Getting started with AI
From what a model actually is to agents, tools and the protocol that connects them, ending on how to tell an AI problem from a process one.
6 episodes · 45 min · from bradshaw.cloud: Audio Edition
In this playlist
-
AI Fundamentals
A business leader's guide to the building blocks of AI — no code, no jargon, just the mental models that matter.
-
Frontier Models
The most capable AI models available — and when a frontier model earns its cost vs when a small specialised model wins.
-
Model Context Protocol
How to assess MCP as an integration contract: where it reduces repeated connector work, and where identity, trust, and operating responsibility remain.
-
Agentic AI Patterns
From single agents to orchestrated teams — the architecture patterns behind AI that acts, and how to choose between them without over-engineering.
-
AI Delegation Loop
Stop building a specialist agent for every job. Capture process, toolbox and proof in a playbook a general agent can run — and put every correction back into the folder.
-
Most AI Requests Aren't AI Problems
Many AI requests are process-ownership and decision-rights problems that arrive as tool requests. A five-question test to run before funding one, and where to route a request that fails it.
Subscribe to the podcast
Every episode, in your podcast app. Each is a piece from this site read by a synthetic voice cloned from my own, with my consent. How the audio is licensed.
More playlists
- Cloud economics How cloud and AI spend is measured, where the cost curves cross, and how to decide what to run, buy or bring back in-house.
- Governing AI agents What an agent is allowed to do, who answers for it, and the controls that make autonomy something an organisation can run.
- Every episode The full catalogue, newest first, with subscribe links for every app.