How I AI

The speaker discusses how staying within Gmail limits the compounding value of AI-assisted work and writing, and demonstrates a workflow using Claude to enhance Gmail's functionality by adding formatting, links, and draft management capabilities.

The speaker emphasizes the importance of integrating AI, specifically Claude, into daily workflows by creating reminders to seek its assistance. This approach allows for collaborative problem-solving, transforming static prompts into dynamic conversations.

The episode discusses how AI tools like Claude can enhance productivity and collaboration in business and personal tasks by enabling users to focus on intentions rather than complex prompting. Grace Clark offers insights on her projects and how she built tailored solutions to improve communication and client relations using AI.

The evaluation of internal AI agents is crucial for maintaining their reliability. An internal eval platform allows engineers to review agent performance regularly and ensure their responses are accurate, particularly in critical areas like coding.

The speaker describes an AI agent framework that automatically reviews pull requests by scoring them across six risk factors using markdown-based instructions and skills. PRs are classified as low (0-24 points), medium (25-64), or high risk (65+), with only medium and high risk requiring human approval.

Voice interaction with AI addresses the common problem of 'blank chat window syndrome' by enabling users to naturally dump context through speech rather than carefully constructed text prompts. Voice-to-voice AI interaction mirrors the experience of delegating to a human assistant, making it a higher-bandwidth and more natural way to communicate with LLMs.

ChatGPT's voice interface can now operate a user's computer in parallel, handling tasks like booking flights and hotels in the background while the user continues with other work. The user demonstrates asking the AI to check their calendar, find travel options, and book accommodations for a Paris offsite, with the AI managing browser automation to complete these logistical tasks autonomously.

Nick Bowman from OpenAI demonstrates advanced use cases of ChatGPT and Codex, including voice-orchestrated multi-threaded task management, AI-powered website creation via ChatGPT artifacts, and automated video editing for content creation. He emphasizes how these tools are becoming accessible to non-technical users through mobile and voice interfaces.

The conversation explores the concept of personal APIs that store individual preferences like favorite restaurants and coffee orders, enabling others to make thoughtful gestures without asking. The discussion evolves to envision AI agents autonomously accessing these APIs to perform personalized tasks like making reservations.

A developer describes setting up an old pager as a Twitter notification device using modern cloud services. The system routes Twitter API events through Cloudflare Workers, Resend email service, and Gmail to finally deliver notifications to the pager's email address.

The speaker criticizes Opus 5 for being excessively cautious and indecisive, constantly asking for human permission or approval rather than taking action. Even when faced with simple tasks like fixing a one-line merge conflict, Opus 5 deferred to the original branch owner's preferences, requiring the speaker to repeatedly push it to make autonomous decisions.

A product manager describes using GPT-5.6 with Codex to automate video editing for social media clips. By simply dragging a file and providing natural language instructions, the AI generated five polished, fast-paced hype videos from a long conference talk recording, dramatically reducing the time-intensive manual clipping process.

An executive contrasts two AI models (Fable and Soul/GPT-5.6 Sol), arguing that Soul is superior for product work because it prioritizes practical effectiveness over theoretical intelligence. The speaker values the ability to ship products to customers and understand end-user goals over theoretical sophistication.

Building a harness for repetitive workflows allows you to be more prescriptive about job execution, resulting in greater efficiency, consistency, and better outcomes. Rather than explaining requirements to an AI agent each time, a harness lets you use a simpler interface like pasting a link while the agent already understands the intended task.

Claire Vo compares OpenAI's new GPT 5.6 models (Soul, Terra, Luna) against Claude's Fable using her custom "How I AI" benchmark, finding that GPT 5.6 Soul excels at practical product work, prototyping, and natural communication, while Fable is theoretically intelligent but pedantic and difficult to collaborate with.

The speaker highlights context offloading as an underrated AI use case, where AI serves as a safety net for routine cognitive tasks like email management and personal finances. Rather than adding new capabilities, AI reduces anxiety about missing important information or making mistakes by handling monitoring tasks, thereby freeing up mental bandwidth.

A harness is code that wraps around an AI agent to make it more effective. The speaker demonstrates how a harness can automatically investigate production issues by analyzing Sentry warnings, identifying root causes, determining impact, and recommending whether to create tickets or apply fixes.

The speaker discusses the shift from traditional agent prompting to agent management, highlighting the limitations of local Kanban board approaches and advocating for cloud-based VPS solutions with multiple communication channels to effectively manage autonomous AI agents across projects.

A custom AI harness is code wrapped around an AI agent to make it more effective for specific workflows. The speaker demonstrates building a Sentry bug-debugging harness using Claude SDK with a terminal UI, showing how structured constraints, custom prompts, and specific tool adapters enable agents to handle complex tasks more efficiently than general-purpose AI tools.

Alessio Finelli demonstrates how he uses OpenAI's Symphony framework combined with Linear and Codex to run autonomous coding agents from his phone, managing both software engineering tasks and a Pokémon card trading business through cloud-based VPS infrastructure instead of local machines.