Discover how AI agents take intelligence a step further by acting, adapting, and collaborating. Agents are designed not just to process information, but to make decisions and carry out tasks, sometimes on their own, sometimes in teams. In this category, you'll find posts that explore how agents are built, how they work in real systems, and what role they might play in the future of automation.
When an admin fixes a wrong value in an AI scraper’s sample events, that edit can do more than fix one event. Here is how…
How we built a city-scale event aggregation platform using LLMs for every variable, judgment-intensive task, onboarding, parsing, classification, and enrichment and the architectural pattern that…
The three characteristics that make a repetitive workflow a good fit for a Claude Code skill and MCP server, and how we applied the pattern…
Judge panels and step-by-step trajectory grading are the first evals most teams build. Three recent papers measured both against causal ground truth, and neither one…
How we built the MCP server behind our AI Assistant for our blog writing process: an ingestion pipeline, pgvector search, FastMCP tools and resources, and…
Not every AI solution needs to be a custom agent. How I built an MCP server and Claude Code plugin for our blog writing process…
A beginner-friendly guide to writing your first Claude Code skill: a sharp description that makes it trigger, a lean SKILL.md, dynamic context injection, and progressive…
AI Agents are everywhere. Every day, tools, libraries, new use cases, and new products come out using and leveraging AI Agents. Several frameworks have been...
