See onemind in 24 seconds
A short film about working with AI members: give them tasks, invite people and AI to your team, and keep using your own AI tools.
Blog
Ideas for humans and AI
Thoughts on shared memory, connected teams, and the way we work with AI.
Fix an AI mistake once, for every tool
Turn a repeated AI mistake into a shared rule, then check that your other tools follow it.
Hand off AI tasks without losing the details
Keep the request, decisions, and shared changes together when another teammate or AI tool takes over.
Keep each Project’s AI rules separate
Give each product its own AI rules while keeping the team’s shared rules together.
How agencies keep each client's AI rules separate
Share your agency's working rules while keeping each client's voice and files in their own work folder.
Keep AI product copy consistent across markets
Give AI tools the same product writing rules, then check each market’s pages against your catalogue.
Keep AI fee wording accurate in financial services
Keep each product’s fee rules separate, share approved wording with your AI tools, and check every draft against the fee table.
Hand off AI game dialogue without losing the story
Keep the story rules, naming decisions and file changes together when you move a dialogue task from Codex to Cursor.
Keep your AI marketing drafts on brand
Keep one approved set of brand rules for Claude Code, Codex and Cursor, and check each new draft before you use it.
Share AI coding standards across your team's tools
Give your AI tools the same coding rules, then check the code, tests and changelog yourself.
Stop repeating the same rules to every AI tool
Keep your team’s AI rules in one place, approve changes, and check each tool’s next result.
AI memory and agent collaboration tools: onemind, Raft, Mem0 and alternatives
Compare shared team instructions, agent workspaces, memory infrastructure and native AI-tool rules before choosing a workflow.
A Standard to Guide AI: Lessons from Apple’s iPhone Duo
What Apple’s design guide can teach us about giving AI clear rules.
How to share AI instructions across Claude Code, Codex, and Cursor
Choose a shared source, keep tool-specific scope explicit, and verify that a correction helps the next task.
Don't Just Buy AI Assistants. Build an AI Team.
You gave AI to the people in your team. You didn’t necessarily make AI part of the team.
What Is a Mind in the AI Era?
We start with a model, then give it a shell. We add system prompts, tools, skills, memory, files, workflows, harnesses, and ways to learn from previous work.
Future customer stories
Illustrative stories follow people from a concrete work problem through the decisions, tool changes, safeguards, and consequences of using the complete future onemind product.
Composite future scenario · Not a current customer claim or MVP description
Maya And The Reminder That Could Not Be Wrong
A wrong-time clinic reminder forces a solo founder to turn one painful migration lesson into safeguards shared by every AI tool.
Jon And The Client Name In The Wrong Report
Twelve minutes before delivery, Jon finds another client's name in a report—and rebuilds his AI workflow around evidence and isolation.
Northstar And The Feature The Team Had Already Killed
A clean pull request revives a feature the team already rejected, revealing that code can be current while product judgment is stale.
Harbor Labs And The Engineer Who Changed Clients On Monday
An urgent healthcare audit moves Elena off a retail client on Monday morning, without letting either client's context follow her incorrectly.
Ledgerly And The Feature That Was Beta In Only Half The Company
A beta billing feature becomes generally available inside a sales assistant before it becomes generally available to customers.
Meridian Payments And The Rule That Changed At Midnight
One regulatory interpretation must become fourteen coordinated operational changes at midnight—without one approval pretending to authorize them all.
Orion Industrial And Twelve Versions Of The Same Safety Rule
One supplier-security change has to cross twelve countries, eleven languages, acquired businesses, different AI vendors, and offline factories.
Fieldnote And The Eighty-First Worker
Amara is the invisible eighty-first worker, spending each morning coordinating agents that repeat failures and hide stale context inside successful runs.