{"generated_at": "2026-07-14T03:18:24.253906Z", "slug": "how_i_ai", "source_id": "src_how_i_ai", "name": "How I AI", "episode_count": 18, "avg_signal": 80.5, "median_signal": 84.2, "top_signal": 89.9, "latest_episode_at": "2026-07-09T17:33:20Z", "earliest_episode_at": "2026-05-11T11:00:00Z", "category_mode": "ai", "cover_image_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1783560202195-3db4972e670e9.jpg", "rank_score": 225.264, "episodes": [{"episode_id": "ep_how_i_ai_31705202f2c8", "episode_title": "GPT-5.6 Sol vs. Claude Fable: Why OpenAI\u2019s new model crushes my benchmark", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-07-09T17:33:20Z", "overall_score": 89.9, "score_breakdown": {"clarity": 68.6, "originality": 61.0, "hype_penalty": 0.0, "actionability": 100.0, "technical_depth": 100.0, "information_density": 100.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1783560202195-3db4972e670e9.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/GPT-5-6-Sol-vs--Claude-Fable-Why-OpenAIs-new-model-crushes-my-benchmark-e3lrcne", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/122581166/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-6-9%2F427622015-44100-2-39b3fe43deb86.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/GPT-5-6-Sol-vs--Claude-Fable-Why-OpenAIs-new-model-crushes-my-benchmark-e3lrcne", "verdict": "worth_your_time", "why_listen": "It goes beyond the title with direct discussion of like, fable, really, including: But guess what, babes?.", "summary": "I have been very, very, very sad the last week because for the last week, I have not had access to my true favorite top of the line model, GPT-56. I'm going to tell you what are these models?."}, {"episode_id": "ep_how_i_ai_a0a5c7eba34a", "episode_title": "What a harness is and how to build one with Claude Agent SDK", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-07-08T11:00:00Z", "overall_score": 88.3, "score_breakdown": {"clarity": 71.0, "originality": 50.3, "hype_penalty": 0.0, "actionability": 100.0, "technical_depth": 100.0, "information_density": 100.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1783446749633-c9f3595b0dfab.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/What-a-harness-is-and-how-to-build-one-with-Claude-Agent-SDK-e3lnv0k", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/122468820/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-6-6%2F427472067-44100-2-b6d14be11b2df.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/What-a-harness-is-and-how-to-build-one-with-Claude-Agent-SDK-e3lnv0k", "verdict": "worth_your_time", "why_listen": "It goes beyond the title with direct discussion of harness, it's, like, including: Why we've seen people build these specific use case harnesses is sometimes with a specific job, you just want to micromanage a little bit.", "summary": "A harness is some code around an AI agent that makes it more effective. Why we've seen people build these specific use case harnesses is sometimes with a specific job, you just want to micromanage a little bit."}, {"episode_id": "ep_how_i_ai_464e1dc70d81", "episode_title": "How I run autonomous coding agents from my phone with OpenAI Symphony + Linear | Alessio Fanelli (Kernel Labs)", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-07-06T11:00:00Z", "overall_score": 83.0, "score_breakdown": {"clarity": 71.0, "originality": 54.1, "hype_penalty": 6.0, "actionability": 100.0, "technical_depth": 100.0, "information_density": 100.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1783109617986-4218fcd3f8deb.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/How-I-run-autonomous-coding-agents-from-my-phone-with-OpenAI-Symphony--Linear--Alessio-Fanelli-Kernel-Labs-e3lj6bn", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/122312503/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-6-2%2F427261102-44100-2-dce39f6a892e9.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/How-I-run-autonomous-coding-agents-from-my-phone-with-OpenAI-Symphony--Linear--Alessio-Fanelli-Kernel-Labs-e3lj6bn", "verdict": "worth_your_time", "why_listen": "It goes beyond the title with direct discussion of like, kind, it's, including: Just the ability to intersect the human world in a way that has been historically very inefficient has been a quality of life improvement for me.", "summary": "Just the ability to intersect the human world in a way that has been historically very inefficient has been a quality of life improvement for me. You know, my dad, their business, they deliver fish to restaurants."}, {"episode_id": "ep_how_i_ai_bb7562cca611", "episode_title": "Sonnet 5 review: I ran 64 generations to find out if it's worth it", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-06-30T23:19:05Z", "overall_score": 85.9, "score_breakdown": {"clarity": 54.2, "originality": 55.1, "hype_penalty": 0.0, "actionability": 100.0, "technical_depth": 100.0, "information_density": 100.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1782860342908-d04e401f3a4a4.