Weekly newsletter highlighting the latest AI news, with short video tutorials and copy/paste prompts you can use to improve your skills as an AI operator. As artificial intelligence moves from optional to operational, technical specialists no longer have the advantage. It is those who can supervise and coach AI to improve that will thrive in an AI-augmented future.
Share
The SAGE Framework turns a repeated task into an AI Agent
Published about 2 hours ago • 4 min read
🏎️ “AI agents don’t have a speed limit, but the person managing them still does.” - Kieran Klaasen
Hello Reader,
The fastest way to build a disappointing AI agent is to begin with a vague, grand ambition.
“Handle my marketing for me.”
“Run all our customer service.”
“Become my chief of staff.”
Those are only aspirations, not workflows. An agent cannot reliably operate within a fog bank. A useful agent starts with clear goals:
Turn this meeting transcript into decisions, owners, deadlines, and unresolved questions
Review incoming enquiries, classify them, draft a response, and escalate the risky ones to my personal email
Gather material from these approved sources, create a first draft of a presentation, and flag any unsupported claims
Compare a published asset with an evaluation checklist, identify gaps, and ask for missing information
When I develop AI agents in New Zealand for clients, I use the same 4-step process I teach in the AI Agent Accelerator. It's called the SAGE Framework, and it stands for: Scope, Automate, Generate, Evaluate.
1. Scope Agentic Tasks
Choose one workflow worth improving.
Projects fail when they aim too wide. By defining a narrow scope, you’ll learn how to identify agent-ready workflows, break them into steps, define success criteria, and decide where human review belongs.
A strong scope is narrow enough to test and valuable enough to matter.
2. Automate Your Workflows
Break the workflow into handovers.
Each tool connected to your systems creates another point of failure. Mapping each input, action, tool, handoff, and deliverable will create an automation map that allows you to debug individual steps.
Automation is a series of design decisions.
3. Generate System Prompts
Engineer agent instructions.
You want to give the agent enough context to produce good results without your active involvement. That means your instructions, skills, examples, and SOPs have to be fit for purpose.
Durable system prompts define success.
4. Evaluate Agent Performance
Test the output before you trust the workflow.
An agent becomes useful when you can tell the difference between a good result and a plausible-looking mistake. Building a simple evaluation can process to test outputs, spot failure points, reduce risk, and improve agent reliability over time.
Measure what matters.
This is the process I am teaching starting this Thursday, 10-11:30am, at EPIC Innovation for the next 8 weeks.
Last Call for the AI Agent Accelerator
If you'd like to join me in this live, in-person 8-workshops series in downtown Christchurch, click here. (Newsletter subscribers get 25% off.)
If you'd like to have a conversation about hosting these workshops in-house with your team, click here.
🎬 [REPLAY] Human-First AI: Find the Work that Matters Most
OpenAI's Dev Day announced the release of Dots (it's like Grok Bot) ChatGPT Space (it's like Google Drive) and GPT-6.1 Sol (it'a like Astra but cheaper token cost)
Anthropic launched Claude Marketplace to organise connectors, plugins, and partner apps
Viral AI Agent Instinct raised $1B at $10B valuation
The World is Changing: AI For Creativity by Jeffrey Katzenberg - “Technology didn't diminish the craft, it expanded the canvas. It gave artists more room to create.”
My AI Doom Scenario by Hunter Ash - "Speed of change is the only defense against parasitism, control, decay. Change so fast that they can’t keep up. AI will either end the evil dream of centralized control once and for all, or, if the controllers manage to capture AI, cement it for all time. Hence, acceleration."
📢 Feedback Time!
If I were to attend an 8-webinar series for the AI Agent Accelerator, I would prefer:
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. If you hire a capable new employee, you don't simply at a project and say,...
Turn Curiosity to Growth Build smarter learning habits with AI support. Learn how to personalise learning paths, reflect more effectively, and continuously upskill in a fast-changing environment. Create personalised learning systems using AI. Turn information into insight through reflection and synthesis. Maintain continuous development without...
Weekly accountability meeting. Come prepared to share your: WINS - what were your wins with AI this week? CHALLENGES - where did AI go wrong? COMMITMENTS - what will you be working on this week?
You've subscribed to a newsletter, downloaded a lead magnet, or attended an event with Caelan Huntress.
You can unsubscribe, but you will miss out on funny memes in the future.
You can modify your preferences, to reduce frequency.
PO Box 8081, Riccarton, Christchurch 8440 ·
AI Coaching Newsletter
by Caelan Huntress
Weekly newsletter highlighting the latest AI news, with short video tutorials and copy/paste prompts you can use to improve your skills as an AI operator. As artificial intelligence moves from optional to operational, technical specialists no longer have the advantage. It is those who can supervise and coach AI to improve that will thrive in an AI-augmented future.
📊 “Context engineering is the strategic process of selecting, packaging, and managing the most relevant information for each step.” - Antonio Gullí Hello Reader, 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 prepares everything prior to the prompt. Even the best prompts will fail without the right context. Giving AI backstory...
🗂️ "An AI Agent runs tools in a loop to achieve a goal." - Simon Willison Hello Reader, Generative AI makes things for you. Agentic AI does things for you. This distinction, between making and doing, is the next step on the exponential curve of capability. An AI Agent can initiate and execute tasks independently, finding the best way to transition from an initial state to a goal state by using any tools it has available, as often as it is capable of doing. In his excellent primer on AI...
🌱 “It’s clear that we are well into the adoption phase of AI, but not everyone is adapting.” - Lou Compagnone Hello Reader, I was in Wellington this week for the #AotearoaAISummit, the annual festival hosted by the AI Forum New Zealand. I livetweeted the event on LinkedIn (live-posted? doesn't have the same flavour) on the hashtag linked above, and I made AI anime illustrations of all the speakers. You can see my takeaways (and my art) below: (Please note - other than the illustrations, no AI...
