Staying in Gmail means none of your AI work compounds
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.
Summary
The speaker expresses frustration with Gmail as a constraint on AI productivity, arguing that work done entirely within Gmail doesn't compound or create lasting value—it remains isolated within the email platform. To address this limitation, they describe an iterative back-and-forth collaboration with Claude AI to essentially rebuild Gmail's functionality. The process involves asking Claude to implement specific improvements: adding hyperlinks, bolding text, and pushing content back to Gmail. The speaker demonstrates a practical workflow where they can draft emails through Claude, make revisions in conversation, and then send the finalized version to Gmail. This approach allows them to either continue refining responses in Claude's interface or simply send the completed draft without further iteration. The system bridges the gap between Claude's AI capabilities and Gmail's email delivery, enabling the speaker to maintain their email workflow while leveraging AI assistance for composition and enhancement.
Key Insights
- The speaker believes that work conducted entirely within Gmail fails to compound in value and remains locked away with no lasting benefit beyond the immediate email exchange
- The speaker expresses strong dissatisfaction with Gmail itself ('I hate Gmail. Absolutely never want to be in it') as a constraint on their workflow
- The speaker iteratively built an enhanced email system through repeated requests to Claude, asking for specific feature additions like links, bolding, and Gmail integration
- The resulting workflow provides flexibility to either continue refining drafts conversationally with Claude or send completed emails directly without further revision
- The speaker views this system as a practical compromise that gets them 'pretty much where I want to go' between staying in Claude for refinement or pushing to Gmail for delivery
Topics
Transcript
[0:00] We can actually be training our AIS as we respond and communicate through Gmail. If we stay in Gmail, all that learning and all that writing and all that work actually doesn't go anywhere. It doesn't compound. It's just locked away. So, I went back and forth with Claude saying, "I hate Gmail. Absolutely never want to be in it." Claude was like, "Let's rebuild Gmail." Back and forth, back and forth. The process was just asking Claude, "Can you change this? Can we add a link? Can we add bolding? Can we push this to Gmail?" Let's see what happens. A student wants [0:30] the recording for the class. I don't like this draft. It's totally fine. Sending…
Full transcript available for MurmurCast members
Sign Up to AccessMore from How I AI
Intent engineering beats prompt engineering every time
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.
Claude Code for normal people: skills, voice mode, and how to collaborate with AI
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.
Running evals on your internal agents is how you keep them trustworthy over time
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.
You don't have to review every AI-generated PR
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 is the highest-bandwidth input channel for AI
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.