75 stories
AI Search in LangSmith is a new way to query traces using natural language. Describe the behavior you're looking for, and LangSmith returns the traces where it happened.
Claude Code led both Q3 2026 developer surveys, Codex grew fastest on GitHub and npm, and Copilot's vendor and survey numbers split. Data and method.
Coworker AI compares 10 LiteLLM alternatives, from Bifrost and Portkey to Kong, Cloudflare and OpenRouter, with October 2026 pricing, licenses and hosting.
More than a year ago I wrote a few posts here that recommended people not to load custom tools into their context (or MCP servers) but to just use more scripts. Most importantly I wrote that Code Is All You Need and I wrote about that MCP needs code.
This article covers building robust Python AI libraries specifically, Python AI SDK best practices, and what separates a production-ready AI package from one that only survives in its own demo.
Compare 10 AI tools for real estate investors, from deal sourcing and rental analysis to valuations and CRE deal management, with features, reviews, and pricing.
Compare six open-source AI agent frameworks by language, workflow control, tools, and use case, including Mastra, LangGraph, CrewAI, and Pydantic AI.
Compare 9 AI agent observability tools on what each shows for a multi-step run: handoffs, sessions, MCP calls, agent evaluators, framework support and hosting.
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content What I Built A few weeks ago, I was checking my DEV.to dashboard and noticed something weird in the Traffic Sources panel.
12 hours after GPT-6.1 Sol launched, 3 of 10 AI libraries knew it. LlamaIndex raises ValueError; LangChain returns an empty profile. Probe inside.
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content What I Built Ask most award-travel tools "what's the cheapest way to fly SFO to Tokyo in business with my points?" and you get a confident number. Ask where the number came from and things get vague.
Manage AI models, prompts, evaluations, rollouts, and production performance with a practical AI model management workflow.
In the volatile landscape of 2026, manual trading is a relic. The market moves too fast for human reaction times, and the data volume is too vast for unaided analysis. Building a crypto signal bot powered by AI APIs is no longer just an advantage; it is the baseline requirement for serious traders.
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content. What I Built Ask what happens when a goalkeeper holds the ball too long. Then ask the same question about a match on 1 March 2025. The wording barely changes. The applicable rule does.
Most AI workflows run on a single model. Every step goes to the same large language model, whether the task is drafting a customer reply or answering a simple question like "Is this ticket urgent?" That setup gets expensive fast.
Most teams send every AI task to the same place: a frontier LLM. That includes the small, repetitive calls, like tagging a support ticket, scoring a lead, or deciding whether an agent should retry a step. At ten items, nobody notices.
Most of the AI calls inside your software don't need an essay. They need an answer: which team owns this ticket, whether a tool call is safe, whether a lead is worth chasing. The usual approach is to ask a large language model for a paragraph and then parse it into something your code can use.
If you give an LLM access to your code, you write tools. A tool is a function plus what a model needs to call it: a name, a description, and a schema for the arguments. Then you write the same tools again. The first version uses the AI SDK's tool().
Showing 18 of 75 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
