The mental model
Understand Stellary in 3 ideas
A simple loop for turning intent into work your team and AI agents can actually move forward.
01
Project
A project brings together your goals, roadmap, cards, documents, team, and AI agents.
02
Card
A card is a clear mission. It can be prepared, discussed, assigned, and tracked.
03
AI agent
An AI agent is a configurable assistant that can work on a card with a role, rules, and an autonomy level.
Complete workspace
Everything you need to move from idea to execution
Projects, docs, cards, agents, Activity, workflows, and cockpit stay connected. You see what is moving, what is blocked, and what needs a decision.
In the app
From project to mission
The path is visible: clarify the project, turn it into cards, run the mission, and keep the cockpit focused on what needs attention.
Stellary/Workspace/Workforce
All5
Agents3
Members2
Search team...
Agents
3Product AI
SystemFrames, breaks down, assigns
3100%$0.00
Ready for project assignment
Front AI
Produces the first version
00%$0.00
Ready for project assignment
Review AI
Rereads, corrects, scores
00%$0.00
Waiting for mission
Try it!
Members
2M
Marie
product lead
marie@stellary.io
Owner
N
Nina
final approval
nina@stellary.io
Member
Invite member
Execution
AI agents that work inside your projects
Agents do not just suggest. They help frame projects, prepare cards, execute missions, ask for missing detail, and leave a clear activity trail.
Clarify the work
AI helps identify what is missing, asks useful questions, and breaks down the next steps.
Less vague backlog work.
A clearer roadmap appears faster.
Bring in what already exists
Add notes, files, or a brief so the project has useful context from the start.
Docs stay close to the work.
The team and agents read the same source.
Make the board actionable
The roadmap becomes visible cards that people and agents can assign, discuss, and track.
Cards carry execution.
Everyone sees what can move next.
Prepare the mission
Refine first turns a vague card into a clear mission with context, constraints, and success criteria.
Launch the work
Assign a card to a human or AI agent, then Run mission when the card is ready.
Follow Activity
Every action, question, result, and approval stays visible from the card.
Linked docs
Documents stay near the missions and feed the context agents use while working.
Why it worksWhy Stellary keeps
Why Stellary keeps
work clear
The system keeps the mission, context, execution state, and human control in one place.
1
Cards frame the real work
The execution state lives in cards, not in loose prompts.
2
Context stays with the work
Docs, exchanges, and decisions stay connected to the mission.
3
Agents know where to act
Each agent works with a role, tools, and an autonomy level you define.
4
Humans stay in control
The agent can ask for a detail or approval when the mission needs it.
5
The cockpit shows what matters
You see what is blocked, what is moving, and what still needs a decision.
Governance
Agents execute under your rules
Stellary does not push AI to act without control. You choose what an agent can do alone, what needs approval, and what must stay as a proposal.
Governance
Autonomous for routine work
Use autonomy for low-risk missions where the rules are already clear.
- You define the safe perimeter.
- Routine work moves without noise.
- The history remains visible.
Approval for sensitive changes
The agent prepares the work. A human gives the green light before it applies.
- Important changes wait for review.
- Pending approvals stay visible.
- The decision is tied to the card.
Proposal only for fragile topics
For money, data, compliance, or risky work, the agent suggests and you decide.
- No silent execution on sensitive work.
- Drafts and recommendations stay traceable.
- You keep the final word.
This is not just another AI layer
AI works in the project context, not in a separate chat you have to keep in sync.
This is not a board with a single AI assistant.
Every card can become an AI mission with context, Activity, assignment, execution, and approval.
This is not docs separated from execution.
The useful context feeds cards, missions, approvals, and decisions directly.
This is not an uncontrolled AI autopilot.
You choose the autonomy mode before agents act on real work.
It is a workspace for shared execution.
Humans and agents work from the same project, board, documents, and cockpit.
Advanced workflows
For advanced workflows: pipelines
When a mission needs several steps - produce, review, fix, request approval, notify - a pipeline can orchestrate the sequence. Powerful, but not required to launch your first AI mission.
