In a solo episode of the How I AI podcast, host Claire tested Jev, TypeSafe AI's new decision model that returns structured choices, scores and probabilities instead of generated text, using it to ana…
TypeSafe AI's Jev decision model returns type-safe structured values — a choice, a score, or a probability — instead of generated text, priced at 4 cents per million input tokens with no output charge…
In a blind evaluation on the How I AI podcast, host Claire Vo tested Claude Opus 5.5, GPT-6 Astra, GPT-6 Sol, and other newly launched models across emails, PRDs, frontend prototypes, backend work, lo…
Anthropic shipped Claude Opus 5.5, which is 40% cheaper than Opus 5, faster, and built on what Anthropic calls a fundamentally different alignment approach, according to a first-person review by ChatP…
Hamel Husain and Shreya Shankar, drawing on work with over 50 AI companies, published an advanced follow-up on building eval systems for AI products, arguing that most teams skip the critical step bef…
In a solo episode of the How I AI podcast, host Claire reviewed Meta's Muse, a personal AI agent that manages her family calendar, generates a morning newsletter PDF on its first attempt, tracks perso…
Warp, the AI-powered terminal and software factory platform led by co-founder and CEO Zach Lloyd, ships 2,000 pull requests a month through its cloud-based software factory, which runs a Slack → Linea…
SpaceXAI Grok Bot designers John Bai and Peng Zheng demonstrated on the How I AI podcast how they use AI agents to automate design work, with Peng building a self-updating personal site where Grok Bot…
Grok Bot designers John Bai and Peng Zheng use AI agents to build personal sites and product prototypes, including Peng's self-updating personal website that runs on Grok Bot as its entire backend pip…
In a solo podcast episode, Claire explains why she replaced her entire OpenClaw agent stack with Grok Bot, citing its simplicity, reliability, and multi-account support as key advantages. She details …
Stripe engineering manager Sharadh Krishnamurthy revealed that the company built its internal AI agent Kai from scratch, which is now used by more than 10,000 employees weekly, citing the need for cus…
OpenAI's GPT-6 Astra model successfully completed tasks that previous models like GPT-5.6 Sol and Fable could not, according to early-access user Claire Vo, who demonstrated breakthroughs in ChatPRD's…
Anshu Chimala, who led software engineering and design teams at Apple for 12 years, shares techniques in a newsletter post for unlocking AI's creative potential in design, arguing that typical LLMs pr…
Daniel Blum, a product manager at Melio, has built a self-improving AI system using Anthropic's Claude and Cowork that now handles 70% to 80% of his workday, enabling him to complete a week's worth of…
Daniel Blum, a product manager at B2B payments company Melio, has built a Claude- and Cowork-based productivity system that automates his Notion board, processes Slack and email, and runs self-improve…
OpenAI product lead Tara Seshan discussed the rise of persistent AI coworkers in a podcast, describing a shift from 'rowing' to 'steering' where human judgment and ambition become key differentiators …
In a solo episode of the How I AI podcast, Claire tested Grok Bot, Cursor Origin, and Grok 4.6, finding that Grok Bot's multi-account connectors solve a problem other agent platforms ignore, while Cur…
Ryan Carson, solo founder of Untangle, a B2B SaaS platform for family law firms, said he spent $20,000 on Devin, Cognition's AI coding agent, in one month, managing 15 concurrent agents with a folder …
Lenny's Newsletter's subscriber-only Slack community shared favorite Lenny's Product Pass tools, discussed how AI is reshaping hiring, and offered advice on what to prioritize when joining a new compa…
A new Claude Code-based interview coach, built by Lenny's Newsletter community research lead Noam Segal from techniques used by over 30 tech professionals, helps job seekers prepare for interviews. Th…