AgentRun is a domain-specific language and runtime for turning existing agents and tools into repeatable, inspectable workflows. It wires scripted tools, Jev-typed decisions, and agent calls into JSON or TypeScript-defined flows with Zod-backed schemas, runtime path validation, and features for nesting, parallel mapping, and bounded loops. A canonical support workflow demonstrates its control logic: search for an answer, use Jev to judge fit with a confidence threshold (example uses >=0.8), allow one agent investigation attempt if needed, re-check with Jev, then either return the answer or escalate for review. Workflows include deadlines, typed inputs/outputs inferred by a TypeScript builder, and an interpreter that enforces state paths during execution.
Integration is via npm packages (@parcha/agentrun-dsl, @parcha/agentrun-jev, @parcha/agentrun-pi) and adapter hooks (runEffect, runNode, createJevRunner). Quickstarts require Node 22.19+; demos run without live APIs while Jev live calls require a TYPESAFE_API_KEY. A Pi extension provides in-chat build, run, save/load, and status commands. The project is beta (0.1.0-beta.4), Apache-2.0 licensed, and includes examples and tests. Important limitations are explicit: code nodes execute JavaScript with process privileges (host sandboxing needed for untrusted authors) and typed decisions/validated outputs do not guarantee factual correctness.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Rob Race argues that traditional programming tutorials are becoming obsolete because static, step-by-step instructions no longer meet developers' needs. Instead, he advocates for more dynamic, context-rich educational approaches that focus on real-world application and understanding. (robrace.dev)
Critic is a tool that allows developers to review code written by AI agents, ensuring better understanding and accountability. It manages question sessions across disconnected devices using a leasing system to keep context consistent. (critic.run)
Agents are better viewed as processes that can be scheduled, interrupted, and resumed, rather than infinite entities. Proper state management and coordination are essential for building reliable distributed systems with agents. (instacloud.com)
Whiteboard is an open-source IDE designed to facilitate thoughtful software design. It aims to improve development workflows with features supporting code quality, security, and collaboration. (github.com)
Castle Game Engine provides an introduction to Modern Object Pascal for programmers, covering basics like syntax, classes, exceptions, and language features. The guide emphasizes practical programming concepts suitable for game development and software engineering. (castle-engine.io)
Paper Office releases Python packages that enable agents to safely and accurately manipulate Word, PowerPoint, and Excel files, building on existing open-source tools. These packages improve correctness and feature breadth, addressing challenges in editing complex office documents for professional workflows. (paperinstruments.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.