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/Sonnet-5-review-I-ran-64-generations-to-find-out-if-its-worth-it-e3lga05", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/122217925/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-5-30%2F427131012-44100-2-00e3dda044fe6.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/Sonnet-5-review-I-ran-64-generations-to-find-out-if-its-worth-it-e3lga05", "verdict": "worth_your_time", "why_listen": "It goes beyond the title with direct discussion of like, sonnet, going, including: No, but it is Claude Sonnet 5.", "summary": "We've got a new model, people, and it's from Anthropic. No, but it is Claude Sonnet 5."}, {"episode_id": "ep_how_i_ai_bb678e37cbd7", "episode_title": "No Figma. No Jira. No docs. How Gusto built a new product line with Claude Code | Eddie Kim (CTO)", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-06-29T11:00:00Z", "overall_score": 65.4, "score_breakdown": {"clarity": 43.7, "originality": 53.5, "hype_penalty": 18.0, "actionability": 100.0, "technical_depth": 100.0, "information_density": 100.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1782525479524-53921fc338b79.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/No-Figma--No-Jira--No-docs--How-Gusto-built-a-new-product-line-with-Claude-Code--Eddie-Kim-CTO-e3l9dkt", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/121992285/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-5-25%2F426845751-44100-2-9721922ac73d1.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/No-Figma--No-Jira--No-docs--How-Gusto-built-a-new-product-line-with-Claude-Code--Eddie-Kim-CTO-e3l9dkt", "verdict": "worth_your_time", "why_listen": "It goes beyond the title with direct discussion of like, it's, actually, including: We had no JIRA board where we tracked stories or tracked work.", "summary": "We had no tech specs."}, {"episode_id": "ep_how_i_ai_19b8412a3e42", "episode_title": "How Claude Mythos found a 15-year-old bug in Mozilla Firefox | Brian Grinstead", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-06-22T11:00:00Z", "overall_score": 79.7, "score_breakdown": {"clarity": 65.2, "originality": 43.3, "hype_penalty": 6.0, "actionability": 100.0, "technical_depth": 100.0, "information_density": 100.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1781888841200-d424b59c1f359.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/How-Claude-Mythos-found-a-15-year-old-bug-in-Mozilla-Firefox--Brian-Grinstead-e3kvgl1", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/121667681/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-5-18%2F426415106-44100-2-515c5cbd0b1ad.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/How-Claude-Mythos-found-a-15-year-old-bug-in-Mozilla-Firefox--Brian-Grinstead-e3kvgl1", "verdict": "worth_your_time", "why_listen": "It goes beyond the title with direct discussion of like, think, it's, including: It's not possible to say, one shot, go find all the potential bugs in this project.", "summary": "Firefox has tens of thousands of source code files and tens of millions of lines of code. It's not possible to say, one shot, go find all the potential bugs in this project."}, {"episode_id": "ep_how_i_ai_dee957949e29", "episode_title": "How to design AI agent loops: schedules, goals, and subagents in Claude Code and Codex", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-06-17T11:00:00Z", "overall_score": 87.8, "score_breakdown": {"clarity": 58.7, "originality": 60.5, "hype_penalty": 0.0, "actionability": 100.0, "technical_depth": 100.0, "information_density": 100.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1781646826473-9f0ed66ab4bc2.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/How-to-design-AI-agent-loops-schedules--goals--and-subagents-in-Claude-Code-and-Codex-e3ks6mt", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/121559197/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-5-16%2F426259555-44100-2-1b61a314a7bc8.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/How-to-design-AI-agent-loops-schedules--goals--and-subagents-in-Claude-Code-and-Codex-e3ks6mt", "verdict": "worth_your_time", "why_listen": "It goes beyond the title with direct discussion of going, loop, it's, including: If your agent isn't able to prompt itself through an automation, what are you even doing?.", "summary": "Prompts are out and loops are in. If your agent isn't able to prompt itself through an automation, what are you even doing?."}, {"episode_id": "ep_how_i_ai_adfb35ef61d4", "episode_title": "How Braintrust uses AI agents, evals, and CI to ship better software | Ankur Goyal", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-06-15T11:00:00Z", "overall_score": 86.2, "score_breakdown": {"clarity": 61.3, "originality": 49.9, "hype_penalty": 0.0, "actionability": 100.0, "technical_depth": 100.0, "information_density": 100.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1781559048546-21a17005915a1.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/How-Braintrust-uses-AI-agents--evals--and-CI-to-ship-better-software--Ankur-Goyal-e3kh936", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/121201190/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-5-9%2F425771285-44100-2-d91dab8395c07.