# #ai

> 14 public memos tagged #ai on MythOS.

## Links

- [Tag Page](https://mythos.one/tag/ai)
- [MCP Server](https://mythos.one/api/mcp)

## Memos

- [Andrej Karpathy](https://mythos.one/me/brianswichkow/3e5540): Andrej Karpathy is an AI researcher, educator, and builder. Co-founder of OpenAI, former Director of AI at Tesla (led Autopilot), and creator of widely influential educational resources including the...
- [AI Observability and Debugging](https://mythos.one/me/brianswichkow/a024b5): AI Observability and Debugging Part of: Effective AI Utilization — Table of Contents AI calls are black boxes. The input goes in, the output comes out, and when something goes wrong, you need...
- [Streaming vs Blocking AI Calls](https://mythos.one/me/brianswichkow/7ec247): Streaming vs Blocking AI Calls Part of: Effective AI Utilization — Table of Contents BrianBot uses generateText() for every AI call — fully blocking, wait-for-complete-response. This is the right...
- [Multi-Provider Strategy](https://mythos.one/me/brianswichkow/c05999): Multi-Provider Strategy Part of: Effective AI Utilization — Table of Contents Depending on a single AI provider is a single point of failure. BrianBot is wired for three providers (Anthropic, OpenAI,...
- [Context Window Management](https://mythos.one/me/brianswichkow/0bfafb): Context Window Management Part of: Effective AI Utilization — Table of Contents Every AI model has a finite context window. How you fill that window determines the quality of the output. Stuff it...
- [Queue and Rate Limiting for AI Workloads](https://mythos.one/me/brianswichkow/6efa49): Queue and Rate Limiting for AI Workloads Part of: Effective AI Utilization — Table of Contents AI APIs are external services with their own capacity limits. Your system's job queue is the buffer...
- [Cost Tracking and Budget Controls](https://mythos.one/me/brianswichkow/cd3b53): Cost Tracking and Budget Controls Part of: Effective AI Utilization — Table of Contents You can't optimize what you don't measure. BrianBot has the measurement infrastructure (token counts per step,...
- [AI Pipeline Design](https://mythos.one/me/brianswichkow/d0d41e): AI Pipeline Design Part of: Effective AI Utilization — Table of Contents A single AI call is simple. Five AI calls that depend on each other's output, share context, and need to complete reliably is...
- [Prompt Architecture](https://mythos.one/me/brianswichkow/ea10ab): Prompt Architecture Part of: Effective AI Utilization — Table of Contents Prompts are code. They should be versioned, overridable, testable, and separated from the logic that calls them. BrianBot's...
- [Temperature and Parameter Tuning](https://mythos.one/me/brianswichkow/6075c0): Temperature and Parameter Tuning Part of: Effective AI Utilization — Table of Contents Temperature is the most misunderstood AI parameter. It doesn't control "creativity" — it controls the...
- [Model Fallback and Resilience](https://mythos.one/me/brianswichkow/701cf0): Model Fallback and Resilience Part of: Effective AI Utilization — Table of Contents The most important AI call is the one that fails. How your system responds to that failure defines its...
- [Token Optimization Playbook](https://mythos.one/me/brianswichkow/580621): Token Optimization Playbook Part of: Effective AI Utilization — Table of Contents Tokens are the fundamental unit of both AI capability and AI cost. Every token you send is money spent and context...
- [Model Routing Strategies](https://mythos.one/me/brianswichkow/baea20): Model Routing Strategies Part of: Effective AI Utilization — Table of Contents Model routing is the decision logic that determines which AI model handles a given request. Get it right and you...
- [Effective AI Utilization — Table of Contents](https://mythos.one/me/brianswichkow/ca8dae): Effective AI Utilization — Table of Contents A comprehensive guide to building production AI systems, drawn from patterns observed in BrianBot and generalized into reusable principles. Each memo...