WORKING DRAFT This is a non-normative summary and index of the work of the W3C AI Knowledge Representation (AI KR) Community Group, and a map to the documents held in its repository. The AI KR CG applies canonical knowledge-representation techniques — formal semantics, logic, and controlled natural language — to track, map and evaluate the fragmented and rapidly evolving landscape of agentic AI on the Web and its neighbouring standards. The documents in the repository are working technical notes: temporary flags that record how web agents and their standards are evolving, rather than finished specifications. This note sets out the organising framework into which those notes — and future contributions — fit, and points to an interactive map of how they relate to one another and to neighbouring W3C and IETF work.
This is a draft Community Group document. It is non-normative and editorial in nature; it makes no conformance claims and uses no RFC 2119 requirement language. The technical notes it indexes are snapshots of an evolving landscape — part of an ongoing process of representation and observation, not a finished product. Comments, corrections and contributions are welcome through the Community Group and its repository.
Agentic AI is triggering a paradigm shift in computation, delivering unprecedented capabilities together with unprecedented risks — amplified by the immediacy and pervasiveness of the World Wide Web as the substrate on which web agents are developed, tested and deployed. Relevant standards are being produced at great cost across disparate venues — W3C Community and Working Groups, the IETF, and industry consortia — without manifesting coherence between them. The AI KR CG exists to make that landscape legible.
The agentic-AI landscape is fragmented and asymmetric across protocols, vocabularies, architectures and governance regimes. Through canonical KR techniques the CG builds shared, explicit knowledge representations — ontic maps — of the facets of agentic AI, in order to support alignment, consistency and model integrity across these disparate efforts.
Fragmentation produces misrepresentation: partial, inconsistent models of what agents are and do, held by systems and people alike. Left implicit, misrepresentation, misalignment and systemic deviation accumulate into systemic risk. By rendering the landscape explicit and inspectable, the CG supports the explainability required for trust, security and reliability.
There is no shared, system-level knowledge representation for the agentic-AI ecosystem. The CG contributes one by tracking and exposing the ecosystem's evolution through KR artefacts — concept maps, graphs, vocabularies, ontologies and semantic models — paying particular attention to where representations diverge. The work is devised to support the cognition of generalists and a shared understanding of a vast and complex ecosystem for which there is, as yet, no map.
This is an index and a scaffold, not a specification. Each document in the repository is a focused snapshot taken at the point where the AI KR perspective met a specific neighbouring effort. The two sections that follow give the constructs every note plugs into: the AIAO classification vocabulary (what facet of agentic AI a note concerns) and the Agent Interoperability Framework (which layer of the representation-to-trust progression it serves). The repository map then slots the current documents into that scaffold, and the slot template shows how a new note joins.
AIAO synthesises recurring agent taxonomies from the research literature into a single multi-dimensional vocabulary. Its stated design principle is synthesis over invention: existing classifications are harmonised rather than replaced. In its current revision it comprises eight dimensions:
Dimensions 7 and 8 (highlighted) are recent additions contributed by the CG beyond the synthesised literature.
Working through concrete interactions (for example the agent-interface and proof binding exchanges), the CG has identified two categories that have no adequate home in prior upper-level schemes and are proposed as genuine additions to the ontic map:
The framework arranges the work as a progression of layers, from making things explicit to making them trustworthy. Each repository note serves one or more layers:
A fuller treatment of the framework is in preparation for separate publication.
The table below slots the documents currently in the repository into the scaffold. The ontic category column names the relevant AIAO dimension or ontic-map category; the layer column gives the framework layer the note principally serves; and bridges to names the neighbouring standard it engages.
| Document | Ontic category | Layer | Bridges to |
|---|---|---|---|
| agonalign — Agent Ontology Alignment (IDL ↔ HMAS) | Agent ontology | Alignment | HMAS / Web of Things |
| webMCP — WebMCP Technical Notes | Tool / context invocation (Functional Role · Cognitive) | Representation | Model Context Protocol |
| conduit — Missing Layer Zero | Capability / commerce (Interaction Paradigm: Transactional) | Interoperability + Trust | IETF VCAP / AIVS / ATEP · Google AP2 |
| voiceAI — Configurable Voice Interaction | Interface Modality: Voice | Interoperability | W3C Web Speech API |
| DFMC — Digital Forensics Model Card | Verification / Trust Layer (provenance) | Trust | Model Cards |
| Solid — How to Use Solid | Data sovereignty | Trust (data) | Solid / decentralised data |
A contributor does not need to understand the whole repository to add to it. A new note declares five fields, and it drops into the map:
| Field | Meaning |
|---|---|
| Title | The note's subject. |
| Ontic category | Which AIAO dimension or ontic-map category it represents. |
| Layer | Representation · Alignment · Interoperability · Trust. |
| Bridges to | The neighbouring W3C / IETF / external standard it engages. |
| Status | Draft snapshot · under discussion · stable. |
The AI KR CG work sits among many related efforts across standards bodies. The table below is a short orientation; a wider, working-draft inventory — with each effort's core elements and a sketch of its AIAO / KR alignment — is maintained separately at Inventory of Agentic-AI Standards Activity.
| Body / group | Effort | AIAO / KR pointer |
|---|---|---|
| W3C — Autonomous Agents on the Web CG | HMAS / hypermedia agents | Embodiment · Alignment |
| W3C — Agent Protocol CG | Agent protocols | Interaction Style · Interoperability |
| W3C — AIVS CG (Sanctuary) | Agentic integrity verification | Verification / Trust Layer |
| W3C — Web ML WG | WebMCP (proposed) / WebNN | Tool-context invocation · Representation |
| W3C — Voice / Smart Voice Agents | Voice agent standards | Interface Modality: Voice |
| W3C — VC / DID WGs | Credentials & identity | Verification / Trust Layer |
| IETF — draft-stone-vcap / -atep / -aivs | Capability, reputation, integrity | Interoperability + Trust · cite AI KR CG TN |
| ISO/IEC JTC 1 SC 42 | AI risk / management | Governance / systemic-risk facet |
| A2A (Google→LF) · MCP (Anthropic→LF) | Agent & tool interoperability — Linux Foundation, maintainer-gated | Interaction Paradigm · Representation → Interoperability |
An interactive map of how the documents relate to one another and to neighbouring W3C and IETF work is published at https://w3c-cg.github.io/aikr/map/. It is intended to orient new readers and contributors.
The most direct way to understand the meaning and impact of this work is to participate in the Community Group. Contributions to the repository are welcome: open an issue or a pull request, populate the slot template for any new note, and the change will be triaged by the maintainer. Discussion takes place on the public-aikr mailing list.
Repository documents: agonalign, webMCP, conduit, voiceAI, DFMC, Solid.
Neighbouring W3C activity: Autonomous Agents on the Web CG, Agent Protocol CG, Web Machine Learning WG (WebMCP), Smart Voice Agents Workshop, Solid CG.
Neighbouring IETF activity: draft-stone-vcap, draft-stone-atep, draft-stone-aivs.