Look for any podcast host, guest or anyone
Showing episodes and shows of

Jared Zoneraich

Shows

Exception Handlers
Exception HandlersInterview with Jared Zoneraich: Agents and the Future of AI SystemsAlex and Bill interview Jared Zoneraich, CEO and Co-founder of PromptLayer, on the evolution of agentic AI - from DAGs to agentic loops.
2026-03-0200 minThe Changelog: Software Development, Open Source
The Changelog: Software Development, Open SourceThe era of the Small Giant (Interview)Damien Tanner (founder of Pusher, now building Layercode) is back for a reunion 17 years in the making. Damien officially returns to The Changelog to discuss the seismic shift happening in software development. From the first sponsor of the podcast to frontline builder in the AI agent era, Damien shares his insights on why SaaS is dying, why code review is a bottleneck (and non-existent for some), and how small teams can now build giant things. Join the discussionChangelog++ members save 8 minutes on this episode because they made the ads disappear. Join today!...
2026-01-221h 38Changelog Interviews
Changelog InterviewsThe era of the Small GiantDamien Tanner (founder of Pusher, now building Layercode) is back for a reunion 17 years in the making. Damien officially returns to The Changelog to discuss the seismic shift happening in software development. From the first sponsor of the podcast to frontline builder in the AI agent era, Damien shares his insights on why SaaS is dying, why code review is a bottleneck (and non-existent for some), and how small teams can now build giant things. Join the discussionChangelog++ members save 8 minutes on this episode because they made the ads disappear. Join today!...
2026-01-221h 38Changelog Master Feed
Changelog Master FeedThe era of the Small Giant (Changelog Interviews #673)Damien Tanner (founder of Pusher, now building Layercode) is back for a reunion 17 years in the making. Damien officially returns to The Changelog to discuss the seismic shift happening in software development. From the first sponsor of the podcast to frontline builder in the AI agent era, Damien shares his insights on why SaaS is dying, why code review is a bottleneck (and non-existent for some), and how small teams can now build giant things. Join the discussionChangelog++ members save 8 minutes on this episode because they made the ads disappear. Join today!...
2026-01-221h 38Tech Updates
Tech UpdatesEpisode 242 - Decoding Claude's Code - Jared ZoneraichHow Claude Code Works - Jared Zoneraich, PromptLayerlink to the source
2025-12-2920 min跨国串门儿计划
