How Jev Turns AI Into Software That Gets Things Done
a16z · 2026-09-28 · 42 min
https://www.youtube.com/watch?v=Ut3LOjKNJaEVideo summary
TypeSafe founder Diogo Almeida says Jev embeds probabilistic intelligence in software, aiming to automate work and make SaaS applications more capable.
TypeSafe founder Diogo Almeida tells a16z’s Ben Horowitz and Martin Casado that AI coding agents can write code faster without making software itself more capable. TypeSafe’s Jev adds an intelligent layer inside programs: developers describe intent and define a state machine, and Jev makes probabilistic decisions with confidence levels. Almeida says reliable automation—not flashy demos—is the goal, distinguishing robustness from uptime or strict determinism. He questions why basic tasks remain manual despite capable models, noting OpenAI has pursued customer-service automation since 2020, and argues the issue is not simply missing data. Rather than a “SaaS apocalypse,” he predicts established software companies could benefit by using Jev to improve workflows for customers they already reach. The conversation also explores Jev’s potential inside system infrastructure, the trade-offs of intelligence per dollar, and a future where interfaces understand “do what I mean.”
Chapters
- 0:00Meet Diogo and TypeSafe: Jev brings AI into software for automation
- 4:07Smart software, not just faster code: Jev adds a confidence-based classifier to programs
- 7:20Smart software, not just faster code: Jev targets program internals and intelligence per dollar
- 11:48Smart software, not just faster code: Diogo’s OpenAI path and TypeSafe’s “prod not god” vision
- 15:46Where’s all the automation? From reliable background tasks to the drive-through test
- 22:00Is it just a data problem? Long-tail exceptions, support metrics, and Jev’s unexpected reception
- 25:47Is it just a data problem? Jev’s reliability, coding-agent limits, and SaaS’s reversal
- 30:21SaaS apocalypse reversed: AI could make existing products far more useful
- 34:58New capabilities, not more code: Jev points toward probabilistic systems and smarter infrastructure
- 38:27Apps vs. system guts: Jev connects AI to state machines beneath the interface
- 41:08Reliability and “do what I mean”: TypeSafe delays Jev to earn user trust
This is a Tier 1 public summary
Whether the chapter key points, section summaries and mind map are public is up to the person who shared it. Want the full analysis?Submit one yourself.
More from this channel
How Cursor Built One of AI’s Fastest-Growing Companiesa16zCursor bet on the human-model interface, grew rapidly without early sales hires, and later expanded through Graphite and founder acquisitions.
Why Top Founders Are Racing Into AI Infrastructurea16za16z’s Machine Age Fund targets AI infrastructure as GPU supply is booked to 2028 and memory demand needs three years of capacity.
Why AI Demand Is Outrunning Compute Supplya16zGavin Baker argues AI compute demand will outpace supply, with sub-one-year infrastructure paybacks and orbital data centers approaching.
What Today’s Best Models Still Can’t Do in Matha16zDaniel Litt praises AI’s Erdős unit-distance result but warns that proofs alone cannot replace mathematical understanding or human curiosity.
Inside Moderna’s Biggest mRNA Test Since COVIDa16zModerna and Merck’s personalized mRNA vaccine beat Keytruda alone in a Phase 3 melanoma trial, after 1,000 cancer-vaccine trials failed.
Related analyses
Why Investors Are Rethinking Everything for the AI Eraa16za16z’s David George and Accolade’s Aram Verdiyan argue AI is intensifying venture power laws, with only 20 of 3,000 US firms delivering consistent 3x net returns.
The 5 megatrends that will dominate 2026Money & MacroJuri forecasts China’s industrial rise, debt constraints, an AI bubble surviving 2026, and a 25% chance of a Taiwan blockade.
To Regulate AI Effectively, Focus on How It’s Useda16z Deep DivesMartin Casado argues AI laws should target harmful uses, while regulatory uncertainty pushes US startups toward Chinese open-source models.
The RAM Crisis Keeps Getting WorseColdFusionAI data centers are tightening RAM supplies, driving up device costs as Samsung, SK Hynix, and Micron prioritize enterprise buyers.
股市暴跌，無人消費：AI贏了，但白領消失了？！《全球智能危機》Better Leaf 好葉《2028 年全球智能危機》警告 AI 裁員恐衝擊 13 兆美元房貸，並提出投資、決策與工作流三種應對策略。