No Workspace Selected
Create or select a workspace to manage access and runtime credentials.
Goals
The objectives the workforce pursues. Org goals are the workspace's mission (every member inherits them); member goals are assigned to one member. A goal can auto-close when its measurement target is met, or be closed by hand.
Authorize goal intake
Allow an application to start goals for a member within a token budget you set. Choose the member and the application, review the terms, then set it up — it is active at once. Existing member, funding-goal and workspace limits still apply, and this permission does not expand what anyone's memory reaches.
Limits are tokens, not money. Revoking stops new goals; it does not cancel work already running.
Active permissions
Confirm these terms
Workforce
What members do. Each member — a person a client acts for, or a worker — holds a role, pursues a mandate (its goals), and can be made proactive with triggers that spawn tasks on a schedule. Select a member to see its mandate and triggers, or hire a worker. Who a member is and what it can read are on the Members tab.
Track record — cost & outcomes per role
What each role has cost and how it's performed across recent runs — the prior a cost-informed hire reads.
Team templates — start from a curated team
A template seeds specialist roles (activated, ready to hire against) plus the starter org goals they exist to pursue — the one-click cold start. Re-applying is safe: goals already present are skipped.
Activity
Recent runs in this workspace — what members (and human tasks) are doing, who is acting, toward which goal, and at what token cost. Select a run for its detail. The Conversations view is the register of goal-planning chat sessions.
Inbox
What is waiting on a person. Waiting on you: answer an agent's clarification to resume its run; runs that ran out of budget are listed so nothing stalls silently; and the learning loop's config promotions queue here for your approval before any config goes live. Waiting on members: memory changes and identity questions that only the asked members settle.
Waiting on you
Waiting on members
Memory state only the asked members settle: promotions, a requester's change confirmation and any required approvals, and identity questions. The engine keeps them; the client decides whether, when and how to ask. Shown here, answered by no one here.
Resources
Where the tokens go, against what was allocated — burn by member, goal, and role, with the per-member and per-goal budgets the engine enforces at every spawn. Set or edit an allocation inline; remaining headroom drives the near-cap and exhausted alerts.
Recurring token budgets
Set an organization budget for the workspace and optional team or user budgets. All applicable limits must have room. These rolling allowances cover executor model calls and their delegated work; embeddings are outside this allowance.
Remove this spender’s recurring limit? Other applicable budgets still apply.
Workspace execution funding
A workspace-wide token limit for native model execution. Committed tokens include retained call allowances; they are distinct from provider-reported usage. Run, Goal and member budgets still apply separately.
Daily burn
Allocations — most pressured first
Members — burn vs. allocation
Goals — burn vs. allocation
Roles — burn
Learning
The workforce improving itself, under your control. Underperforming roles and workflows are flagged from real outcomes; an LLM proposes a revised candidate as a DRAFT; the scoring harness replays history against the incumbent and gates promotion. When the autonomous steward wins the gate, the promotion waits here (and in the Inbox) for your approval — nothing goes live without you. Every run and every approval is recorded.
Members
The people and workers this workspace acts for. A client reaches a member through its linked accounts (its login and each connector account bound to the member), and the member's role bounds the memory that runs as it can read and write.
Channels
The conversations a client declared as channels. Each keeps its own memory for its current members. Workspace owners, admins and authorized operators can also read it; its content never moves to another partition and reaches the whole workspace only as a promoted copy. Which conversations become channels, and who belongs to them, is the client's to declare.
Console access
Who can sign in to this console and operate the workspace. A console login is not a workforce member and acts for no member. Console members read shared memory; workspace owners, admins and authorized operators can also read private scopes. Workforce members are on the Members tab.
New API key secret
Ontology Profiles
Memory by scope
The entities, relations and facts memory holds in one scope — workspace-wide, one channel, or one member's own — with who can read it, as the engine states it. Every row names its scope and its readers.
Entities
Relations
Facts
Entity Dossier
Everything known about one entity: every name it carries and where each came from, what was merged or relinked into it (by which process, when and why), where it merged to, its typed relations, its fact history, and the source text behind each provenance quote.
Advanced: Debug Views & Projections
Debug Views
No view selected
Use this tab to inspect and debug persisted memory projections and query behavior.
Parameters
Consumers
Advanced Governance
Governance Audit Rollups
View Query Runner
Saved Query Presets
End-to-End Workflow Runner
Agent Refinement Diagnostics
Run Diagnostics
Rollups
Agent Planner Diagnostics
Run Diagnostics
Rollups
Agent Critique Diagnostics
Run Diagnostics
Rollups
Embedding Diagnostics
Rollups
Cross-Diagnostics Dashboard
Cross Rollups
Dashboard Presets
Roles
The positions members hold: an instruction overlay plus advisory priors (preferred agents as skills, preferred workflows) and memory-access bounds. Save stores a DRAFT; Activate makes the version live (one ACTIVE per role id). Skills and workflows bias the orchestrator — they are not a whitelist.
Agents
No agent selected
Capabilities
This catalog lists the agents currently resolvable for runs (built-ins plus your active workspace agents). Author and version workspace agents below.
Workspace agent definitions
Author manifest-only agents. Save stores a DRAFT; Activate makes the version live (one ACTIVE per agent name); Retire removes it.
Workflow definitions
A workflow declares an orchestrator agent, a dispatchable-agent whitelist, and hard constraints — never a fixed sequence. Save stores a DRAFT; Activate makes the version live (one ACTIVE per workflow id). Activation requires every referenced agent and the prompt template to resolve.
Memory pipeline definitions
A memory pipeline declares a memory-orchestrator agent, a dispatchable-stage whitelist, and hard constraints — never a fixed sequence. Save stores a DRAFT; Activate makes the version live (one ACTIVE per pipeline id). Activation requires every referenced stage agent and the prompt template to resolve.