---
id: "prereq-agentic-workflows"
type: "prereq"
source_timestamps: ["00:14:06"]
tags: ["ai-architecture", "software-engineering"]
related: ["concept-agent-callable-primitive", "framework-agent-primitive-loop", "claim-images-as-intermediate-data"]
reason: "Necessary to comprehend the shift of images from human-consumed artifacts to machine-consumed subroutines."
sources: ["s07-chatgpt-images"]
sourceVaultSlug: "s07-chatgpt-images"
originDay: 7
---
# Agentic AI Workflows

## Why this is a prerequisite

The speaker's analysis of images as [[concept-agent-callable-primitive]] — and the loop in [[framework-agent-primitive-loop]] — only makes sense if one understands what an *AI agent* is.

## What you should know going in

- An **AI agent** is autonomous software that can: write text, call APIs/tools, read outputs (including images via vision), and decide its next action without human turn-taking.
- Agents commonly chain: **plan → call tool → read result → revise plan → call next tool**.
- Modern coding agents (e.g. Devin-class, Cursor-class) routinely consume images via vision-language models and emit code in response.
- A 'tool call' is a function invocation that can include external services such as web search, code execution, or — relevant here — image generation.

With this background, [[claim-images-as-intermediate-data]] and [[contrarian-images-for-agents]] become intuitive: an image is just an intermediate data type in an agent's pipeline.