Formal name: Qi Intelligent Cooperating System—the cooperation layer for humans, AI agents, applications, and services over IXO state. This page uses Qi for readability.
Qi helps humans and AI agents work together on verified workflows: shared context, clear permissions, messages and rooms where coordination lives, and actions taken through declared interfaces—not by inventing facts or bypassing governance.
Qi gives agents what they need to act on IXO state responsibly: context, tools, workflow surfaces, and auditability, instead of isolated prompts or opaque tool chains.
A useful rule:
- IXO answers: what is asserted, who has authority, what evidence exists, and what changed?
- Qi answers: who needs to act next, what context they need, how participants coordinate, and how actions flow through governed steps?
How Qi fits into the IXO stack
Qi sits above IXO verifiable state and uses several parts of the stack.
IXO Protocol
IXO Protocol provides the verifiable state foundation.
Linked data and evidence services
Linked services provide the data, evidence, indexes, and retrieval surfaces that applications and agents need.
These services help Qi actors understand what happened, what evidence exists, and which state transitions may be valid.
IXO Matrix
IXO Matrix provides secure rooms, messaging, and shared cooperation spaces.
It gives humans, agents, applications, and services a place to exchange context, coordinate decisions, and preserve the conversation around workflow actions.
Agentic Oracles
Agentic Oracles are the service family for intelligent observation, evaluation, decision support, and workflow automation.
They connect agent behavior to IXO-backed context, evidence, and state transitions.
Qi Agents
Qi Agents are productized agent surfaces built on the Qi cooperation model.
They help users and systems act on IXO-backed context through guided reasoning, secure coordination, and declared tools.
SDKs, APIs, and MCP tools
Developer interfaces expose IXO and Qi capabilities to applications and agents.
Use SDKs and APIs for implementation. Use MCP tools when AI agents need structured access to IXO-backed context, tools, and workflows.
Why Qi exists
Most agent frameworks focus on prompts, memory, tools, and API calls.
Qi is designed for a different problem: intelligent cooperation over verifiable reality.
In IXO-based systems, agents do not operate only on generated context or private application state. They operate over domains, identities, claims, credentials, evidence, workflows, messages, and permissions that other participants can inspect and verify.
This makes Qi useful when an intelligent system must:
- coordinate across people, organizations, applications, services, and agents
- preserve shared context across long-running workflows
- evaluate claims and evidence before taking action
- support human review, delegation, negotiation, and escalation
- trigger updates to IXO-backed processes through declared interfaces
- keep action accountable to state, authority, and provenance
Qi is not just automation. It is cooperation with memory, context, authority, and verifiability.
Cooperation model
Qi workflows usually follow this pattern.
Read verifiable state
A human, agent, application, or service identifies the relevant domain, entity, claim, credential, workflow, room, or evidence record.
Build shared context
Qi combines IXO-backed state, linked evidence, room history, messages, permissions, and tool outputs into useful context.
Reason and coordinate
Actors interpret the context, evaluate evidence, discuss options, request clarification, negotiate next steps, or escalate to a human reviewer.
Act through declared interfaces
Actions are performed through documented SDKs, APIs, MCP tools, protocol operations, or workflow-specific services.
Feed results back into state
The outcome is recorded, attested, messaged, indexed, or used to advance an IXO-backed workflow.
The important principle is that Qi actors should not invent state or act outside the workflow model. They should discover state, respect authority, use declared interfaces, and make results inspectable.
Agentic Oracles and Qi Agents
Agentic Oracles and Qi Agents are related, but they should not be treated as interchangeable terms.
The oracle and agent service family for observing state, evaluating evidence, supporting decisions, and automating workflow actions.
Qi AgentsProductized agent experiences that use Qi cooperation patterns to help humans and systems work with IXO-backed context.
Use Agentic Oracles when describing the architecture and service pattern.
Use Qi Agents when describing user-facing or productized agent surfaces.
Use the SDK and API references when implementing either pattern.
What developers can build with Qi
Qi is useful wherever intelligent actors need to cooperate over verified state.
Examples include:
Agents that inspect evidence, compare it with workflow rules, and support claim review or verification.
Digital MRV workflowsSystems that connect measurement, reporting, verification, claims, attestations, and outcomes.
Secure data roomsCooperation spaces where organizations, people, services, and agents coordinate around shared context.
Workflow automationServices that monitor state, detect required actions, route decisions, and trigger the next workflow step.
MCP-enabled agent toolsTool interfaces that allow AI agents to access IXO-backed context and perform documented actions.
Human-agent operationsSystems where humans supervise, delegate, approve, dispute, or refine actions performed by agents and services.
Developer entry points
Learn the vocabulary for IXO state, Qi cooperation, claims, credentials, workflows, evidence, and agents.
Agentic OraclesUnderstand the conceptual model for intelligent oracle services, agent capabilities, and automation patterns.
IXO MatrixLearn how secure rooms, messaging, and shared context support cooperation between people, services, and agents.
Model Context ProtocolConnect AI agents to IXO-backed context, tools, and workflow actions through MCP interfaces.
Agentic Oracles ADKUse the development kit for oracle-powered services and agentic automation patterns.
Personal Agent ADKUse the package reference for building personal agent capabilities and integrations.