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/How-Braintrust-uses-AI-agents--evals--and-CI-to-ship-better-software--Ankur-Goyal-e3kh936", "verdict": "worth_your_time", "why_listen": "It goes beyond the title with direct discussion of like, think, it's, including: I still talk to engineers that say AI on our most complicated things cannot do a good job.", "summary": "I'm still in, as I say, the year of our cloud, 2026. I still talk to engineers that say AI on our most complicated things cannot do a good job."}, {"episode_id": "ep_how_i_ai_101c2c2797e2", "episode_title": "Claude Fable 5 review: what the new Mythos model gets right (and very wrong)", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-06-09T18:28:35Z", "overall_score": 84.2, "score_breakdown": {"clarity": 70.8, "originality": 45.1, "hype_penalty": 3.0, "actionability": 100.0, "technical_depth": 100.0, "information_density": 100.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1781029679044-ad67b8388baea.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/Claude-Fable-5-review-what-the-new-Mythos-model-gets-right-and-very-wrong-e3kifk4", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/121240644/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-5-9%2F425823246-44100-2-7eb52f340db5.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/Claude-Fable-5-review-what-the-new-Mythos-model-gets-right-and-very-wrong-e3kifk4", "verdict": "worth_your_time", "why_listen": "It goes beyond the title with direct discussion of model, it's, fable, including: We're calling it Fable 5, and this new model is crushing benchmarks, but the question is, can it crush my backlog?.", "summary": "It's here, the model, the myth, the legend, Mythos from Anthropic has finally dropped. We're calling it Fable 5, and this new model is crushing benchmarks, but the question is, can it crush my backlog?."}, {"episode_id": "ep_how_i_ai_908b04bd201a", "episode_title": "Shopping with Claude: How to find quality brands, automate returns, and buy things that last 100 years | Nicole Ruiz", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-06-08T11:00:00Z", "overall_score": 89.2, "score_breakdown": {"clarity": 80.4, "originality": 45.7, "hype_penalty": 0.0, "actionability": 100.0, "technical_depth": 100.0, "information_density": 100.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1780693502516-2411dc4bba105.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/Shopping-with-Claude-How-to-find-quality-brands--automate-returns--and-buy-things-that-last-100-years--Nicole-Ruiz-e3k38jq", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/120741946/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-5-5%2F425590685-44100-2-32050b61fc9e.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/Shopping-with-Claude-How-to-find-quality-brands--automate-returns--and-buy-things-that-last-100-years--Nicole-Ruiz-e3k38jq", "verdict": "worth_your_time", "why_listen": "It goes beyond the title with direct discussion of like, really, want, including: I totally have the mental overload of having to buy something for my kids or my family or myself.", "summary": "The modern world is just rife with online administrative tasks where parents become the human link between all of these really, really hard to navigate systems where you're constantly just doing these small tasks, returns, purchasing, navigating help emails and all this different stuff. And then going through this kind of invisible checklist of like, is it made of a natural fiber?."}, {"episode_id": "ep_how_i_ai_4d2017589926", "episode_title": "Gemini Omni: Clone yourself with AI in under 15 minutes", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-06-03T11:00:00Z", "overall_score": 84.3, "score_breakdown": {"clarity": 71.8, "originality": 46.8, "hype_penalty": 0.0, "actionability": 83.0, "technical_depth": 100.0, "information_density": 100.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1780442530283-e6a64c22bfc8f.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/Gemini-Omni-Clone-yourself-with-AI-in-under-15-minutes-e3k2rdb", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/120728427/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-5-8%2F425699190-44100-2-5f8ebad546ff3.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/Gemini-Omni-Clone-yourself-with-AI-in-under-15-minutes-e3k2rdb", "verdict": "worth_your_time", "why_listen": "It goes beyond the title with direct discussion of going, video, it's, including: This episode is brought to you by Merge.", "summary": "Today, I am doing a very strange episode where I'm going to create a video avatar of myself and in about 15 minutes get to a full minute long video starring none other than your favorite podcast host, Claire Ho."