AI content workflow: keep evidence with every draft
Keep sources, claims and approvals together in your AI content workflow with a worked example, copyable review prompt and publication checklist.
Blog
Notes from building Tokenrip, the shared workspace your AI agents work from.
Claude skills in ChatGPT, Codex, Cursor and Copilot: one SKILL.md for every tool
How Claude skills work, how they differ from agents, MCP and commands, where Claude, ChatGPT, Codex, Cursor and Copilot each load them, and how to keep one copy working everywhere.
How to manage multiple AI agents without them doing the same work twice
How to use Claude, ChatGPT, Codex and Grok together on one project without duplicate work or double-contacted leads: one job per agent, claims, send locks, one dedupe key and one shared record.
Claude Duet connectors and memory: what carries over from Claude, and what we're waiting to test
Claude Duet uses the connectors, memory and skills already in your Claude account. What Anthropic documents about Duet's connectors, memory, usage limits and the waitlist, how it compares with dots and Muse, and what we plan to test when our invitation arrives.
Grok Bot memory: what a Bot remembers, why we run one Bot per job, and how ours talk to everything else
Grok Bot memory explained: what each Bot keeps across sessions, why memory leaks between projects on one Bot, what sharing a Bot or using Team Bots does to memory, how to reset it, custom MCP servers, and how we run Grok Bots as our daily agents.
Grok memory: why Grok forgets with memory on, and how we use Grok without it
Grok memory explained: what grok.com remembers across chats, why it can seem forgetful, how to turn it off, how it differs from ChatGPT memory and from Grok Bot and Grok Build memory, custom MCP connectors, and why we use Grok every day without relying on its memory.
Muse custom connector: how to add an MCP server to Meta Muse, and where its memory lives
Meta Muse has no settings form for MCP servers: you ask Muse to build a custom connector on its own cloud computer. How that works, what Meta reviews and does not, where Muse keeps keys and memory, whether two Muses can collaborate, and our plans for a Tokenrip connector.
ChatGPT dots memory: what your dot remembers, what you can't see, and what we found on the first call
ChatGPT dots memory explained: your dot starts from your ChatGPT memory and keeps its own notes you cannot view or edit, reset is the only wipe, what it shares with ChatGPT and Codex, whether it can use a custom MCP plugin, and what we found using one.
Claude Duet vs dots vs Muse vs Grok Bot (October 2026): the comparison, and which one we actually use
Claude Duet, OpenAI dots, Meta Muse and Grok Bot compared on plans, price, regions, memory control, custom MCP servers and team use, from the makers' pages, plus which ones we run at Tokenrip and why Grok Bot won.
How to add MCP to ChatGPT (2026): Plugins, Developer mode, and which plans get write tools
How to add an MCP server to ChatGPT: the Plugins flow, Developer mode, the desktop app, which plans qualify, OAuth, local servers through Secure MCP Tunnel, and the fixes for the usual problems.