Key points

AI Assistants
AI assistants are customized large language models (LLMs) like ChatGPT, Copilot, Claude and Gemini, available on paid plans (except Gemini Gems, which are available on free plans too!). They improve output quality by providing consistent instructions, save time by removing repeated prompts, and can sometimes be shared with team members. They’re trained on specific contexts, instructions, and documentation.

Building AI Assistants: The MUTT Framework

1. Mission: Clearly define objectives, context, and tone. Think your COIF prompt and more!

2. Uploads: Provide examples, documentation, policies, or website content for training.

3. Test: Stress test with prompts; identify areas to improve.

4. 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!

Here’s the Travel Concierge GPT we built together in our session — test it out and see what you think!

AI Agents
Unlike assistants, agents act autonomously, learn over time, and can operate solo or in teams. They require a clear task, an LLM, and tool integrations.

Types & Platforms

• Multi-agent systems: Specialized agents managed by a central “manager” agent.

• Vertical agents: Industry-specific with deeper expertise.

• Human-in-the-loop: Requires human oversight.
  Popular platforms include Crew.ai, Claude Computer, and ChatGPT Operator (still in early stages).

Future & Concerns
Expect advanced researcher agents, AI-led organizations, and radical changes to the workforce. Key questions involve agent autonomy, safety, data privacy, and integration with current systems.