跨国串门儿计划#371.Claude Code：为什么“大道至简”才是编程 Agent 的终极答案？📝 本期播客简介本期我们克隆了：AI Engineer 大会技术分享为什么早期的自动化编程工具都很“烂”，而现在的 Claude Code 和 Cursor 却让人直呼好用？本期嘉宾 Jared Zoneraich（PromptLayer 创始人）将带我们拆解 Claude Code 的内部逻辑。他提出了一套反直觉的观点：最好的 Agent 架构不是复杂的流程图，而是一个简单的 While 循环；与其花精力写代码防止模型幻觉，不如“让开道路”信任模型的自主性。在这场深度技术分享中，你将听到：Claude Code 如何利用 Bash 命令作为万能适配器？为什么“上下文”是 Agent 最大的敌人？以及在 Droid、Codex、Cursor 丛生的时代，开发者该如何选择和构建自己的 AI 工作流。这不仅是一次对 Claude Code 的拆解，更是一次关于 AI 工程化思维的深度洗礼。👨‍⚕️ 本期嘉宾Jared Zoneraich，PromptLayer 的创始人。PromptLayer 是全球领先的 Prompt 管理与评估平台，帮助开发者更严谨地构建和测试 AI 应用。Jared 是 AI 工程领域的资深专家，致力于探索 Agent 架构与 Prompt 工程的最佳实践。⏱️ 时间戳00:00 开场 & 嘉宾介绍编程 Agent 的进化与突破01:05 为什么现在的编程 Agent 终于“能用”了？04:23 历史回顾：从 ChatGPT 复制粘贴到 Claude Code 的无头模式05:45 核心突破：更好的模型能力 vs 更简单的架构设计07:48 “AGI 药丸”心态：不要为解决今天的问题而过度设计深度拆解 Claude Code 内部原理08:55 架构哲学：简单胜于复杂，扁平胜于嵌套11:02 核心主循环：四行代码构建的“While 循环”革命12:39 工具箱揭秘：为什么 read、grep 和 edit 比 RAG 更高效14:58 Bash 的魔力：作为 Agent 万能适配器的 shell 工具16:55 待办事项（Todo Lists）：如何通过非确定性指令增强可控性上下文与 Agent 管理19:35 上下文管理：Agent 最大的敌人是“变笨”20:37 告别 DAG：为什么复杂的流程图是工程噩梦25:47 沙盒与安全：如何在 YOLO 模式与企业安全间平衡26:47 子 Agent（Sub-agents）：研究员、审查员与任务分发逻辑31:03 Skills 功能：如何构建可扩展的系统 Prompt主流编程 Agent 横向对比34:34 未来趋势：超级工具调用 vs 自适应推理预算38:14 “AI 治疗师”比喻：为什么 AI 产品没有全局最优解40:01 各显神通：Codex 的 Rust 并发、Amp 的交接模式、Cursor 的速度优势45:24 评估与测试：如何通过“Agent Smell”判断 Agent 的健康度实战建议与 Q&A52:04 总结：信任模型、简单设计、Bash 为王53:43 Q&A：如何强制 Agent 的执行顺序？56:39 TDD 与规范驱动：AI 时代的工程原则59:14 关于 PromptLayer：如何招聘与协作🌟 精彩内容💡 信任模型（Trust the Model）Jared 强调，开发者往往喜欢过度优化脚手架代码来防止模型出错。但 Claude Code 的成功证明了：给模型工具，然后“让开”。随着模型能力的提升，很多现在的硬编码逻辑在三个月后都会变成累赘。🛠️ Bash 是 Agent 的“圣杯”在所有的工具调用中，Bash 是最重要的。因为它简单、健壮，且拥有海量的互联网训练数据。Claude Code 通过在沙盒中运行 Python 脚本或测试用例，实现了极高的灵活性。🚀 告别复杂的 DAG 流程过去两年，大家都在构建拥有成百上千个节点的 DAG（有向无环图）。但现在，这种“工程噩梦”正在被简单的循环取代。依赖模型的自主探索，比硬编码每一个 if/else 语句效果更好，维护成本也更低。🧠 上下文压缩艺术上下文越长，模型越笨。Claude Code 通过 H2A 缓冲区管理 IO，并在上下文达到 92% 阈值时进行智能压缩。Jared 建议，将长期记忆存储在沙盒的 Markdown 文件中，而不是全部塞进对话框。🎨 AI 产品的“品味”与视角不同的编程 Agent 代表了不同的哲学：Claude Code 追求极致的命令行简洁，Cursor 追求 UI 交互的快感，而 Amp 探索免费与广告模式。开发者应根据“品味”选择最适合自己工作
2025-12-271h 03Practical AI
Practical AIWhile loops with tool callsDan and Chris sit down (again) with Jared Zoneraich, co-founder and CEO of PromptLayer, to discuss how prompt engineering has evolved into context engineering (and while loops with tool calls). Jared shares insights on building flexible AI applications, managing tool calls, testing and versioning prompts, and empowering both technical and non-technical users in AI development. Along the way, they dive into coding agents and the “crawl-walk-run” approach to AI deployment.Featuring: Jared Zoneraich – LinkedInChris Benson – Website, LinkedIn, Bluesky, GitHub, XDaniel Whitenack – Website, GitHub, XLinks:PromptLayerUpcoming Events: Join us at the Midwest AI S...
2025-10-3044 minCrazy Wisdom
Crazy WisdomEpisode #495: The Black Box Mind: Prompting as a New Human ArtIn this episode of Crazy Wisdom, host Stewart Alsop talks with Jared Zoneraich, CEO and co-founder of PromptLayer, about how AI is reshaping the craft of software building. The conversation covers PromptLayer’s role as an AI engineering workbench, the evolving art of prompting and evals, the tension between implicit and explicit knowledge, and how probabilistic systems are changing what it means to “code.” Stewart and Jared also explore vibe coding, AI reasoning, the black-box nature of large models, and what accelerationism means in today’s fast-moving AI culture. You can find Jared on X @imjaredz and learn more or sign...