}, {"episode_id": "ep_how_i_ai_a2f14612c7c3", "episode_title": "Building an iPhone app with zero technical skills | Bryce Rattner Keithley", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-06-01T11:00:00Z", "overall_score": 70.5, "score_breakdown": {"clarity": 55.5, "originality": 52.1, "hype_penalty": 15.0, "actionability": 100.0, "technical_depth": 100.0, "information_density": 100.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1780006903423-4fe28312436e3.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/Building-an-iPhone-app-with-zero-technical-skills--Bryce-Rattner-Keithley-e3jula3", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/120591107/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-4-27%2F424956437-44100-2-cde769b19e9fa.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/Building-an-iPhone-app-with-zero-technical-skills--Bryce-Rattner-Keithley-e3jula3", "verdict": "worth_your_time", "why_listen": "It goes beyond the title with direct discussion of like, it's, really, including: I opened Lovable and Replit actually on the same day and left the simplest prompt.", "summary": "I built an app called Daily Hundreds. I asked you the other day, I was like, are you in test flight?."}, {"episode_id": "ep_how_i_ai_6242df1851aa", "episode_title": "Claude Opus 4.8 is here. Is it as good as they say?", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-05-28T21:32:37Z", "overall_score": 80.4, "score_breakdown": {"clarity": 85.0, "originality": 82.0, "hype_penalty": 2.0, "actionability": 75.0, "technical_depth": 78.0, "information_density": 72.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1780002704196-ce78506b5ffd7.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/Claude-Opus-4-8-is-here--Is-it-as-good-as-they-say-e3k1l0v", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/120689119/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-4-28%2F425086059-44100-2-ee030741560df.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/Claude-Opus-4-8-is-here--Is-it-as-good-as-they-say-e3k1l0v", "verdict": "worth_your_time", "why_listen": "You\u2019ll learn where Opus 4.8 excels in agentic coding and where its overconfidence can mislead, with real-world test results from prototype to production edge cases.", "summary": "Claude Opus 4.8 shows strong performance in greenfield coding tasks and one-shot feature development, shipping working code in a prototype environment. However, it struggles with edge cases, existing codebases, and long-horizon autonomy, often hallucinating or over-rotating on small data points without validation. Despite high benchmarks like 69.2% on Sweebench Pro, the model exhibits overconfidence ungrounded in data, particularly in strategy and complex refactoring tasks."}, {"episode_id": "ep_how_i_ai_8108bcb9bff7", "episode_title": "The Codex feature that works while you sleep", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-05-27T11:00:00Z", "overall_score": 54.2, "score_breakdown": {"clarity": 0.0, "originality": 94.0, "hype_penalty": 0.0, "actionability": 0.0, "technical_depth": 82.0, "information_density": 75.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1779833292030-9dd15d6ecf581.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/The-Codex-feature-that-works-while-you-sleep-e3judoo", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/120583384/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-4-26%2F424944949-44100-2-5bf9048d90ac.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/The-Codex-feature-that-works-while-you-sleep-e3judoo", "verdict": "must_listen", "why_listen": "Learn how to offload persistent, tedious tasks to AI by defining measurable goals\u2014enabling autonomous problem-solving over hours without supervision.", "summary": "Goals in Codex enable long-running, autonomous AI execution by defining measurable outcomes instead of one-off prompts. The feature works by iteratively testing, executing, and validating steps until a predefined success state is reached\u2014such as eliminating all errors in a codebase or cleaning an inbox. Real-world examples include resolving thousands of edit-operation errors in a document editor and automating email triage across 4,000 messages."}, {"episode_id": "ep_how_i_ai_6328234be250", "episode_title": "How the engineer behind Claude Cowork actually uses Claude | Felix Rieseberg (Anthropic)", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-05-25T11:00:00Z", "overall_score": 73.0, "score_breakdown": {"clarity": 75.0, "originality": 85.0, "hype_penalty": 3.0, "actionability": 80.0, "technical_depth": 62.0, "information_density": 58.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1779469328660-24f2ec3ed82cd.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/How-the-engineer-behind-Claude-Cowork-actually-uses-Claude--Felix-Rieseberg-Anthropic-e3jn9c2", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/120349506/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-4-21%2F424637135-44100-2-74cda3214bf81.