Duke, the AI teammate, works inside every app.Journal
Notes from building AI that ships.
What we learn building Duke and custom AI products for clients: agents, evals, guardrails, observability, and getting found when AI writes the answers.
Programmatic SEO in 2026: not dead, just done differently.
AI Overviews ate 38% of clicks. Google's 2026 spam policy hit templated AI pages by name. But organic search is only down 2.5% — programmatic SEO isn't dead. The lazy version is. Here's what actually works now, the unsold version.
RAG vs agents vs fine-tuning: when each one wins.
Three techniques. Three different problems. Most teams reach for the wrong one because they're picking based on hype, not problem shape. Here's the honest decision framework.
How much does it cost to build an AI agent in 2026?
Pricing for AI work is opaque. Here's the honest breakdown — what a prototype costs, what production costs, what operations costs, and what makes the numbers move.
LangSmith vs Langfuse vs Arize vs Braintrust: comparing AI observability platforms.
Four platforms, four philosophies. We've shipped on all of them. Here's the honest comparison — what each does well, what each doesn't, and how to pick.
How to write your first AI eval suite without a framework.
You don't need LangSmith, Braintrust, or any platform to ship your first eval suite. Most production-grade evals start as 100 prompts in a JSON file and a script. Here's the playbook.
AI safety in production: a checklist that actually ships.
Safety isn't a content filter you add at the end. It's an architecture. These six layers are non-negotiable before any AI product touches real users.
Schema.org markup for AI engines: what actually works in 2026.
Most schema markup is wasted effort. The four types that actually move citation rates on ChatGPT, Perplexity, and Google AI Overviews — and what to skip.
Evals that actually catch regressions before users do.
The eval suite most teams ship with is a confidence-builder, not a regression detector. Here's the structure we use to catch real failures earlier.
Five agent-loop patterns we keep reaching for.
Planner-executor, ReAct, supervisor-worker, hierarchical, pure tool-calling. When each one fits, when it doesn't, and when to mix them.
Guardrails that survive contact with real users.
Why bolt-on safety layers fail and what production-grade guardrail architecture actually looks like in 2026.
GEO and AEO: the new search stack for AI-native brands.
Citation-rate has replaced rank-position. Here's how we instrument content for ChatGPT, Perplexity, and Google AI Overviews — and what we measure.
See it running for a business like yours.
Open a live demo in one click, or tell us about your business and we'll show you how SmartDuke would run it.
Talk to us
