How I would define an AI agent at the start of 2025: In abstract, a piece of software that can achieve a certain goal, and uses AI to navigate the fuzzy path of achieving that goal. More specifically, a combination of - Goal - Context management - Underlying model - Tools (datastores and functions with effects) - Prompting & self-prompting strategies (including delegating to other agents) Example: A geocoding agent Goal: Parse content from a sentence and geocode it Context Management: Trimmed sliding window. We only need the very most recent messages to get the job done. Underlying model: A simple model like 4o mini is more than enough Tools: A function to search cities with inbuilt query match ranking, and a function with access to a Google Maps geocoding API Prompting: Single turn. The agent should be able to get the job done in a single exchange, or ask the user to clarify the location if needed
- 0 replies
- 0 recasts
- 9 reactions
Howdy! Pleasure to be here. Looking forward to maximising synergies and promoting win win win solutions for ebitda maximisation
- 0 replies
- 0 recasts
- 0 reactions
A friend shared this pretty cringe auto-email. Bless modern recruitment "Picking a single candidate felt a bit like choosing between pizza and tacos - both incredibly delicious, but we could only go with one at a time"
- 0 replies
- 0 recasts
- 0 reactions