In July 2025, Gartner told AI leaders that “context engineering is in, and prompt engineering is out.” The past year, people on the bleeding edge of AI have been paying attention to framing.

context engineering

 

💡 Context engineering prepares everything prior to the prompt.

Even the best prompts will fail without the right context. Giving AI backstory and reference material will create a landscape that is suitable to your scenario. But you can’t just give an AI agent infinite data; you have to understand memory as a stateful context, so you don’t overwhelm your agent by asking it to do too many things, with too much information. Managing context intentionally is the key to successful agentic design.

As AI systems evolve from single-turn prompts into persistent, multi-step, goal-driven agents, the differentiator between the results of different AI operators is not the model capability, or the prompt quality – it is context.

If prompt engineering taught us how to ask better questions, context engineering teaches us how to design the mind that answers them.

🤖 The upcoming AI Agent Accelerator begins with Ai301: Context Engineering.

Last Thursday, 1 October, I started teaching all 8 of my 300-level workshops in a series of live, in-person workshops at the new EPIC Exchange. 100 Manchester St, Christchurch. 10am-11:30am for 8 consecutive Thursdays. $350 NZD to join.

Register here: https://events.humanitix.com/ai-agent-accelerator-1026

🔍 Programme Schedule:

1 October: Ai301 – Context Engineering

Focus Attention Intelligently

The quality of AI output depends on the quality of the information environment you design around it. Learn how to structure context — session history, long-term memory, and supporting data — so your agents perform at their best.

8 October: Ai302 – Agent Management

Operate Your AI Team

Managing AI agents is a new skill. Learn how to monitor, maintain, and improve autonomous agents in production — including memory management, task decomposition, and knowing when to intervene.

15 October: Ai303 – Vibe Coding Applications

Build Software with AI

Use AI to build working software applications without traditional coding expertise. Learn the vibe coding approach — describing what you want in natural language and iterating with AI until it works.

22 October: Ai304 – Agent Harnesses

Deploy Your Personal AI Agent

A comparison of open-source AI agent platforms, OpenClaw and Hermes, versus hosted solutions. Learn how to set up, configure, and operate a personal AI agent that runs 24/7 across your messaging platforms, automating tasks and managing workflows on your behalf.

29 October: Ai305 – S.C.O.P.E. Agent Tasks

Define Agentic Projects

Identify which tasks in your organisation are suitable for autonomous AI agents. Learn how to scope agent projects, define success criteria, and set boundaries that keep agents productive and safe.

5 November: Ai306 – Automate Your Workflows

Connect Tools to Systems

Move beyond one-off prompts to connected, automated workflows. Learn how to chain AI tools together, trigger actions across platforms, and build systems that run without manual intervention.

12 November: Ai307 – Generate System Prompts

Engineer Agent Instructions

Write the instructions that govern how AI agents behave. Learn how to craft system prompts that are clear, consistent, and robust — the foundation of every reliable agent deployment.

19 November: Ai308 – Evaluate Agent Performance

Measure What Matters

How do you know if your AI agent is doing a good job? Learn frameworks for testing, measuring, and improving agent output so you can trust the systems you build.

 

Newsletter subscribers get 25% off the AI Agent Accelerator.

Use discount code NEWSLETTER at checkout. Or just click here.​

For those outside of Christchurch who have been asking, yes, I will host a webinar series in the near future – probably around the holiday season. Stay tuned!

 

🛠️ Expert Interviews

How do coaching experts use AI? Watch this series of 10-15 minute interviews on my YouTube channel.

expert interviews

Watch Now

 

👓 What I’m Reading

  • ​The State of Context Engineering by Redis -“Standards are cheap to adopt when they are still forming and expensive to retrofit once your systems have grown in other ways.”
  • ​How To Fine-Tune a Small LLM on Your Own Data by Sai Rahul – “Do not compare your fine-tuned model against training loss. Compare it against the model you were using before.”
  • ​The Two-Hour School Day by Peter Diamandis – “Nobody is teaching creativity or self-agency. And the promise at the end of the conveyor belt, that a diploma buys you a stable job, is breaking in real time as AI absorbs the entry-level work that a diploma used to unlock.”

Upcoming Events

Webinar for members of the AI Coaching Academy​

Onboarding AI Agents: How to Delegate Workflows Friday, October 16 at 1:00 PM GMT+13

Onboarding AI Agents: How to Delegate Workflows

If the Internet gave everyone access to infinite information, AI has given us access to infinite skills. Managing these skills effectively will help you move beyond using AI as a research assistant, and into training an AI agent like a new hire on their first day of work.

RSVP