Field notes · AI & software
Useful answers before you build.
Practical decision guides drawn from building AI agents, knowledge systems, ecommerce assistants, and full-stack products end to end.
Engineering resources
Beyond Chatbots: What AI Agents Actually Do for Businesses in 2026
A 2026 map of production AI agent use cases — from support and operations to browser automation and voice — and the integration realities that decide which ones work.
Voice AI Agents in 2026: Architectures That Actually Ship
Speech-to-speech models vs. modular pipelines vs. managed platforms — how production voice agents are built in 2026, where latency budgets go, and what still breaks.
Computer-Use and Browser Agents in 2026: The New RPA
How businesses use agents that operate real interfaces — legacy portals, ERPs, supplier back-ends — plus the reliability and security rules that make them deployable.
RAG vs. Filesystem in AI Agents: The 2026 Retrieval Rethink
Claude Code dropped vector search for grep and most coding agents followed. When agentic file search beats RAG, when embeddings still win, and how to choose in 2026.
Choosing an AI Agent Framework in 2026: A Decision Guide
Provider SDKs vs. independent frameworks — OpenAI Agents SDK, Claude Agent SDK, LangGraph, Agno, Pydantic AI — and the questions that actually decide the choice.
Agentic Commerce in 2026: When the Customer Is an AI Agent
ChatGPT checkout, ACP, AP2, and UCP explained for merchants — how agent-driven buying works in 2026 and what ecommerce teams should do about it now.
How to Secure an MCP Server in Production
A 2026 MCP security checklist covering OAuth boundaries, token audience validation, SSRF, confused-deputy attacks, tool permissions, and untrusted output.
How to Evaluate AI Agents in 2026: Outcomes, Traces, and Tool Use
A production evaluation method for AI agents that tests environment outcomes, tool trajectories, permissions, recovery, and cost—not just the final answer.
Context Engineering for Long-Running AI Agents
A 2025–26 guide to managing instructions, tools, retrieval, memory, compaction, and subagents when an agent must work across many steps.
AI Agent Protocols in 2026: MCP, A2A, A2UI, AG-UI, and UCP
A practical guide to the 2026 agent protocol stack: which standards connect tools, agents, interfaces, and commerce—and when a normal API is still enough.
Agentic RAG in 2026: When Iterative Retrieval Beats One-Shot Search
A practical architecture for company knowledge agents that plan searches, route across sources, verify evidence sufficiency, preserve permissions, and stop on budget.
Stop Flattening PDFs: Multimodal Document AI in 2026
A production guide to preserving layout, tables, charts, images, and provenance when building AI systems over PDFs and mixed business documents.