Reason
Agentic Teams
Orchestrate specialist AI agents into collaborative teams. Choose your topology, set budgets, schedule autonomous workflows. The learning router gets smarter with every task. Powered by QuoxEngine.
In plain words
What it is, where it lives, when to reach for it
- What is it
- A dashboard feature of QuoxCORE that runs several specialist agents as one team under an orchestrator.
- Where do I use it
- In the dashboard, on the Agentic Teams page in the AI Studio section.
- When would I use it
- When one agent is not enough and a task needs several specialists working together under your rules.
- How do I use it
- Open Agentic Teams, click Create Agentic Team, then choose an orchestrator and at least one member agent.
QuoxCORE is the free, self-hosted platform underneath this. What is QuoxCORE
Human-in-the-loop
Real autonomy.
A hand on the wheel.
Agent teams plan, split the work and execute on their own, until a step crosses a threshold you set. Then the team holds, the decision routes to a person, and who approved what is written into the evidence chain.
Gate · policyHuman-in-the-loop gates
Declare which actions pause for a person: spend above a limit, touching production, contacting a customer. Everything else flows at machine speed. The gate is enforced in the execution layer, not suggested in a prompt.
▸ enforced in-engine · not advisoryDecide · HITL inboxApproval inbox
Pending decisions arrive with full context: what the agent wants to do, why, and the evidence behind the request. Approve, deny, or ask the agent to explain itself. No grepping logs to find out what is stuck.
▸ full context · one tapContain · scoped powersLeast-privilege powers
Agents never hold your credentials. They are granted scoped, short-lived powers (this API, this budget, this window) revocable at any moment. What a team cannot reach, it cannot break.
▸ short-lived · revocableLive demonstration
Watch a team run an objective.
Six agents from the Quox core registry, running the daily security audit as a team. An autonomous schedule fires, the orchestrator decomposes the objective, specialists hand the work along the line, and the run holds at the gate the moment it wants to touch production.
Nothing above is a mock-up of a slide. It is the shape of a real run: CommanderQ, PRISM, WARDEN, SCHOLAR, DAEDALUS and VULCAN are shipped Quox agents, the gate is the AOCL policy layer doing its job, and the approval lands in the same evidence chain an auditor reads.
When the human approves, watch the hands behind this page: the whole team lights up, the same governance a whole organisation gets from the Quox enterprise platform.
How it works
From objective to auditable output.
One flow, minutes from team definition to live execution: you set the objective, the orchestrator splits the work, specialists execute, and everything lands on the record.
Choose an orchestrator and specialist agents. Set policies, budgets and autonomy rules.
Describe what you want done: a high-level goal, not a script.
The objective is broken into concrete tasks and each one is assigned to the right specialist.
Monitor progress in real time. Approve plans, review checkpoints, or let autonomous schedules handle it.
Auditable output, monitored from the dashboard. Every objective leaves a trail you can hand to an auditor.
Topologies
Pick the shape of the team.
Four coordination topologies, one engine. Choose the structure that fits the work, not the other way round.
Capabilities
Everything you need for multi-agent teams.
Define, deploy and monitor autonomous agent teams from a single dashboard.
Team manifests
Define teams as YAML or JSON manifests: orchestrators, specialists, policies and budget limits. Collaboration you can version-control.
Objective decomposition
Submit a high-level objective. The orchestrator decomposes it into concrete tasks and assigns each one to the right specialist.
Autonomous scheduling
Cron-based scheduling with budget guardrails. Teams execute objectives on autopilot within configurable daily token limits.
Family-tree hierarchy
A visual tree of orchestrator-to-member relationships. See who does what at a glance.
Live objective tracking
Real-time SSE streaming shows objective progress, task status and agent activity as it happens.
Budget guardrails
Set daily token limits, tool call caps and a maximum for unattended objectives. Teams disable automatically after consecutive failures.
Team plugin packs
Bundle a team as a pack and distribute it. Install a complete team setup from the marketplace in one click.
Shared context
Team instances share key-value context across tasks. Every agent works from the same working memory.
Topology selection
Choose how your team coordinates: star for flat dispatch, hierarchical for pod leads, pipeline for sequential stages, mesh for collaborative research.
Learning router
Tracks agent performance and routes tasks to the best-performing specialist. It gets sharper with every objective run.
Fallback routing
When an agent fails and retries are exhausted, the engine finds a domain-compatible replacement. No task left behind.
Circuit breaker
Three consecutive failures pause the objective and escalate to a human. No burning tokens on a broken plan.
Define · share
A team is a file.
The whole demonstration above starts as a manifest: who leads, who specialises, what pauses for a human, what it may spend, and when it runs. Review it in a pull request, roll it back like code, or bundle it as a pack and install the same team from the marketplace in one click.
The gate policy is right there in the file. It is not a suggestion in a prompt, it is configuration the execution layer enforces.
name: secops-audit topology: star # star · hierarchical · pipeline · mesh orchestrator: commanderq members: [prism, sentinel, scholar, nova, forge] policies: hitl: # these pause for a person - touches_production - spend_above_limit budgets: daily_tokens: 250000 tool_calls: 400 schedule: cron: "0 6 * * *" # the daily audit on_failure: fallback: domain_compatible circuit_breaker: 3 # consecutive failures → pause + escalate
Use cases
Teams built for real work.
Pre-configured team templates for common operational workflows.
01 · SecOpsSecurity audits
A SecOps team runs daily vulnerability scans across your fleet. This is the team from the demonstration above.
02 · DevOpsInfrastructure health
A DevOps team monitors, diagnoses and fixes infrastructure issues.
03 · DevelopmentCode review pipelines
A development team reviews PRs, runs tests and reports findings.
04 · AuditCompliance monitoring
An audit team tracks policy compliance and generates reports.
Where it stands
What's proven, what's not yet.
- Team manifests validate on load and the four topologies (star, hierarchical, pipeline, mesh) are real: TopologyBadge renders whatever manifest.topology.type declares
- Autonomous cron scheduling is live, with overlap prevention, timezone support and a configurable circuit breaker (default: 3 consecutive failures pauses the objective)
- Fallback routing to a domain-compatible agent when one fails, orphan-run recovery on service restart, and a family-tree view of the agent hierarchy are all shipped code, not concept art
- Budgets enforce daily token and tool-call caps, but per-request token-in accounting is incomplete (STATUS_AND_LIMITS_AUTOMATION.md)
- HITL routing, the inbox and SLA escalation are Beta throughout; the server-side VOLT-witness path for approvals has not been live-verified against the deployed containers yet
- The learning router (epsilon-greedy exploit/explore scoring) is real, but a fresh team’s Performance tab reads "No performance data yet" until objectives actually run: nothing has learned from live traffic yet
- The task-time skill loop (Crystal drafting from a run) is WARDEN-only; other team members do not draft Crystals from their own objectives yet
- No sub-agent creation flow: a team is assembled from the existing registry, not generated on demand
Autonomy you can hand to an auditor.
approvals on the recordbudgets enforced in-engineaudit trail on every objective
Many hands, one gate
Ready to build your first team?
Define objectives, assign specialists, set budgets, and let your agents collaborate with a human on the important calls.
Go deeper