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/How-the-engineer-behind-Claude-Cowork-actually-uses-Claude--Felix-Rieseberg-Anthropic-e3jn9c2", "verdict": "must_listen", "why_listen": "Learn how an Anthropic engineer leverages Claude to build maintainable, data-driven personal systems while avoiding the pitfalls of over-automation.", "summary": "Felix Rieseberg, an engineer at Anthropic, uses Claude to solve real-world personal and product problems by treating data as a first-class citizen, building abstractions over time, and integrating AI into workflows without over-automating. He emphasizes comfort with latency, structured data extraction from silos like email, and using AI as a collaborative thought partner rather than a cursor-mover. His approach centers on iterative task abstraction, long-term maintainability, and designing systems where AI augments human judgment."}, {"episode_id": "ep_how_i_ai_5f56c22e8ad4", "episode_title": "What launched at Google I/O 2026 (30-minute day 1 recap)", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-05-20T01:58:14Z", "overall_score": 75.4, "score_breakdown": {"clarity": 85.0, "originality": 72.0, "hype_penalty": 3.0, "actionability": 75.0, "technical_depth": 72.0, "information_density": 68.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1779242106756-7e18fd02dde84.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/What-launched-at-Google-IO-2026-30-minute-day-1-recap-e3jkcso", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/120254808/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-4-20%2F424510185-44100-2-192703b265be8.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/What-launched-at-Google-IO-2026-30-minute-day-1-recap-e3jkcso", "verdict": "worth_your_time", "why_listen": "Get a hands-on breakdown of Google\u2019s latest agentic AI tools and which ones actually deliver on speed and usability in real workflows.", "summary": "Google I/O 2026 showcased a strategic shift toward agentic AI systems, highlighted by faster Flash models powering real-time coding in Anti-Gravity IDE and advanced video generation with Omni for consistent, character-aware video editing. New tools like Flow and Pomelli expand creative workflows with AI-driven design, branding, and workspace-integrated app development. Despite promising capabilities, several features showed sharp edges in real-world testing, including failed avatar generation and inconsistent performance."}, {"episode_id": "ep_how_i_ai_fbfab932bc1b", "episode_title": "HTML is the new Markdown: How Anthropic engineers are building with Claude Code | Thariq Shihipar", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-05-18T11:00:00Z", "overall_score": 87.3, "score_breakdown": {"clarity": 66.7, "originality": 49.7, "hype_penalty": 0.0, "actionability": 100.0, "technical_depth": 100.0, "information_density": 100.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1778948405763-1686c68a06d6d.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/HTML-is-the-new-Markdown-How-Anthropic-engineers-are-building-with-Claude-Code--Thariq-Shihipar-e3jd2qj", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/120015123/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-4-15%2F424187974-44100-2-6efb6e4bf7bd2.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/HTML-is-the-new-Markdown-How-Anthropic-engineers-are-building-with-Claude-Code--Thariq-Shihipar-e3jd2qj", "verdict": "worth_your_time", "why_listen": "It goes beyond the title with direct discussion of like, yeah, know, including: And this is honestly a mistake.", "summary": "Markdown became a really popular way of interacting with agents, but the plans are so long, I honestly have stopped reading them. I think that you still need to be really in the loop."}, {"episode_id": "ep_how_i_ai_03360c3ea9b2", "episode_title": "Spec-driven development: The AI engineering workflow at Notion | Ryan Nystrom", "podcast_name": "How I AI", "podcast_slug": "how_i_ai", "source_id": "src_how_i_ai", "category": "ai", "publish_date": "2026-05-11T11:00:00Z", "overall_score": 84.5, "score_breakdown": {"clarity": 61.5, "originality": 55.9, "hype_penalty": 3.0, "actionability": 100.0, "technical_depth": 100.0, "information_density": 100.0}, "podcast_cover_url": "https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/43412682/43412682-1778017900432-02e64c8cd8ce.jpg", "source_link": "https://podcasters.spotify.com/pod/show/pen-name/episodes/Spec-driven-development-The-AI-engineering-workflow-at-Notion--Ryan-Nystrom-e3it6be", "audio_url": "https://anchor.fm/s/1035b1568/podcast/play/119494446/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-4-5%2F423481186-44100-2-94dc1aaa80e9f.mp3", "listen_url": "https://podcasters.spotify.com/pod/show/pen-name/episodes/Spec-driven-development-The-AI-engineering-workflow-at-Notion--Ryan-Nystrom-e3it6be", "verdict": "worth_your_time", "why_listen": "It goes beyond the title with direct discussion of like, it's, know, including: You gotta explain it like I'm a five-year-old.", "summary": "One line that I've been putting in my prompts lately is, I literally don't know what I'm doing here. You gotta explain it like I'm a five-year-old."}], "category_breakdown": [{"category": "ai", "count": 18}]}