“How 1.5 engineers got Stripe Kai in two weeks #1 in Claire Vo recapped a How I AI episode in which Sharadh Krishnamurthy demonstrated Kai, Stripe’s “company brain,” which the post says 1.5 engineers and 2 weeks helped deliver.”

#1 in Claire Vo recapped a How I AI episode in which Sharadh Krishnamurthy demonstrated Kai, Stripe’s “company brain,” which the post says 1.5 engineers and 2 weeks helped deliver. The episode covered projects as governance, skill routing and telemetry, and a skills platform described as working for 10k teammates.

“claire vo shared that she has an agent named Penny Pincher, which, about 10 messages into their interaction, was negotiating a vintage Rolex for her.”

#8 𝕏 claire vo shared that she has an agent named Penny Pincher, which, about 10 messages into their interaction, was negotiating a vintage Rolex for her.

“#6 𝕏 claire vo 🖤 questioned whether agents can work without indexing source data, how ephemeral connectors and stored data should be presented to users, and how to prevent prompt injection.”

#6 𝕏 claire vo 🖤 questioned whether agents can work without indexing source data, how ephemeral connectors and stored data should be presented to users, and how to prevent prompt injection. She characterized an unnamed harness as immature and lacking user-empathetic evaluation, while noting that self-serve data deletion shipped but promised email follow-up did not occur.

“Claire Vo shared how she uses Codex browser/Chrome/computer for operational tasks including accounting, inbox management, Stripe Radar configuration, browser-based QA, security questionnaires, SaaS setup when an API is unavailable, and subscription cancellation.”

GenAI PM Daily August 20, 2026 GenAI PM Daily 🎧 Listen to this brief 3 min listen Today's top 20 insights for PM Builders, ranked by relevance from Blogs, X, YouTube, and LinkedIn. OpenAI announces Zero Data Retention for frontier models #1 📝 OpenAI News Offering Zero Data Retention for frontier models - OpenAI announces offering zero data retention for frontier models, committing to not retain user data for those models and clarifying how this impacts customers and data handling. The post outlines the company's privacy-focused approach for frontier model interactions. Also covered by: @OpenAI , @OpenAI , @Sam Altman #2 𝕏 Cursor announced that it can now monitor pull requests, watch a Slack thread, and run scheduled tasks. Cloud agents automatically subscribe to pull requests they create and drive them to completion. #3 𝕏 Mustafa Suleyman announced that MAI-Image-2.5 is ranked #1 on the Artificial Analysis leaderboard for image editing. #4 𝕏 Logan Kilpatrick announced that Google AI Studio now supports GitHub repository imports and bi-directional push/pull synchronization. A new UI also supports force pushes and merges. #5 𝕏 Qwen shared that Qwen3.8-27B ranked as the #1 open-weight model on Harvey’s Legal Agent benchmark, describing it as capable of professional tasks while remaining small enough to run locally. #6 𝕏 NVIDIA shared that NVIDIA cuOpt, its open-source solver, is the fastest open-source solver on Hans Mittelmann benchmarks across three optimization problem classes. #7 𝕏 Results from benchmarks of 300+ NVIDIA verified skills on real tasks showed that using skills improved correctness by 41 points, effectiveness by 39 points, and efficiency by 35 points. SkillEvaluator is open source for testing skills before shipping. #8 𝕏 Philipp Schmid shared that Gemini 3.7 Flash ranked first on Artificial Analysis’s new AA-AnalystAgent, which covers 80 real-world quantitative analysis tasks across 14 business and scientific domains. #9 𝕏 Claire Vo shared how she uses Codex browser/Chrome/computer for operational tasks including accounting, inbox management, Stripe Radar configuration, browser-based QA, security questionnaires, SaaS setup when an API is unavailable, and subscription cancellation.

“claire vo 🖤 commented that she maintains two main OpenClaws, one lifeguard OpenClaw, and one Codex tuned to connect via SSH and rescue both main OpenClaws—a setup she calls annoying to maintain and a labor of love.”

#8 𝕏 claire vo 🖤 commented that she maintains two main OpenClaws, one lifeguard OpenClaw, and one Codex tuned to connect via SSH and rescue both main OpenClaws—a setup she calls annoying to maintain and a labor of love.

“"#12 𝕏 claire vo 🖤 praised @bot’s UX, highlighting multi-account sign-in for services such as Slack and Google Workspace as its key feature for managing systems across multiple businesses."”

#12 𝕏 claire vo 🖤 praised @bot’s UX, highlighting multi-account sign-in for services such as Slack and Google Workspace as its key feature for managing systems across multiple businesses. She said she tested @bot early and provided feedback, though it has not yet replaced another tool she represented with a lobster emoji.

“claire vo demonstrated how she used Codex to turn something into an always-on toolbar app for managing her smart lightbulb from her Mac, in a post referencing a video.”

#12 𝕏 claire vo demonstrated how she used Codex to turn something into an always-on toolbar app for managing her smart lightbulb from her Mac, in a post referencing a video.

“claire vo recommends @evedev_ as a default framework for internal agents, citing its instructions, skills, built-in channels, and connectors.”

#11 𝕏 claire vo recommends @evedev_ as a default framework for internal agents, citing its instructions, skills, built-in channels, and connectors. She also announced a forthcoming How I AI episode about building a PR review and approval agent with Eve, while a quoted post describes Vercel’s internal AI agent @v as powered by @evedev_.

“#17 ▶️ I hate Opus 5. It’s the best model, anyway. How I AI Podcast Claire Vo runs a live How I AI benchmark comparing seven AI models (Opus 5, Sonnet 5, Fable, Opus 4, Mabu, GPT Terra and Gemini 3.1 Pro) across six tasks—PRD creation, prototype creation, wireframe creation, bug triage, agentic coding and agent voice—scored 70% by her manual vibe check and 30% by GPT-5.5, with Opus 5 emerging first on the leaderboard.”

#17 ▶️ I hate Opus 5. It’s the best model, anyway. How I AI Podcast Claire Vo runs a live How I AI benchmark comparing seven AI models (Opus 5, Sonnet 5, Fable, Opus 4, Mabu, GPT Terra and Gemini 3.1 Pro) across six tasks—PRD creation, prototype creation, wireframe creation, bug triage, agentic coding and agent voice—scored 70% by her manual vibe check and 30% by GPT-5.5, with Opus 5 emerging first on the leaderboard. The benchmark evaluated seven models—Opus 5, Sonnet 5, Fable, Opus 4, Mabu, GPT Terra and Gemini 3.1 Pro—in a blind test over six tasks: PRD creation, prototype creation, wireframe creation, bug triage, agentic coding and agent voice.

“claire vo is retiring her keyboard by handing her computer to GPT-5.6–powered Codex agents, demoing automated front-end bug detection (03:49), synthetic browser persona research (24:26), LinkedIn inbox cleanup (41:19) and personal shopping (44:39).”

#23 𝕏 claire vo is retiring her keyboard by handing her computer to GPT-5.6–powered Codex agents, demoing automated front-end bug detection (03:49), synthetic browser persona research (24:26), LinkedIn inbox cleanup (41:19) and personal shopping (44:39). #24 📝 Ampcode Chronicle Event Driven Orbs - Amp orbs can now be woken by external HTTP requests: amp.createWebhook registers a durable webhook endpoint that verifies signatures, deduplicates deliveries, and spawns read-only orb threads with trusted repository/event/actor metadata so the orb can inspect and act on GitHub issues, CI failures, Linear issues, Discord messages, etc.