

119 episodes
by Claire Vo · English
How I AI, hosted by Claire Vo, is for anyone wondering how to actually use these magical new tools to improve the quality and efficiency of their work. In each episode, guests will share a specific, practical, and impactful way they’ve learned to use AI in their work or life. Expect 30-minute episodes, live screen sharing, and tips/tricks/workflows you can copy immediately. If you want to demystify AI and learn the skills you need to thrive in this new world, this podcast is for you.

Ryan Carson (solo founder) explains how coding agents like Devin changed his workflow over the last year, why “cloud agents” beat local for most engineering, and how solo founders must become “agent…
24 Aug 2026 · 44m · 21 chapters
The host tests and gives an “honest take” on XAI/Cursor-related releases: GrokBot (multi-agent chat/work agent), Cursor Origin (a GitHub replacement in early access), and the Grok 4.6 model…
18 Aug 2026 · 27m · 9 chapters
Yana Welinder explains how she launched an AI-native fashion brand as a solo founder using Codex/ChatGPT for design, visualization, website building, vendor outreach, and production workflows—arguing…
17 Aug 2026 · 33m · 12 chapters
How to use Claude Code and Claude “skills” to build AI-assisted workflows for proposals, onboarding, email triage, and personal tracking—emphasizing “intent engineering” over prompt engineering, plus…
10 Aug 2026 · 43m · 17 chapters
Building an AI PR review bot that risk-scores pull requests, auto-approves low-risk changes, and escalates medium/high-risk PRs for human review, using Vercel Eve plus Vercel’s GitHub/Slack…
5 Aug 2026 · 24m · 7 chapters
Nick Baumann (OpenAI) demonstrates advanced ChatGPT Codex/ChatGPT Work workflows: voice “hotkey” delegation that can see the screen, create/fork threads, run multiple background tasks via plugins,…
3 Aug 2026 · 42m · 20 chapters
How Maddy Reese, a non-traditional coder turned “hardware hacker,” uses Cursor and AI to build playful physical AI projects—especially a “Message Maddie” thermal printer, a “Message Maddie” pager,…
27 Jul 2026 · 28m · 11 chapters
Review of Anthropic’s Claude Opus 5, including a “How I AI” benchmark for PRDs/prototypes/wireframes/bug triage/agentic coding, plus a comparison of model “personality” (timidity, trust, verbosity)…
24 Jul 2026 · 25m · 10 chapters
How to use Codex/Claude-style “computer & browser use” so AI can control the mouse/keyboard, navigate websites, and complete tasks for you.
22 Jul 2026 · 28m · 11 chapters
Alex Lieberman (10X) explains his “content machine” workflow for generating non-generic AI-assisted marketing content, plus how 10X gets employees posting via an incentive program.
20 Jul 2026 · 43m · 15 chapters
Alex Finn explains how he runs “ambient AI” locally 24/7 using multiple machines (three Mac Studio 512GB, a DGX Spark, and a custom RTX 5090 build), coordinated via OpenClaw/Hermes agents and…
13 Jul 2026 · 36m · 15 chapters
The host reviews OpenAI’s GPT-5.6 family (Sol, Terra, Luna) using their “How I AI Vibe Review” benchmark (PRD writing, prototyping/wireframes, coding/debug, and agentic “talk to me like a human”…
9 Jul 2026 · 37m · 17 chapters
The episode explains “harnesses”: code that wraps an AI agent to make it more effective for a specific workflow by adding constrained context, allowed tools/actions, and required outcomes.
8 Jul 2026 · 25m · 6 chapters
How Alessio Fanelli (Kernel Labs) runs autonomous coding agents from a phone using OpenAI Symphony plus Linear as a state machine, and how he applies Codex for inventory/pricing automation in his…
6 Jul 2026 · 36m · 17 chapters
The episode reviews Anthropic’s “Claude Sonnet 5” and tests whether it’s truly “Opus-level” for cheaper pricing.
30 Jun 2026 · 26m · 8 chapters
How Gusto’s CTO Eddie Kim and a tiny team built “Gusto co-founder,” a new agentic product line, in 10 weeks without traditional product artifacts (no Figma, no Jira boards, no tech specs, minimal…
29 Jun 2026 · 52m · 23 chapters
The episode tests GLM 5.2, an open-weight text-to-text model from Beijing startup Z.ai, as a cheaper replacement for Anthropic Opus/GPT-class models in coding workflows.
24 Jun 2026 · 27m · 8 chapters
Mozilla Firefox’s security team explains how “Claude Mythos” (Anthropic’s model) plus a custom agentic “harness” helped find and verify long-hidden vulnerabilities, including a 15-year-old bug, and…
22 Jun 2026 · 48m · 24 chapters
Explains AI “prompt loops” (automated, recurring prompting) in Claude Code and Codex: heartbeat/cron/hooks, plus “goal” loops that run until a measurable outcome is validated or blocked.
17 Jun 2026 · 29m · 11 chapters
Braintrust’s CEO Ankur Goyal explains how coding agents, rigorous evals, and CI/observability help ship better software—especially for hard infrastructure tasks like database query latency and AI…
15 Jun 2026 · 40m · 15 chapters
Review of Anthropic’s Claude “Fable 5” (a Mythos-class model) after early access, covering benchmark claims, safety guardrails, costs, and real-world strengths/weaknesses.
9 Jun 2026 · 17m · 7 chapters
Busy mom uses Claude (and Claude Cowork connected to email) to shop for high-quality, natural-material brands that last, automate returns, and reduce “administrative” mental load.
8 Jun 2026 · 37m · 15 chapters
Host tests Google Flow with Gemini Omni to create an AI “clone” avatar and generate a stitched, ~1-minute hype video for the How I AI podcast in under ~15 minutes, including avatar scanning,…
3 Jun 2026 · 21m · 8 chapters
How Bryce Rattner-Keefley, a non-technical talent leader, built and shipped Daily Hundreds, a vibe-coded iPhone fitness app that generates customized anthropomorphic animal exercise videos using AI…
1 Jun 2026 · 47m · 17 chapters