Workflows Articles
Browse 1221 articles about Workflows.
Claude Co-work Now Runs in the Cloud: What Changed and How to Use It
Claude Co-work moved from desktop-only to cloud-based scheduled tasks. Learn what changed, which connectors still need a local machine, and how to migrate.
How to Use AI Agents for Content Marketing: From Research to Published Post
Build an AI agent workflow that handles research, ideation, writing, and publishing for content marketing using Claude Code and automation tools.
How to Build an AI Second Brain with Obsidian and Claude Code: The LLM Wiki Method
Learn how to build an AI-maintained knowledge base using Obsidian and Claude Code, inspired by Andrej Karpathy's LLM Wiki architecture.
AI Video Generation for E-Commerce: How to Turn Product Images Into Marketing Videos
Use AI video tools and agent workflows to automatically generate product videos, UGC-style ads, and B-roll from your existing product catalog images.
How to Use ChatGPT Sites to Build and Host Web Apps Without a Backend
ChatGPT Sites lets you generate, host, and share fully functional web apps from a single prompt. Here's how it works and when to use it.
How to Use Claude Code with Clay for AI-Powered Lead Generation
Use Claude Code as an orchestrator and Clay as your data source to find, enrich, and write personalized cold outreach at scale automatically.
Local AI vs Cloud AI for Agents: The Hybrid Routing Strategy That Saves Money
Learn when to run AI models locally and when to route to cloud APIs. A practical hybrid strategy for reducing costs without sacrificing quality.
How to Use Multi-Agent Workflows for Parallel Content Production at Scale
Fan out multiple AI agents to process product catalogs, generate content, and validate outputs in parallel using orchestration tools like Archon.
How to Build an AI-Powered Personal Productivity Dashboard with ChatGPT Work Mode
Use ChatGPT Work Mode to build a daily control tower that monitors email, Slack, calendar, and brand mentions—all from one AI-powered dashboard.
How to Use Claude Code with Clay for Automated Lead Generation and Cold Outreach
Use Claude Code as an orchestrator and Clay as your data source to find leads, enrich contacts, and write personalized cold emails automatically.
How to Use the /goal Command in Claude Code for Fully Autonomous Agent Loops
The /goal command lets Claude Code run until a condition is met. Learn how to set goals, success criteria, and verification steps for autonomous workflows.
Plan with Fable 5, Build with Sonnet: The Model Routing Pattern That Cuts AI Costs
Use Claude Fable 5 for planning and architecture, then switch to Sonnet for implementation. This routing pattern cuts token costs without sacrificing quality.
How to Reduce Claude Fable 5 Token Costs: 8 Settings to Change Right Now
Fable 5 now bills at API rates. Learn which settings to disable—MCP servers, auto-memory, Claude.md bloat—to cut token costs without losing quality.
How to Build a Semantic Memory System for AI Agents Without Hermes Agent
Hermes Agent proved memory matters, but you can build better recall inside Claude Code. Learn storage, injection, and semantic search using local vector DBs.
How to Use ChatGPT Sites to Build and Host Web Apps Without a Backend
ChatGPT Sites lets you prompt a web app into existence and host it instantly at a clean URL. Learn how to build, publish, and share apps without infrastructure.
ChatGPT Work Mode vs Claude Co-work: Which AI Super App Should You Use?
ChatGPT Work and Claude Co-work both connect to your tools and run background tasks. Here's how they compare on integrations, memory, and autonomy.
How to Use Fable 5 as Architect and GPT-5.6 Sol as Worker in Multi-Agent Systems
Fable 5 excels at planning complex systems while GPT-5.6 Sol executes at lower cost. Learn how to combine both models in a single agentic workflow.
How to Use Grok 4.5 as a Cheaper Sub-Agent in Multi-Model AI Workflows
Grok 4.5 matches GPT-5.5 on coding benchmarks at $2 per million input tokens. Learn how to route tasks to it from a smarter orchestrator model.
How to Use Progressive Disclosure in AI Agent Design to Scale Capabilities
Progressive disclosure lets agents load only the instructions they need per query. Learn how Pydantic AI 2.0 implements this pattern to prevent context bloat.
How to Decide When to Use a Single Agent vs a Multi-Agent Team
Four questions determine whether your task needs one agent or many: size, independence, separation of concerns, and checkability. Here's how to apply them.