Production lessons from AI practitioners
The AI Runtime is a community of AI practitioners. Read the weekly newsletter, come to the Boston meetups, and become part of the Field Lab. It starts with a free weekly issue of production lessons, the kind you'd forward to your team.
Read by AI practitioners at IBM, Amazon, Meta, Google, Nvidia, OpenAI, MIT, Harvard, and more for production learnings.
Free. No spam. Unsubscribe in one click. See past issues →
Read by AI practitioners at
- IBM
- Amazon
- Meta
- NVIDIA
- OpenAI
- MIT
- Harvard
- 2,000+ newsletter subscribers
- 200+ in-person attendees
Read, meet, and build
- Read
The weekly newsletter
Production lessons on Vertical AI Agents, Model Reliability Engineering, and lessons from the trenches of shipping AI. Free, every week.
Read the newsletter → - Meet
The Boston meetup
A monthly meetup in Cambridge. Two practitioner talks a night, real production stories, and the people who ship.
See the next event → - Build
The Field Lab
A library of production-shaped AI problems and a build pilot, so practitioners work on real problems instead of demos.
Explore the Field Lab →
Fresh from the newsletter
- Jun 15, 2026 The "Self-Improving" AI Myth (And What 60 Production Deployments Actually Do) Sixty production deployments converged on a three-layer architecture where the eval surface, not the base model, is the moat.
- Jun 11, 2026 Dario Amodei’s “Policy on the AI Exponential” Describes a World Banking AI Already Lives In His new essay asks regulators to build an FAA for AI models. If you ship AI inside a bank, you already work in that regime, and there is a five-minute test that tells you whether your agent is as far
- Jun 8, 2026 Harness Half-Life: A Field Playbook for Catching Agent Decay The harness engineering discourse names what to build. The Model Reliability Engineering arc names how long the build lasts, what kills it, and what to do at week six.
- Jun 8, 2026 The AI Eval Gate Cheat Sheet Most AI projects die in the gap between "works in the demo" and "works in production."
The AI Runtime Boston
A monthly meetup in Cambridge for practitioners shipping AI to production. Two practitioner talks a night, real production stories.
From the last meetup
A full room in Cambridge for AI Agentic Architectures. Two production talks, real questions, people who ship. The next one is coming.
Scroll for more, tap a photo to enlarge.
Build on real problems, not demos
The Field Lab is where builders work on real, production-shaped AI problems. A library of buildable briefs, a build pilot, and the free tools to start.
The AI Runtime Field Guide
A guided reading path through The AI Runtime for AI practitioners. The essential reads on AI engineering, Model Reliability Engineering, and vertical agents, in the order that builds real production intuition. Free, no email required.
Get it in your inbox
Free, weekly, anti-hype. Production lessons from practitioners, plus the next Boston event before the public drop.
Get The AI Runtime in your inbox
One free issue a week. The operational layer where AI actually runs.
- Evals, agents, inference, reliability, cost
- Specific and sourced, the kind of piece you forward to your team
- The next Boston meetup before the public Luma drop
Read by AI practitioners at IBM, Amazon, Meta, Google, Nvidia, OpenAI, MIT, Harvard, and more for production learnings.
Free. No spam. Unsubscribe in one click. See past issues →