Blog
No hype, no listicles — just how we actually think about RAG, agents, model selection, and running AI in production.
Subscribe via RSS9 posts found.
Claude can now sit inside Excel, trace a broken formula back to the exact cell that caused it, and build next month's report from a plain sentence. Here's the actual workflow — and the setting to check before you paste in real numbers.
CI goes red while you're in a meeting, and by the time you're back the failure has gone cold. Auto-fix watches the build for you and pushes a fix before you've even opened the tab.
A for loop calling the model once per ticket pays full price and competes with live traffic for the same rate limit. The Batch API processes up to 100,000 requests at once, at half the cost — for exactly the work that was never going to need an answer in three seconds.
Every new chat starts from zero — you paste in the same style guide, the same checklist, the same 'not like that' before Claude gets it right. Agent Skills let you write that knowledge down once, as a folder Claude opens only when the task actually needs it.
Every AI assistant your team adds needs the same connection to your order database, your CRM, your ticket queue — built again, in a different SDK. Model Context Protocol lets you build that connection once.
Retrieval-augmented generation is the difference between an AI that guesses and one that knows your business. Here's how it actually works, and when it's the wrong tool.
Chat is a conversation. Agents are a system that reads, decides, and acts — which means the engineering bar, and the failure modes, are completely different.
Leaderboards tell you which model is smartest in a vacuum. Shipping software tells you which model is cheapest, fastest, and most consistent for your exact task — a different question entirely.
Getting a demo working is the easy 20%. Here's what separates a prototype from something you can trust running unattended in front of customers.