AI Infrastructure
The systems that keep AI products running: inference and serving, GPUs, model routing, sandboxes and compute for agents, observability, and the spend controls teams add once token bills arrive. Practical recaps from the people who operate this infrastructure.
- 'How to Know If Your AI Agent Is Any Good: Evals With Phoenix & Claude - Laurie Voss, Arize AI'
- Lessons from Generating 12 Trillion Synthetic Tokens - Bogdan Gaza, DatologyAI
- The AI Bill Is Too Damn High: Tokenomics 101 - Eugene Cheah, Featherless AI
- Why One AI Agent Isn’t Enough (And How to Run 1,000) - CJ Avilla & Harrison Stall, Anthropic
- Stop Renting Your AI's Memory - Dylan Couzon, Qdrant
- No, That's Not a Software Factory - Ryan Cooke, WorkOS
- Autoresearch Made Our Models 3x Faster - Tejas Bhakta, Morph
- 'One Operator, Many Drones: Inside Skydio''s Autonomy Stack - Suchet Bargoti, Skydio'
- 'Skill issue: stop deploying vision language models, use them with Skills - Merve Noyan, Hugging Face'
- The Frontier AI Inference Cloud for Agents - Byung-Gon (Gon) Chun, FriendliAI
- 'Two Bugs That Hid in Plain Sight: A vLLM Debugging Detective Story - Asaf Gardin & Yuval Belfer'
- Are LLM Performance Benchmarks Reliable? - Ashok Chandrasekar & Jason Kramberger, Google
- Large clusters for small models - Daniel Svonava, Superlinked
- Operating Distributed Inference Systems at Scale - Nishant Gupta & Naman Ahuja, Meta
- 'Routing LLM Inference in Production: From Engine Signals to Policy - Qianru Lao & Lu Zhang, OpenAI'
- 'Vertical Mobility: Inference from MVP to Trillion-Parameter Workloads - Sitanshu Gupta, CoreWeave'
- What's New in Inference Engineering - Philip Kiely, Baseten
- Homa: The End of TCP for AI Clusters - John Ousterhout, Stanford
- Connect AI to Billions of Legal Documents - Simon Eskildsen, turbopuffer & Jacob Lauritzen, Legora
- Where RL Will Take Search - Maximilian-David Rumpf, SID.ai
- Your Agreements Are a Database You Can't Query - Hiral Shah, Docusign & Sean Sodha, NVIDIA
- 'Mousepower: agents that can’t be measured, can’t be managed. - Maximillian Piras, Yutori'
- Deep dive on LLM Inference at Scale - Harshul Jain, Audible & Tanmay Sah, Independent AI Researcher
- Tethered: Our Agents Are Us - Shu Fang, Two Sigma
- 'When AI Agents Pay and Sellers Monetize: Building x402 Apps on AWS - Anil Nadiminti, AWS'
- 'Why Your AI Agent Needs a Wallet: USDC and Nanopayments - Harshal Bhangale, Circle'
- Can LLMs Write Fast Multi-GPU Kernels? - Simran Arora, Together AI
- 'The Agent Behind the Curtain: Building the Oz Cloud Agent Platform - Safia Abdalla, Warp'
- 'Preferences Over Benchmarks: Model Routing - Archana Kamath & Tyler Gillam, DigitalOcean'
- Building Agents Is Trivial Now, Context Is the Next Frontier - Jeff Ng, Unblocked
- 'FinOps for AI Agents: Who Spent All the Tokens? - Tisha Chawla & Susheem Koul, Microsoft'
- Give the Agent a Budget, Not a Token - Sachin Malhotra, Anthropic
- Open Source Is Dead. Long Live Open Source. - Saoud Rizwan, Cline
- 'Building Turbopuffer: Gergely Orosz (@pragmaticengineer ) × Simon Eskildsen (CEO)'
- Gadgets: Personal app vibe coding that is actually safe - Kenton Varda, Cloudflare
- The State of Model Routing - NVIDIA, Cognition, OpenRouter
