, Diversity Search (MMR), and Query Profiling as previews, along with Incremental Backups, Gemini audio support for multi2vec-google, and the new BlobHash property type.
Most database performance problems are query plans, not hardware. How to find them, what indexing really costs you, and when to scale up instead.
Every schema has a public card and a private package. This is where we draw the line and why the line matters.
What data engineers actually do now that pipelines became a commodity, which parts of the job automate away, and which judgement calls never will.
Data connectivity lets systems share data so questions can span them. How it works, and how it differs from application and data integration.
We replaced expensive sandboxes with ChromaFs, a virtual filesystem over Chroma, to give our docs AI assistant the ability to explore documentation like a developer would.
Discover how AI-driven testing replaces brittle QA automation, cuts bottlenecks, and helps modern teams ship faster with more confidence.
This isn't about autocomplete anymore, or a slightly smarter Clippy. We're talking about a bot that took a feature request from a chat message, understood the business context, scanned the entire codebase, and opened a production-ready Pull Request. It did it in 20 minutes.
Managing a coding CEO isn't about stopping them from coding. It's about building a padded room where they can do cool karate moves without breaking the furniture.
Move beyond simple tool-calling agents. LangChain's middleware API lets you inject user preferences before model calls and orchestrate complex workflows after tool execution—turning brittle super-tools into composable, testable layers.
Hidden context messages keep user-facing LLM chats clean while giving the model rich, per-message instructions—turning conversations into a predictable, tool‑driven workflow engine with a tiny amount of code.
Label some data, align LLM-evaluators, and run the eval harness with each change.
Based on what I've learned from role models and mentors in Amazon
Beta testing is the stage where real users test a nearly finished software product in a production environment before its official release. It’s the final checkpoint to uncover bugs, validate usability and confirm market readiness.
Technical debt is the implied cost of additional work created when a team prioritizes faster delivery over the most achievable or maintainable solution.
How Dropstone uses Tree-sitter for Abstract Syntax Tree parsing to achieve deep semantic understanding of code across 40+ programming languages, enabling accurate analysis and intelligent suggestions.
A pragmatic schema for AI billing: events, price versions, costs, invoices, and outcomes—so eng doesn't rebuild it twice.
Instrument three signals, simulate pricing on historical data, and start collecting cash—without a 6-month project.
Showing 1,098 of 1,108 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
