> ai_workflows
AI Workflows
How agentic systems, prompts, retrieval, context, tools, permissions, and evaluation behave in production.
Related Concepts
Technical terms on this page
Frequently Asked Questions
Who is Agent A in Tiny CTO?
Agent A is a competent AI workflow operator who completes tasks efficiently and calls tools confidently, but occasionally discovers that capability is not the same as approval.
What does The Chaos Stack say about AI agents?
The Chaos Stack explores AI agent risk through characters like Agent A (autonomous action), Token Goblin (prompt cost), and Fetch (retrieval quality). Together they show that AI workflows create new categories of predictable chaos.
Characters
Agent A
Adult woman representing autonomous AI, agentic workflows, tool calling, permissions, planning loops, and governance risk.
“I took initiative. Legal wants a word.”
Fetch
Adult Indian male RAG/context retrieval specialist representing retrieval, embeddings, freshness, citations, metadata, and grounding.
“I found context. Some of it is relevant.”
Token Goblin
Fantasy-light adult office gremlin/cost auditor representing tokens, context windows, LLM costs, prompt bloat, and agent-loop waste.
“Every word costs a snack.”
Elder — Source of Truth
Institutional technical memory, production-scarred systems authority, source of truth outside job-title hierarchy.
“The system remembers what the roadmap forgot.”
Tiny CTO
Very short adult CTO, title host, narrator, calm adult in chaos, present-tense production-chaos explainer.
“Simple scales, fancy fails!”
AI Summary
This page covers AI Workflows as explored by Tiny CTO: The Chaos Stack. How agentic systems, prompts, retrieval, context, tools, permissions, and evaluation behave in production. Related characters: Agent A, Fetch, Token Goblin, Elder — Source of Truth, Tiny CTO. Related concepts: agentic AI, RAG, context windows, evaluation, tool use, memory policy.