- Learning on the Job: The Future of Post-Training - Raymond Feng, Applied Compute
- Scaling to Long Horizons - Ross Taylor & Chengxi Taylor, General Reasoning
- 'Agents at Scale: Inside MiniMax''s Model and the Infrastructure Behind It
- Computer-Use 2.0: Agents Just Got Multi-Cursor - Francesco Bonacci, Cua
- WTF Is the Context Layer? The Missing Infrastructure for Production Agents
- 'From fork() to Fleet: Designing an Agent Sandbox Cloud - Abhishek Bhardwaj, OpenAI'
- A Song of Types and Agents - Roberto Stagi, Ratel
- The Agentic Web and the Bazaar Era of AI - Ramesh Raskar, MIT Media Lab
- Deterministic Infra for Non-Deterministic AI Agents - Nishant Gupta, Meta Superintelligence Labs
- 'Bypassing the Multimodal Tax: Hybrid RAG, SQL RRF & UI Telemetry - Abed Matini, Ogilvy'
- 'OpenClaw in Your Hand: Building a Physical AI Terminal - Lech Kalinowski, Callstack'
- Your Agent Is Wasting Tokens and You Don't Know It - Erik Hanchett, AWS
- 6 Things to Know about AIE World's Fair 2026
- You Might Not Need 50 Diffusion Steps - Ziv Ilan, Nvidia
- Why Can't Anyone Answer Questions About the Business? - Garrett Galow, WorkOS
- GPU Cloud Deployment Without Leaving Your IDE — Audry Hsu, RunPod
- Self Driving Products: Product Signals to Pull Requests — Joshua Snyder, PostHog
- Under 5 minutes to a deployed LLM endpoint — Audry Hsu, RunPod
- Why Eval++ Is the Next Great Compute Primitive — Sunil Pai & Matt Carey, Cloudflare
- Building safe Payment Infrastructure for the autonomous economy — Steve Kaliski, Stripe
- AI Engineer Melbourne 2026 Keynote Livestream | Day 1
- What Lies Beneath the API — Benjamin Cowen, Modal
- What if the network was the sandbox? — Remy Guercio, Tailscale
- 'Reachy Mini: the $300 open source robot you can actually hack — Andres Marafioti, Hugging Face'
- How agent o11y differs from traditional o11y — Phil Hetzel, Braintrust
- Run Frontier AI at Home — Alex Cheema, EXO Labs
- Gemini Nano on device — Florina Muntenescu & Oli Gaymond, Google DeepMind
- 'Lobster Trap: OpenClaw in Containers from Local to K8s and Back — Sally Ann O''Malley, Red Hat'
- Scaling Agents on Kubernetes with acpx and ACP — Onur Solmaz, OpenClaw
- Don't Build Slop (4 Levels of AI Agent Maturity) - Ara Khan, Cline
- How Building with AI Can Double the Throughput of Your Engineering Team — Brian Scanlan, Intercom
- CI/CD Is Dead, Agents Need Continuous Compute and Computers — Hugo Santos and Madison Faulkner
- Give Your Agent a Computer — Nico Albanese, Vercel
- Two Roads to Durable Agents: Replay vs. Snapshot — Eric Allam, CEO, Trigger.dev
- Why MLX — Prince Canuma, Neywa Labs
- Accelerating AI on Edge — Chintan Parikh and Weiyi Wang, Google DeepMind
- The Small Model Infrastructure Nobody Built (So We Did) — Filip Makraduli, Superlinked
- 'Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked'
- 'TLMs: Tiny LLMs and Agents on Edge Devices with LiteRT-LM — Cormac Brick, Google'
- From Chaos to Choreography: Multi-Agent Orchestration Patterns That Actually Work - Sandipan Bhaumik
- Claude Code With No Rate Limits
- Multi-agent Orchestration with Opus 4.6
- Convex: The New Database for The AI Era
- AGENT THREADS
- How To Code With A.I
- Agent SDK POC Validation
- Atlas — Agent OS Web Scraper & Core Pipeline Milestones