Agentic AI, LLM engineering, and the models behind modern automation — multi-agent systems, LLM evaluation and comparisons, RAG, fine-tuning, AI infrastructure, security, and production AI engineering.
From the blog
Gemini 2 Pro and Claude 4.7 ship 1M+ context windows. RAG still wins on most enterprise queries — 1s latency vs 30-60s, 1/1250 cost, and citation tracking. Here is the decision matrix.
Run a 5% → 25% → 50% → 100% canary on a voice agent with Argo Rollouts, AnalysisTemplate against eval pass-rate, and the new Metric AI plugin from ArgoCon 2026.
Quick-reply chips lift chat conversion 28–40%. Here is how 2026 chat agents render carousels, suggest replies, and route users without forcing them to type.
Turborepo 3.0 (canary, 2026) is the first monorepo orchestrator built for the agent era. Wire git worktrees, remote cache, and PR previews for AI apps.
A practical engineering deep dive into Claude Haiku 4.5, covering architecture, tradeoffs, and what production teams need to know about low-latency AI.
A practical engineering deep dive into Claude Opus 4.7, covering architecture, tradeoffs, and what production teams need to know about Opus 4.5.
A practical engineering deep dive into Anthropic Skills vs tools, covering architecture, tradeoffs, and what production teams need to know about Claude API design.
A practical engineering review of OpenAI AgentKit 1.0's visual builder, hosted state, and deploy pipeline — what production teams should expect in 2026.
Prompt A/B testing is not about proving a winner — it is about learning how changes behave under real workloads. Here is the 2026 playbook with Langfuse, Braintrust, and PostHog.