2025-10-0657 minThe Jason Levin Show
The Jason Levin Show#84: Jared Zoneraich — The $5M Prompt EngineerJared Zoneraich is the founder PromptLayer, the first platform built for prompt engineers(00:45) The secret sauce behind prompting(06:54) “Intelligence is cheap as fuck now”(12:45) Remember when the whole internet dunked on prompt engineering?(18:40) Talking on the phone with your users and being friends with them(22:37) That one time Jared and I built a bot to talk to dead people during my bachelor party(24:14) Building while hackathon teammates hit the strip club(28:25) Founders: please have a hobby(32:50) Real talk: should you throw money at investing or keep building stuff?(36:55) Contrarian hot take: “This is a good time to be a softwa...
2025-03-2748 min(AI) People
(AI) PeopleAI People with Jared Zoneraich - Founder at PromptLayerAI People with Jared Zoneraich - Founder at PromptLayer
2025-02-0535 minAI and I
AI and IHow to Win With Prompt Engineering - Ep. 38 with Jared ZoneraichPrompt engineering matters more than ever. But it’s evolving into something totally new:  A way for non-technical domain experts to solve complex problems with AI. I spent an hour talking to prompt wizard Jared Zoneraich, cofounder and CEO of PromptLayer, about why the death of prompt engineering is greatly exaggerated. And why the future of prompting is equipping non-technical experts with the tools to manage, deploy, and evaluate prompts quickly. We get into: His theory around why the “irreducible” nature of problems will keep prompt engineering relevant Prompt enginee...
2024-11-131h 02AI & I
AI & IHow to Win With Prompt Engineering - Ep. 38 with Jared ZoneraichPrompt engineering isn’t just about telling AI to solve your problems—it’s about knowing which ones to solve. Yet there’s a mismatch between the people who can identify the right problems—experts with deep domain knowledge—and the technical infrastructure required for developing and refining prompts. Jared Zoneraich, the cofounder and CEO of prompt engineering platform PromptLayer, is bridging the gap with a platform on which non-technical experts can manage, deploy, and evaluate prompts quickly.The role of human prompt engineers, however, has been the topic of controvers...
2024-11-131h 02Everyday AI Podcast – An AI and ChatGPT Podcast
Everyday AI Podcast – An AI and ChatGPT PodcastEP 294: Why the Future of AI Will Be Built by Non-Technical Domain ExpertsPrompting a large language model requires a bunch of tech know-how right?↳ Super structured inputs↳ RAG↳ Fine-tuningMeh. Not so much. The best way to prompt your way to better results? Flex your domain expertise. Jared Zoneraich, Founder of PromptLayer, joins us to discuss.Newsletter: Sign up for our free daily newsletterMore on this Episode: Episode PageJoin the discussion: Ask Jordan and Jared questions on building AIRelated Episodes: Ep 164: ChatGPT Doesn’t Suck. Your Prompts Do.Ep 1...
2024-06-1432 minPractical AI
Practical AIPrompting the futureDaniel & Chris explore the state of the art in prompt engineering with Jared Zoneraich, the founder of PromptLayer. PromptLayer is the first platform built specifically for prompt engineering. It can visually manage prompts, evaluate models, log LLM requests, search usage history, and help your organization collaborate as a team. Jared provides expert guidance in how to be implement prompt engineering, but also illustrates how we got here, and where we’re likely to go next.Sponsors:Shopify – Sign up for a $1/month trial period at shopify.com/practicalaiFly.io – The home of Changelog.com —...
2024-03-2045 minChangelog Master Feed
Changelog Master FeedPrompting the future (Practical AI #261)Daniel & Chris explore the state of the art in prompt engineering with Jared Zoneraich, the founder of PromptLayer. PromptLayer is the first platform built specifically for prompt engineering. It can visually manage prompts, evaluate models, log LLM requests, search usage history, and help your organization collaborate as a team. Jared provides expert guidance in how to be implement prompt engineering, but also illustrates how we got here, and where we’re likely to go next. Leave us a comment Changelog++ members save 4 minutes on this episode because they made the ads disappear. Join today! ...
2024-03-2046 minMLOps.community
MLOps.communityCost/Performance Optimization with LLMs [Panel]Sign up for the next LLM in production conference here: https://go.mlops.community/LLMinprod Watch all the talks from the first conference: https://go.mlops.community/llmconfpart1 // Abstract In this panel discussion, the topic of the cost of running large language models (LLMs) is explored, along with potential solutions. The benefits of bringing LLMs in-house, such as latency optimization and greater control, are also discussed. The panelists explore methods such as structured pruning and knowledge distillation for optimizing LLMs. OctoML's platform is mentioned as a tool for the automatic deployment of custom models and...
2023-05-0635 min