Stellary/Pipeline live
Test rundry run1 cardfinal approval
Pipeline
Checkout release pipeline
Ship checkout without escalating the whole routine to a human.
Execution log
Run started
State
Step 1 / 7
Route
Production
Approval
None
What the pipeline just did
Ship checkout without escalating the whole routine to a human.
Checkout release pipeline
Produce, review, correct if needed, request a human green light, then notify automatically.
Pipeline
Ship checkout without escalating the whole routine to a human.
Pipeline editor
The pipeline picks the next step on its own.
Start
01
Produce
Product AI builds the first version.
02
Review
Review AI scores the output and surfaces risks.
03
Score >= 8?
The pipeline decides whether the work can pass.
04
Payment green light
Only one decision reaches the product lead.
05
Loop back
The pipeline launches another pass if the score is too low.
06
Correct
Fix AI applies changes and sends the work back to review.
07
Notify
Slack and release docs update without manual work.
End
Comparisons & guides
Explore the category before you explore the product
Use our comparison pages, methodology, and technical docs to evaluate tools, workflows, MCP, and AI-native delivery systems with a clearer frame.
Best project management tools for product and engineering teams
A broad 2026 comparison covering workflow fit, AI readiness, docs, governance, and delivery depth.
Open resource
Notion vs ClickUp vs Linear vs monday
A side-by-side look at strengths, trade-offs, and which team context changes the recommendation.
Open resource
How we compare tools
Read the methodology behind our comparison pages, update cadence, and evaluation criteria.
Open resource
What MCP changes for AI coding tools
Understand how MCP shifts integrations, runtime access, and agent workflows for modern teams.
Open resource
MCP server documentation
Go deeper on tokens, tools, mission flows, approvals, and client setup for MCP.
Open resource
REST API reference
Explore the real backend routes behind workspaces, projects, documents, pilotage, agents, and billing.
Open resource
Comparisons & guides
Explore the category before you explore the product
FAQ
The real questions about Stellary
Everything you need to know before getting started.
Stellary is an intelligent workspace for organizing a project, turning it into a roadmap, creating cards, and moving those cards forward with a human team or AI agents.
In a classic board, a card mainly tracks work. In Stellary, a card can also become an AI mission with context, Activity, assignment, execution, and approval.
They can help frame a project, enrich a card, execute a mission, ask a question when blocked, propose an action, or act directly if you allowed them to.
No. You choose each agent’s autonomy level: supervised, approval-based, or autonomous for work you consider safe.
No. Workspace knowledge, project documents, and card-linked documents are part of the working context. They serve both humans and agents.
Yes. Advanced teams can connect tools, use the API or MCP, and orchestrate repeatable workflows. You do not need those pieces to launch your first AI mission.
Start with one project
Turn one idea
into your first AI mission
Create a project, generate a roadmap, and move the first card forward.
AI moves the work forward. You stay in control.
Beta
Open access
Cards
Mission-ready
Activity
Visible work
Project
Stellary use caseA project keeps objectives, roadmap, cards, documents, decisions, and next actions in the same workspace.
Roadmap, cards, docs
Mission
Stellary use caseA card can be prepared, assigned, run as an AI mission, discussed, reviewed, and validated from one place.
Cards, Activity, approvals
Steering
Stellary use caseThe cockpit keeps blockers, decisions, approvals, and important activity visible without rebuilding status by hand.
Cockpit, workflow, control
Project
Stellary use caseA project keeps objectives, roadmap, cards, documents, decisions, and next actions in the same workspace.
Roadmap, cards, docs
Mission
Stellary use caseA card can be prepared, assigned, run as an AI mission, discussed, reviewed, and validated from one place.
Cards, Activity, approvals
Steering
Stellary use caseThe cockpit keeps blockers, decisions, approvals, and important activity visible without rebuilding status by hand.
Cockpit, workflow, control
Free during early access · No credit card · Cancel anytime