Exploring Subagents in Claude Code with Addy Osmani
In this walkthrough, Addy Osmani demonstrates Claude Code’s sub‑agent feature by prompting the model to build a simple bookmarks manager called Link Shelf using Express and SQLite. The parent orchestrator reads the single request, decomposes it into three sub‑agent briefs, and launches two agents in parallel to generate the data‑layer and business‑logic code. The demo highlights how the orchestrator can run independent agents simultaneously, then spawn a third agent to create API routes once the first two have written their files. This parallelism reduces overall generation time, while each sub‑agent enjoys context isolation, preventing token overload and allowing specialization. However, the parent must manually track dependencies and sequence execution, as there is no built‑in messaging or automatic unblocking between agents. Osmani notes, “We get parallel execution where it’s possible, but the parent is manually managing our dependency graph.” The example shows the parent reading existing files to understand interfaces before wiring everything together, illustrating both the power and the current friction of the approach. The implication is clear: sub‑agents can accelerate AI‑driven code creation and keep prompts concise, but developers still need to handle orchestration logic. Until automated messaging and dependency resolution are added, large‑scale or highly interdependent projects may require significant manual coordination, affecting productivity and cost efficiency.
This Week in AI: Rethinking the Agent Harness
The inaugural episode of O'Reilly’s “This Week in AI” introduced the series and previewed a lineup of expert guests, while host Eric Freeman set the stage by surveying major AI developments—from security breakthroughs to infrastructure expansions and emerging agent frameworks. Freeman...
AI Divorce Agent: $2M Startup Journey with Ryan Carson
Ryan Carson, former Maple executive, launched an AI‑powered divorce platform, positioning himself as the sole full‑time employee while the rest of the workforce consists of artificial‑intelligence agents. The venture, dubbed the AI Divorce Agent, recently closed a $2 million seed round. Carson...
Generative AI in the Real World: Stefania Druga on Designing for the Next Generation
Stefania Druga, former DeepMind research scientist, explains how generative AI must be re‑engineered for the next generation of users—primarily Gen Z learners. She contrasts the typical utilitarian, task‑automation mindset of adult‑focused tools with the playful, exploratory ways children experiment, such as...
Generative AI in the Real World: Chang She on Data Infrastructure for AI
The podcast spotlights the growing gap between legacy analytics stacks and the data demands of generative AI. Chang Shi, CEO of LanceDB, explains how his experience building embeddings at Tubi TV revealed that tools such as Pandas, Spark, and Parquet...
Inside the Code Factory: Ryan Carson Live with Tim O’Reilly
In a Code Factory episode, Tim O’Reilly talks with veteran entrepreneur Ryan Carson about his newest venture, Untangle, an AI‑powered divorce assistant built and operated entirely by artificial‑intelligence agents. Carson recounts how he re‑learned full‑stack development with ChatGPT, launched a minimal...
Generative AI in the Real World: Douwe Kiela on Why RAG Isn’t Dead
The podcast with Douwe Kiela, CEO of Contextual AI, tackles the hot question of whether Retrieval‑Augmented Generation (RAG) is obsolete in the era of massive‑context language models. Kiela argues that expanding context windows solve the same problem RAG addresses—bringing relevant...
Generative AI in the Real World: Danielle Belgrave on Generative AI in Pharma and Medicine
In this podcast, GSK’s Vice President of AI and Machine Learning, Danielle Belgrave, explains how generative and traditional AI are being deployed across the pharmaceutical pipeline. Drawing on a 15‑year career that spans a PhD on asthma heterogeneity, stints at...
AI Scouts and AI Chiefs of Staff with Ryan Carson
Ryan Carson explains how he runs an open‑source AI "chief of staff" called OpenClaw, built around a simple priority map and a 15‑minute cron job that triages inbox, Slack and other data streams. The loop surfaces high‑priority items and can...
How to Delegate Effectively with Anemari Fiser
In the video, tech‑lead coach Anemari Fiser explains how tech leads can delegate effectively, focusing on two simple secrets that address most common delegation pitfalls. First, she stresses setting crystal‑clear expectations: define the problem, desired outcomes, specific artifacts, and any required...
Generative AI in the Real World: Shreya Shankar on AI for Corporate Data Processing
In this podcast, UC Berkeley PhD candidate Shreya Shankar explains how generative AI is reshaping enterprise data processing. She highlights the long‑standing challenge of extracting structure from unstructured assets—PDFs, transcripts, logs—and shows how large language models now make that feasible....
Encourage AI Exploration with Camille Fournier
Camille Fournier argues that the biggest barrier to AI adoption is not technology but managerial inertia. She stresses that leaders need to carve out dedicated, protected time for teams to experiment with AI tools, rather than expecting employees to fit...
Avoid Interpassivity in AI Tooling with Camille Fournier
Camille Fournier cautions engineers against "interpassivity"—the habit of letting AI tools operate autonomously while the user remains passive. She frames the issue as a modern extension of an old debugging mindset, where engineers once leaned on debuggers or print statements...
Simplifying Context Engineering for AI Agents in Production with Cornelia Davis
The video outlines three core best practices for production‑grade AI agents: narrowly scoping each agent, delivering data incrementally, and rigorously managing conversation history. By treating agents as micro‑service‑like components, developers can avoid the monolithic pitfalls that often cripple performance. The speaker...
Highlights From Software Architecture Superstream: Software Architecture and the Age of Agentic AI
The Superstream session examined how software architecture must evolve for the age of agentic AI. Speakers highlighted the rapid rise in interest for autonomous AI agents, noting that while generative models have matured, the ability of agents to act independently...