AI workflows
How to build AI content workflows you can rerun: images, video and voice on one canvas.
How to give Claude or ChatGPT a canvas with MCP (step by step)Add a canvas to Claude or ChatGPT in about two minutes with an MCP connector, pick the right one for the job, and build your own MCP App if nothing fits. Includes setup, troubleshooting, and code.
Why give your AI agent a canvas? What changes when Claude or ChatGPT can see the workChat is a poor place to hold a plan with ten steps. Here's what a canvas gives Claude, ChatGPT, or your own agent, which tools offer one in 2026, and when plain chat is still enough.
You can now run Orisu from ChatGPTOrisu's MCP connector now works in ChatGPT. Add one URL, sign in, and build and run your content workflows without leaving the chat.- AI workflows7 AI content workflows every marketing team should stealSeven repeatable AI content workflows, from URL-to-ad-variants to one-click weekly drops, with the pipeline shape, who each is for, and how to build it.
- AI workflowsMeta, Google, and TikTok will generate your ads now. Should you let them?Meta's Muse Image, TikTok Symphony, and Google's asset generation all make ad creative for you. Where platform AI helps, where it flattens your brand, and how to split the work.
- AI workflowsAI slop: what it is, and how marketing teams avoid it'Slop' was Merriam-Webster's 2025 word of the year: low-quality AI content made in quantity. Here's why marketing teams produce it, what it costs, and the workflow that prevents it.
- AI workflowsMultimodal AI pipelines: image, video, text, and audio in one placeReal campaigns need scripts, voiceovers, video, captions, and thumbnails. What changes when all four content types share one pipeline, and when separate tools still win.
- AI workflowsStructured prompting for AI video: the format behind consistent clipsVague prompts hand you a different video every run. Structured prompting (named components, formulas and JSON) is how marketing teams make AI video output consistent and repeatable enough to ship.
- AI workflowsWhat is MCP? The Model Context Protocol, explained for marketing teamsMCP, the Model Context Protocol, is the open standard that lets AI assistants plug into your real tools and data. Here's what it means for marketing teams, and when to use it.
- AI workflowsAI content agents: what they actually do for marketing teamsAI content agents don't just generate one asset; they run multi-step content work on their own. Here's what they really do, where they help, and how to keep them on-brand.
- AI workflowsFrom prompt to pipeline: making AI content repeatableTeams climb the same ladder: one-off prompts, saved prompts, prompt chains, visible pipelines. What breaks at each rung, and the three properties that make AI content actually repeatable.
- AI workflowsImage-to-video AI: the workflow that keeps your videos on-brandText-to-video reinvents your brand on every clip. Image-to-video anchors each generation to a reference image, so your characters and products stay consistent. Here is how it works and when to use it.
- AI workflowsGenerative engine optimization: how to get your content cited by AI searchAI search engines answer questions instead of listing links. Here's what actually gets your content cited by ChatGPT, AI Overviews, and Perplexity, plus what Google says to skip.
- AI workflowsHow to build an AI content workflowChat threads don't scale into production. Here is the full method for building an AI content workflow: define the recurring output, map the steps, add human review, and save it as a graph your team can rerun.
- AI workflowsWhat is a visual AI canvas? Nodes, edges, and runs explainedNodes, edges, and runs: the three primitives behind every visual AI canvas, how it compares to chat and automation tools, and when a canvas is overkill.