Workflows
How AI tools are combined to automate tasks and processes across real-world systems.
Workflows describe how AI tools are combined to automate tasks and processes across real-world systems. Rather than focusing on individual tools, this section explains how different components work together to solve practical problems.
Content in this hub is educational rather than tool-centric. The emphasis is on patterns, logic, and decision points that apply across platforms, with optional references to specific tools where relevant.
This page links to workflow guides and real use cases, providing structure and context for readers who want to understand how AI workflows are designed, implemented, and maintained in practice.
Claude code review: Agentic bookkeeping
Claude Code is a command-line tool developed by Anthropic that allows users to build and run agentic workflows through natural language instructions. Unlike visual automation platforms, it requires no drag-and-drop interface and handles debugging autonomously. This post covers what Claude Code does, why it is relevant for non-programmers, and how it performs on a practical…
What are agentic workflows?
The term agentic workflows is being used frequently, but often without clear explanation. To understand what they are, it helps to break AI systems into four progressive layers. This article explains: TL;DR Agentic workflows: Build, run, and repair workflows autonomously. AI: Generates responses but requires manual input. AI automation: Connects tools automatically but breaks when…
Hosting agentic workflows with Modal
Running agentic workflows locally works well for experimentation, but it introduces a reliability problem. If a computer shuts down or the internet connection drops, workflows stop running. For mission-critical or team-based use, those workflows need to live in the cloud. This article explains how Anti-Gravity agentic workflows can be deployed to the cloud using Modal,…
First agentic workflow with Google Anti-Gravity
Most automation platforms require users to understand every node, connector, and execution detail before anything works. Google’s Anti-Gravity takes a different approach. Instead of assembling workflows visually, users describe what they want in natural language and let the system build, debug, and improve the workflow over time. This article breaks down a complete agentic workflow…
Perplexity and NotebookLM: AI Research
Research is no longer about collecting information. It is about selecting sources, validating claims, and turning insights into usable outputs. Many workflows still rely on a single AI chatbot for all of this, which often leads to shallow analysis and fragmented results. A more effective approach is to split research and synthesis into two dedicated…
n8n: Extract text from any file with AI
n8n is an automation platform that connects apps, APIs, and services through visual workflows. It supports conditional logic, file handling, and integrations with AI models, making it a practical choice for teams that need to process documents at scale. If your business receives invoices, contracts, scanned receipts, or audio recordings on a regular basis, manually…