Tech Talk by Gavin Wiggins
September 2, 2026
None of the above.
“An LLM agent runs tools in a loop to achieve a goal” ~ Simon Willison 2025
Check out Simon Willison's Weblog at simonwillison.net
Provide LLM agnostic features to build agents that call tools/functions, maintain state, and coordinate multi-step workflows.
Feels like JavaScript UI frameworks, a new one pops up every month.
⚠️ Be aware of vendor lock-in especially for agent deployment.
def calculate_area(width: float, height: float) -> float:
"""Calculate the area of a rectangle.
Args:
width: The width of the rectangle.
height: The height of the rectangle.
Returns:
The area of the rectangle.
"""
return width * height
here
A standard way to give AI agents new capabilities and expertise.
More information about agent skills at https://agentskills.io
Like a README.md file but for agents.
Provides instructions to help AI coding agents work on your project.
# Example of AGENTS.md
## Setup commands
- Install deps: `pnpm install`
- Start dev server: `pnpm dev`
- Run tests: `pnpm test`
## Code style
- TypeScript strict mode
- Single quotes, no semicolons
- Use functional patterns where possible
More information about the AGENTS.md file at https://agents.md