Skip to content

ARCHER Suite Glossary


Capability Hierarchy

TermDefinitionCallsExample
PrimitiveSingle, atomic, judgment-free operation. Does ONE thing.Nothingread_file, create_entity
CompositeMultiple primitives combined into a reusable operation.Primitivesstore_experience, execute_task_with_feedback
WorkflowOrchestrated sequence of composites with branching, conditions, and approvals.Compositesmeeting_notes_to_work_items, approval_workflow
AgentAutonomous, goal-driven actor that selects and executes workflows/composites/primitives based on context.Workflows, Composites, Primitivesmeeting_assistant_agent, compliance_officer_agent
OrchestrationMeta-level coordination across multiple agents, handling conflicts, priorities, and system-wide coherence.Agentsgovernance_orchestration, agent_fleet_orchestration

Core Components

TermDefinition
ArcherMeta-orchestrator and UX layer. Persistent ambient presence that maintains system coherence.
ODIEOutcome Driven Intelligence Engine. Reasoning engine for outcomes, beliefs, and signals.
CogniscientAdaptive intelligence substrate. Memory, knowledge graph, and experience storage.
FluxioAgent runtime and execution platform. Where agents run and actions happen.
LibrarianResource manager. Scores and recommends tools, agents, and services.

Key Concepts

TermDefinition
OutcomeA measurable desired state, structured as: Direction + Measure + Object + Context.
SignalAn observed data point that may indicate progress toward or away from an outcome.
BeliefA provisional assumption held with a confidence level, subject to revision based on evidence.
EntityA node in the knowledge graph (person, organization, project, document, event, concept).
RelationshipA typed, weighted connection between two entities.
ExperienceA stored summary of an interaction or event (gist, not verbatim).
NudgeA non-invasive, actionable notification delivered in the user's flow of work.
Opportunity Score(Importance × 2) - Satisfaction. Measures how underserved an outcome is.

Agent-Native Principles

TermDefinition
ParityWhatever the user can do via UI, the agent can do via tools.
GranularityPrefer atomic primitives. Features emerge from agent loops, not bundled tools.
ComposabilityNew features = new prompts (when tools are atomic and parity exists).
Emergent CapabilityAgent can accomplish things you didn't explicitly design for.
Judgment-FreeTools don't decide IF or WHICH. Judgment belongs in prompts.

Governance Terms

TermDefinition
Autonomy LevelHow much authority an agent has (0=observe only → 5=broad autonomy).
ApprovalHuman authorization required before an action executes.
PolicyA rule that governs what actions are allowed, forbidden, or require approval.
Audit LogImmutable record of all actions taken, by whom, when, and with what result.

Document generated January 2026