News and engineering notes from across the AI field — agents, inference infrastructure, model releases, and the patterns worth paying attention to. Updated weekly.
Every architectural decision in your agent system — subagent delegation, memory, tool design, model choice — boils down to managing a single finite resource: the context window. Here's how to treat the context budget as a first-class constraint, with concrete patterns that ship.
OpenAI Agents forget everything between runs by default. Here's how to wire SQLiteSession for dev, Redis for production, and wrap it in a FastAPI endpoint — with working code.
Claude Sonnet 5 at $2/$10 per million tokens — an Opus 4.8-class agent model for Sonnet prices. GPT-5.6 Sol, Terra, and Luna in limited government-gated preview. Fable 5 leaves subscriptions July 7 at $10/$50 per MTok. And the US quietly lifted export controls on Mythos 5. What shipped, what it costs, and what to actually route your agents through.
Per-token inference costs collapsed 10x in 2026. DeepSeek V4 Flash costs $0.14/M tokens. Yet inference now eats 85% of enterprise AI budgets, and agent workloads spike bills 5-30x. The bottleneck shifted.
The synchronous agent loop is dying. In its place: event-driven agent systems built on Kafka, Flink, Temporal, and Restate. Here's why the shift is happening now, what the new architecture looks like in code, and what breaks when you get it wrong.
Your CFO just asked why the team has $200/mo coding tool subscriptions. We compared 9 tools across free, individual, team, and enterprise tiers. Real costs, credit traps, and the one number that matters: what a heavy user actually pays per month.
Gartner says AI spending hits $2.52T this year, but 88% of agents never reach production. The build-vs-buy question is where most of that money gets burned. Here's a concrete framework for making the call — with real cost data and zero vendor spin.
Pair with one of our solutions architects. Two weeks from kickoff to a deployed, evaluated, observable agent in your stack.