Behind the Craft

The 4-Step Agentic Engineering Workflow I Use to Ship Real Apps | Ras Mic

How to Use AI to Survive (and Even Enjoy) Meetings | Sam Stephenson

We Built Grok Bot. Here Are Our 14 Best Bots | Peng Zheng & Lauren Tan

How to Save Money Now with ChatGPT Finances (6 Real Use Cases) | Ethan Bloch

Stop Building AI Agents. Build AI Employees Instead (Live Demo) | Pedro Franceschi

AI Makes Cheating Easy. Here’s How It Can Make Kids Smarter Instead | Sue Khim

How to Vibe Code Apps That Become Real Businesses | Amol Jain

How to Build Better AI Evals with Claude Code in 5 Steps | Shreya & Hamel

How I Run My 1.5M+ Follower Content Business With Codex | Riley Brown

5 Rules for Building AI Agents That Work in Production | Nan Yu & Jacob Shumway

Autonomous AI agents function as LLMs operating in a loop, utilizing specific tools to achieve defined goals. Linear’s approach to building a production-grade agent centers on a "skills" architecture, which replaces monolithic prompts with modular, specialized capabilities to minimize hallucinations and context overloa...

Hermes Co-Founder on Building an AI Agent That Improves Itself | Karan Malhotra

Hermes agent functions as an open-source AI chief of staff, prioritizing user-aligned performance over the restrictive, sycophantic behaviors common in closed-model systems. By utilizing a modular harness that manages memory, skills, and context, the agent adapts to individual user needs and improves through self-curat...

ChatGPT Work + Codex Tutorial: My Complete System at OpenAI | Jason Liu

AI agents like Codex and ChatGPT Work transform productivity by shifting the focus from manual execution to high-level management and iterative feedback. Jason Liu, from the OpenAI Codex team, demonstrates how these tools automate daily operations—such as managing Slack, email, and project boards—through "heartbeat" th...

How I Plan, Build, and Run Loops with Claude Code in 40 Minutes | Thariq Shihipar

Designing autonomous AI workflows requires moving beyond one-shot prompts toward iterative loops that allow agents to execute complex tasks over extended periods. Thariq Shihipar, from the Claude Code team at Anthropic, emphasizes that effective agent orchestration relies on systematically removing unknowns through con...

How to Build AI Agents That Check Their Own Work | Jared Zoneraich

Building effective AI agents requires shifting away from rigid, over-engineered prompts toward letting models leverage their inherent reasoning capabilities. Modern agentic workflows thrive in cloud environments, where long-running processes operate asynchronously and orchestrate multiple child agents to handle complex...

OpenAI PM Reveals How He Uses Codex to Do Product Work | Rohan Varma

Codex, an AI-powered agent, fundamentally transforms product management by shifting the focus from manual information synthesis and administrative overhead to high-level strategic decision-making and customer engagement. By integrating across tools like Slack, Notion, and Linear, the agent autonomously handles data syn...

Inside Anthropic’s Bet on Claude Agents that Work While You Sleep | Jess Yan

Autonomous agents have evolved from simple prompting loops into self-discovering, long-running actors capable of executing complex tasks with minimal human intervention. These agents rely on a "harness"—the scaffolding that manages tool access, memory, and permissioning—to elevate performance beyond basic token generat...

Full Tutorial: Make Professional Launch Videos for Free with Hyperframes | Bin Liu & Jake Moran

Agentic Engineering, Clearly Explained in 50 Min | Matt Van Horn

How This Ex-Meta L8 Engineer Ships 40 PRs a Day with AI Agents | Kun Chen

The Exact AI Skills This Solo Founder Uses to Build 5 Apps at Once | Josh Pigford