AI Foundations Day in Dublin
Thursday, February 26 from 9:00-17:00 at Hyatt Centric
Overview
In this session, we learned the fundamentals of AI and what’s in it for us, key AI risks, prompt crafting essentials, how to build AI assistants – as well as pointers to get the most out of the AI Lab programme.
Quick Links
🌟 Key points
💻 Session slides
💭 Workout
📚 Further resources
🧪 Your AI Lab Project brief
Key points
This programme is as much about doing as it is learning. To get the most out of it, do the work and join the conversation — in sessions, in your work life and in the WhatsApp community.
We’re in a historic moment. AI will change the world, and we’re only at the tip of the iceberg in terms of capability.
AI may not take your job, but it will fundamentally change it.
And if we look backwards, we’ve been on a massive evolution in this role, and it’s been driven by technological advances all along the way.
LLMs are machine learning models trained on a huge amount of data that understand and can generate text in a human-like way. An LLM is the engine behind a chatbot — so GPT-5 is the LLM behind ChatGPT.
LLMs use complex math to predict the next word to write. Think of them like a calculator for words.
Key limitations are that they’re not great at getting our writing style just right, they lack nuanced context (like we have as humans), they may hallucinate, their context window (aka short term memory) has limits, and their training data will always be out of date
Prompts are the instructions you give a chatbot, and there’s an art to doing them well to optimize outputs.
Carve’s prompt crafting framework is COIF: include Context, Output, Intent, Format in every prompt for best results.
10 “buckets” of tasks you can use a chatbot for in your workflow: writing and editing, research, meetings, minutes & events, project planning, travel, expenses, brainstorming as a thought partner, learning and business intelligence, translation and cultural nuances, data cleaning & analysis.
AI risks overview
Job displacement
First major automation impact on white-collar jobs
World Economic Forum predicts more jobs lost than gained to AI
Data privacy concerns
Most AI tools train on user data by default
Companies typically store conversations for 30 days to monitor for unsafe use, even if not training on your prompts/uploads
ChatGPT experienced a minor data breach back in 2023, highlighting security risks
Other key kisks
Inaccuracy and hallucination in AI outputs
Bias in models, particularly visible in image generation
Environmental impact due to high compute requirements
Copyright and IP uncertainties around AI-generated content
Risk of mediocrity through over-reliance on AI
AI assistants are customized LLMs, aka Copilot Agents, Custom GPTs, Gemini Gems
The MUTT Framework for building AI assistants:
Mission: Clearly define objectives, context, and tone. Think your COIF prompt and more!
Uploads: Examples, documentation, policies, or website content for training.
Test: Stress test with prompts; identify areas to improve.
Tinker: Refine instructions and iterate until quality meets requirements. Anytime your AI assistant annoys you, that’s a great time to jump in and edit your instructions to make sure the mistake doesn’t happen again!
Session slides
Workout
AKA your post-session actions to take
1️⃣ Think up 3 new ways to use AI, then craft 3+ COIF prompts for these tasks. Run the prompts. A/B test with a basic prompt. Share one in WhatsApp, and comment on a peer’s share.
2️⃣ Review the AI Lab Project briefing in full and decide which option you’re going for. Intermediate folks: decide what your AI assistant will do, ready to share in our session on 12th.
Further resources
📌 Your AI Lab Project Brief in full
Our Suno-created AI Lab songs! “AI Lab, You’re The Best” v1 | v2 | v3 | v4
Cortney Hickey on AI/automation on Youtube plus a slide deck of Zapier’s automation resources for EAs
COIF Prompt Writer GPT
This free, open source AI assistant will write fabulous COIF prompts for you with minimal instructions
AI Assistant instructions: Meeting Briefings | Restaurant Scout
Markdown guide
To help you build your AI assistants in Markdown for optimum results
Something big is happening
Matt Shumer’s recent viral piece on how AI is developing and what it might mean for us and our livelihoods
The age of AI has begun
Bill Gates on the power and promise of AI, a great read
WEF Future of Jobs Report 2025
A fascinating World Economic Forum report on how AI will reshape jobs globally
The 3 challenges of AI regulation
Excellent piece written by Tom Wheeler via The Brookings Institute