News and engineering notes from across the AI field — agents, inference infrastructure, model releases, and the patterns worth paying attention to. Updated weekly.
Anthropic paused its Agent SDK billing overhaul on launch day. Salesforce ditched $2/conversation for Flex Credits. Per-seat SaaS is dying, and agent-native pricing remains an unsolved equation. Here's why — and what comes next.
Every major agent framework now shares the same primitives: state graphs, structured tool calling via MCP, handoff delegation, and lifecycle hooks. The framework wars are ending. Here's what the convergence means for your stack — and where the real differentiation lives.
LiteLLM is free but costs $500–$2,000/mo to self-host. Portkey starts at $49/mo (log-based). Kong at $25/mo per control plane. The real cost of each — with hidden ops and scaling traps.
74% of enterprises want AI to grow revenue. Only 20% see it. The industry's cost-cutting obsession is hiding where agent ROI actually lives — and it's bigger.
Trace every tool call, guardrail check, and handoff in your OpenAI Agents SDK app with Langfuse. Working code, no fluff.
Three days after launch, the US government ordered Anthropic to suspend Fable 5 and Mythos 5 for all foreign nationals. The jailbreak was verbal-only evidence. Anthropic was already suing the DoD. Here's how the week that broke the 'one model everywhere' assumption changes your stack.
Apple put Claude on 2 billion iPhones. SpaceX raised $75B in the largest IPO in history. And Anthropic draws a line between 'chat' and 'agents' — starting tomorrow, June 15. Here's what the week that just reshaped the agent economy means for builders.
Pair with one of our solutions architects. Two weeks from kickoff to a deployed, evaluated, observable agent in your stack.