Use AI to find answers and automate tasks. Superthread agents work across tasks, pages, projects, forms, and meetings—then return real work your team can review.
Ask from a task, board, page, project, sprint, or space so the agent starts with the right context.
Use a ready workflow such as project health, client updates, intake triage, or backlog cleanup.
Run it from schedules, comments, forms, new work, or changes to cards.
Choose where the agent can work and who can run, edit, manage, or inspect it.
Open Ask AI while viewing a task, board, page, sprint, project, or space. Superthread attaches that object to the chat, so the agent already knows what you mean.
The same context comes with a custom agent when it starts from a schedule, comment, form submission, or change to the work. It knows what happened and where to act.
Pick a practical agent job, see the prompt and trigger behind it, and compare the estimated time saved with doing the same work manually.
Turn an approved brief into milestones, tasks, owners, dates, and open questions.
“Turn this approved brief into a first project plan. Create milestones and tasks, suggest owners and dates, and list assumptions for the project manager to review.”
Time saved2–4 hours/week
Create role-specific reading, setup, introductions, and knowledge checks.
“Build an onboarding plan from this new starter's role and our approved company pages. Create owned tasks for setup, reading, introductions, and first-week outcomes.”
Time saved2–4 hours/week
Check context, set useful properties, and route work to the right queue or owner.
“Review this request, identify missing details, set the right priority and tags, and move or assign it to the correct queue or owner.”
Time saved2–4 hours/week
Give the agent a goal, then wake it up from the events that matter. It gets the event and the surrounding Superthread context, not just a webhook payload.
Run Sprint Health Monitor automatically on the weekdays and time you choose.
Friday · 09:00
Checked Project Atlas
3 blockers surfaced
Give the agent a workspace role and limit it to the spaces where it should work. Then decide who can run it, improve it, manage it, or inspect other people’s chats.
Run the agent without changing how it is configured.
Improve its instructions and settings as the job evolves.
Manage the agent, its access, and the spaces where it can work.
Control separately who can inspect everyone’s runs, not only their own.
Agent Kit is the capability layer behind the Superthread agent, custom agents, our public CLI, and MCP. It gives AI more than 100 structured ways to work with the system where your team’s knowledge and execution already live.
Search across tasks, pages, projects, boards, forms, comments, sprints, and meetings. Agent Kit resolves ordinary names, so people do not need to know IDs or commands.
Create and update tasks, pages, projects, boards, forms, comments, checklists, sprints, and agents. More than 100 structured actions are available through one capability layer.
Results come back as native task rows, page tiles, boards, sprints, comments, checklists, and search results that people can open and keep working with.
“Atlas is slipping by two weeks. Move the unfinished work, preserve the gaps between tasks, and show me what changed.”
Use it inside Superthread or connect tools such as Claude and Codex through the CLI and MCP server.
The best first agent has a clear job, useful context, and an obvious moment to run.
Write clear instructions in ordinary language. Tell the agent what a good result looks like and how you want it to behave.
Give it access to the spaces where the relevant projects, tasks, pages, and meeting notes live.
Use it on demand or connect it to schedules, comments, forms, new work, and property changes.
Inspect what it changed, leave feedback where the work lives, and refine the instructions as the job evolves.
The system agent can create and configure other agents. That makes a deliberate feedback loop possible without removing the human who decides what “good” looks like.
It creates a task, page, report, plan, or another result inside Superthread.
The reviewer comments on the actual output. The feedback stays attached to the work.
The Superthread agent can pick up that feedback and update the original agent’s instructions for the next run.
Superthread is a drop-in replacement for your existing project management tool
