News and engineering notes from across the AI field — agents, inference infrastructure, model releases, and the patterns worth paying attention to. Updated weekly.
A generation of agent startups will get commoditized. The ones that survive own one of four stateful layers: Memory, Execution, Tooling, or Governance. Here's how to tell the difference between a moat and glue code.
RunPod H100 at $2.69/hr. Lambda at $4.29/hr. CoreWeave at $6.16/hr — but requires 8-GPU minimums. Which GPU cloud makes sense for your agent workloads?
Google's ADK 2.0 ships graph workflows in four languages with native A2A. OpenAI added sandbox execution and three-tier guardrails. Claude offers the deepest MCP integration in the ecosystem. We built the same multi-step agent across all three — here's how they compare, where each one wins, and what you'll regret picking.
Customer service agents resolve tickets at 9x lower cost. Coding agents review PRs at 1/66th the price. Here are the enterprise AI use cases generating measurable ROI in 2026 — and the ones still burning budget.
Cursor's Composer 2.5 matches GPT-5.5 and Opus 4.7 on agentic coding benchmarks at 1/10th the cost. Combined with Spotify's 99% AI coding adoption and Microsoft's computer-use GA, May 18–25 marks the week coding agents stopped being a productivity experiment and started being an infrastructure decision.
Google replaced the search box with 24/7 information agents. Anthropic hit its first profit and hired Karpathy. OpenAI filed for IPO. Here's what the biggest week in AI history means for the agent stack.
Both engines now share NVIDIA's FlashInfer kernels and expose identical OpenAI-compatible APIs. Meanwhile, SGLang spun out as RadixArk with $100M in seed funding, and vLLM hit 2M weekly installs. The inference layer is consolidating faster than anyone expected — here's what that means for teams building on top of it.
Pair with one of our solutions architects. Two weeks from kickoff to a deployed, evaluated, observable agent in your stack.