One workspace. Every team.
The same agents, approvals and audit trail, set up for the work your team does. Pick your team and see how JuhJuh works for you.
Vendors, renewals, and reports. Chased.
Your agents read across the drives, wikis and trackers you already keep, run the recurring work on a schedule, and chase what's due before it's late. Draw a process once as a Charm and it runs itself after that, with an approval wherever you want one.
Charms anyone can draw
Describe a process in plain words and JuhJuh drafts the first canvas. There are 28 kinds of step, including Approval, Decision, Wait, Send email and Create ticket. An Approval step holds the run at Waiting for you.
28 kinds of stepSchedules that keep going
Run work on a schedule in your timezone, on a webhook, on an event or on a mention. Every trigger logs its runs and success rate, and you can pause it without deleting it.
Every run loggedPortals with no API
Agents browse in a real browser on their own computer. They fill in the form and stop before submitting until a person approves. You can watch live, take over and hand it back.
Submitting and paying need approvalViews over any system
Point Views at a system and get a live table, map, board, timeline, calendar, gallery, dashboard or feed. Ask the agent about the page, then let it act after a one-tap approval. Views never changes your systems on its own.
8 layoutsDigests and SOPs
Weekly summaries land in the channel that owns them. Renewals and deadlines come up before they're due. The agent proposes SOPs from how your team actually works.
Posted where the team readsCeilings and versions
Steps, time and tokens are capped per run. Every edit is a version, and a run that has already started keeps its version. Each run shows what every step received, produced and cost.
Capped per runFinding which accounts have gone quiet means an export, a spreadsheet and most of a day.
They point Views at it, map every customer by region, and ask their agent which accounts have gone quiet. The answer and a follow-up plan come back before lunch.
Someone retypes each order from a spreadsheet and hopes nothing was missed.
The agent fills in the order and stops before submitting. The buyer watches it live, approves, and the order goes through.
Draw the process once. It runs itself after that.
Schedules, approvals and ceilings on every run.
On our service, or inside your own boundary.
Most teams start on JuhJuh's hosted service. There is nothing to install, your teams are working within days, and we run, update and support it. A team that needs more control, or must keep sensitive data inside, self-hosts JuhJuh instead.
Hosted by JuhJuh
Sign in and connect your tools. We keep the service running, updated and supported, so your people spend their time on their own work.
Your organization gets a workspace of its own, and each organization sees only its own data. When an AI agent works, the prompts and files it needs go only to the AI model companies you allow, only to do the work, inside the regions you declare.
Self-hosted, inside your boundary
In your own cloud account (AWS, Google Cloud, Microsoft Azure or DigitalOcean) or on your own premises, connected or air-gapped, with open-weight models from the Mistral, DeepSeek, GLM and Kimi families running inside. Our engineers install it and tune it to your compliance obligations.
Your sensitive information, trade secrets and know-how never leave your boundary unless you connect an outside service or chat app, approve a website for your AI agents or approve sending them out. While your AI agents run only on your own models, no AI company receives them or trains a model on them.
Start hosted and move when you're ready: our engineers move your workspace across. Some companies run both, the hosted service for most teams and a self-hosted installation for the systems that must stay inside, and each installation is kept separate.
Go deeper into the platform.
All features
Chat, agents, Plan & Work, Views, Charms, the knowledge base and voice, in one workspace.
OpenSecurity
Approvals before anything consequential, four permission levels, and an audit trail of every agent action.
OpenAI agents
Colleagues that remember every person they work with and work within a budget they can't overspend.
OpenDraw the process once. It runs itself after that.
Schedules, approvals and ceilings on every run.
