Memos by Brian Swichkow
- Carrie Gan
Carrie Ganster I was introduced to Carrie by Tzen Lai in November 2025. motorcyclist orange-sticky
- Acast
Acast is a global podcast hosting and monetization platform that provides distribution, analytics, and advertising tools for creators. Founded in 2014 in Sweden, it has grown into one of the largest...
- AI Agent Mastery Iceberg
The AI Agent Mastery Iceberg is a tiered map of 30 concepts in agentic AI work, arranged from surface-level basics to advanced practice. Its five tiers, Noob, Beginner, Pro, Expert, and Vibe God,...
- Claude Code Scheduled Triggers
Claude Code Scheduled Triggers (the /schedule skill) is the native mechanism in Claude Code for running autonomous agent sessions on a cron schedule. Triggers execute remotely on Anthropic's...
- Artificial Intelligence (AI) Glossary
This memo is a glossary of terms for all things related to Artificial Intelligence (AI). Glossary A Agents Managing Agents – Supervisory agents that spawn, monitor, and steer other agents. AI Agent –...
- Orchestrator-Worker
Orchestrator-Worker is a multi-agent design pattern in which one lead agent plans a task, delegates subtasks to worker agents, and combines their results into a final output. The orchestrator holds...
- Multi-Model Orchestration
Multi-Model Orchestration is the practice of coordinating several different AI models within one workflow, assigning each task to the model whose capability, speed, or cost fits it best. Models...
- Agents Managing Agents
Agents Managing Agents is a multi-agent arrangement in which supervisory agents spawn, assign, monitor, and correct other agents, so a person directs a hierarchy rather than each individual worker....
- Self-Healing Tests
Self-Healing Tests are automated tests that an AI agent repairs when they break, by diagnosing whether the failure reflects a real defect or a stale test and then updating the test or the code...
- Tool Poisoning
Tool Poisoning is an attack on AI agents in which a malicious tool hides instructions in its description or schema, text the model reads as trusted context but the user typically never sees. Agents...
- Self-Improving Loops
Self-Improving Loops are agent systems that review their own results and revise their own prompts, skills, tools, or memory so that later runs perform better without manual rewriting. A...
- Memory Consolidation
Memory Consolidation is the process by which an AI agent distills raw session history into a small set of durable, deduplicated memories that it can load in future sessions. Agents accumulate far...
- Eval-Driven Loops
Eval-Driven Loops are an agent workflow in which output is repeatedly checked against an automated evaluation, such as tests, scores, or a grading model, and revised until it passes. The loop has...
- Parallel Agents
Parallel Agents is the practice of running several AI agents at the same time on independent pieces of work, shortening total time and keeping each agent's context focused. A single agent works...
- Background Agents
Background Agents are AI agents that run a task asynchronously, without holding the user's terminal or chat, and report back when they finish or need input. In an interactive session, the user waits...
- Harness Engineering
Harness Engineering is the practice of designing the software that wraps a language model into an agent: its tools, instructions, context loading, permissions, and control loop. A model on its own...
- Prompt Caching
Prompt Caching is an LLM API feature that stores a stable prefix of a request, such as system instructions and tool definitions, so later calls reuse it instead of reprocessing it, cutting both cost...
- Project
A Project in an AI assistant is a persistent workspace that groups related conversations with shared files and standing instructions, so every chat inside it starts with the same context. Consumer AI...
- Token
A Token is the basic unit of text a Large Language Model (LLM) reads and writes, typically a word fragment of a few characters, and the unit by which model context, speed, and cost are measured....
- Claude Code Glossary
The Claude Code Glossary is a collection of terms used in Claude Code, Anthropic's CLI for Claude, spanning built-in commands, configuration concepts, and the Brian-extended ecosystem layered on top....