Build an analysis agent that actually works
A worked build of an invoice-analysis agent: where analysis agents break, and how to make one you can trust to flag work for a human, not finish it.
Read now
AI Leadership Journal
The Journal separates consequential developments from the weekly noise. It combines strategic interpretation, technical understanding, and lessons from implementation, so leaders can see what changed, why it matters, and what deserves action.
No recycled announcements. No breathless predictions. Useful analysis, written from the work.
How to think about MCPs: what they are, why first attempts fail, and when to use one
The Model Context Protocol is the standard socket connecting AI models to your tools and data. What it does, what it doesn't, and when to use one.
Read now
Two AI content machines, and the one rule that keeps them off slop
The Morning Brew founder demoed his AI content machine on a podcast. I run one too. Where they overlap, where they differ, and the one rule that keeps both off slop.
Read now
The job stays. The tasks move.
A Netflix leader's read on AI and the future of product and tech roles, and what a mid-sized company should actually do about it.
Read now
What to build when the models keep changing
Each new AI model deletes another layer of the scaffolding built around it. A durable-versus-disposable test for where mid-sized companies should invest.
Read now
An AI sandbox won't keep your documents secret. Buy one anyway
An AI sandbox bounds what an agent's code can install, delete, and reach. What it protects, what it never will, and how to buy one without overbuilding.
Read now
Putting an AI agent in front of patients: the four disciplines that decide whether it's safe
A playbook for an AI agent in production in healthcare or any regulated business: bounded routing, deterministic gates, failure-driven testing, per-capability releases.
Read now
Why good agents look nothing like good demos
Good AI agents fail in week six, not on stage. Context engineering, memory, and skills decide whether an agent survives real work.
Read now
The four questions every leader is really asking about AI
AI fluency for leaders is four leadership decisions, not a coding skill: delegation, description, discernment, diligence — the frame the whole column builds on.
Read now
What to delegate to an AI agent (and what to keep in your own hands)
Delegation is the first AI-fluency skill: what to hand to an AI agent, how much autonomy to grant, and what a leader always keeps — plus one honest experiment.
Read now
Running Claude Code on Amazon Bedrock for regulated data
Run Claude Code through Amazon Bedrock so regulated data stays on an approved path: a reproducible, verified setup for security-conscious European teams.
Read now
AI Personalisation: Transforming Customer Engagement
How AI-driven personalisation is revolutionising customer engagement — the five-pillars framework, real-world case studies, and practical strategies.
Read now
Modern RAG Systems: HTML, Multimodal, Agentic
Explore modern RAG system types including HtmlRAG, multimodal RAG, and agentic RAG, and learn how they advance beyond traditional retrieval methods.
Read now
AI in Marketing: New Tools for the Digital Age
Discover how AI is reshaping marketing through personalization, predictive analytics, content automation, and smarter customer engagement across the funnel.
Read now
AI Guide for German Mittelstand
A practical guide for German Mittelstand firms on AI adoption, data foundations, workforce readiness, and investment roadmaps to stay competitive.
Read now
Advanced Prompt Engineering for Business
Learn advanced prompt engineering techniques for business including chain-of-thought prompting, role-playing, meta-prompting, and precision data analysis.
Read now
RAG Evaluation: Metrics and Tools
How to evaluate Retrieval Augmented Generation systems: practical metrics, tools, and methods for improving answer quality and retrieval performance.
Read now
Rethinking Search: My Journey with Perplexity
How Perplexity Pro changes professional research workflows — faster answers, better synthesis, and a productive alternative to traditional search.
Read now
Prompt Engineering: A Practical Guide
Learn practical prompt engineering techniques that improve AI output for content creation, analysis, automation, and everyday business workflows.
Read now