AI
Articles on using and building with LLMs, including how context windows and RAG work, and choosing between frontier models and local inference.
- AIJune 23, 20268 min read
You're Not Getting the Most Out of LLMs
LLMs are good at some things and bad at others. Getting more out of them comes down to matching the tool to the task and running the model in a setup that can actually do work, not just a chat window that talks.
Read article - AIJune 11, 202613 min read
Frontier Models vs Local Inference: How to Choose
What frontier models and local inference each offer, the trade-offs in data control, cost, and jurisdiction, and the benchmark numbers the labs report.
Read article - AIJune 2, 202616 min read
What AI Platforms Do for You: A Founder's Map of the 2026 Ecosystem
A plain map of the AI ecosystem in 2026, from chat assistants to coding agents to work platforms, judged by the three capabilities that decide whether a tool actually helps: a real browser, script execution, and MCP extensibility.
Read article - AIApril 20, 202611 min read
How AI Memory Actually Works: Context Windows and RAG
LLMs don't remember you. Every response is a cold start. Understanding context windows, compaction, RAG, and platform memory systems will make you a dramatically better AI user.
Read article - AIApril 20, 20269 min read
Metaprompts: Share Context Between AI Tools
A metaprompt is a prompt one AI session writes for another. How to carry project context between ChatGPT, Claude, and other AI tools without starting over.
Read article - AIFebruary 19, 202615 min read
Integrating LLMs into Your Next.js App
How to add LLM APIs to a Next.js app: Vercel AI SDK vs LangChain vs direct calls, SSE streaming, cost management, and when you need a Python backend.
Read article
Need help implementing these solutions?
We build, advise, and lead engineering for companies at every stage, from a clean website to a complex AI platform.