AI Agent
An AI agent is a software system in which a model can select actions, use tools, observe results and adapt its next steps toward an objective within defined boundaries.
KNOWLEDGE PLATFORM
Canonical concepts, methods, frameworks, technologies, research fields, research questions and publications in the Electronic Artefacts graph.
GRAPH INDEX
Every entry keeps its type, status, context and route into the wider knowledge system.
An AI agent is a software system in which a model can select actions, use tools, observe results and adapt its next steps toward an objective within defined boundaries.
Algorithmic composition is the use of rules, procedures, probability, computation or formal systems to generate or organize musical material.
Augmented intelligence is the design of tools, interfaces and systems that expand human perception, reasoning, memory and creative capability.
An autonomous system can perceive relevant state, select actions and adapt behavior toward objectives with limited direct human control during operation.
Browser software is application software delivered through web standards while relying on the browser runtime for interface, storage, permissions, media and distribution behavior.
Contextual execution is the practice of making identity, state, permissions, relationships and operating context active constraints on what a system can do.
Creative coding is the use of programming as an artistic, design or exploratory medium rather than only as an engineering implementation tool.
Cybernetic feedback is the circulation of information about a system's state back into the system so that behavior can be regulated, adapted or transformed.
Digital preservation is the long-term work of keeping digital objects understandable, authentic, usable and accessible despite changes in formats, software, hardware and context.
A domain operating system is a shared runtime and information layer that coordinates identities, entities, permissions, workflows, events and interfaces for a specific field of activity.
Entity identity is the durable naming of a person, concept, project, program, publication or artefact so that references remain stable as descriptions evolve.
Event-driven architecture is a system design approach in which components publish, transport and react to records of state change rather than depending only on direct synchronous calls.
Generative AI refers to machine-learning systems that produce or transform media such as text, image, audio, video, code or structured data from learned patterns.
A generative system is a rule-based, procedural or computational arrangement that produces variable outputs from defined constraints, materials and processes.
Graph modeling represents a domain through addressable nodes, typed relationships and properties chosen to answer specific questions and support specific operations.
A graph runtime is an execution environment in which addressable entities and typed relationships participate directly in contextual computation.
Human computer interaction is the study and design of relationships between people, computational systems, interfaces, tasks, environments and cultures of use.
Hypertext is a system of non-linear text and media connected by links, allowing readers and machines to traverse knowledge through associations.
Internet culture is the set of social forms, aesthetics, protocols, communities, memes, archives and practices that emerge through networked communication.
A knowledge graph is a structured network of entities, identifiers and typed relationships that makes knowledge navigable, queryable and reusable across contexts.
A large language model is a parameterized machine-learning model trained to predict and generate sequences of tokens from statistical patterns learned across large text or multimodal corpora.
Linked Data is a web publishing approach that identifies things with stable URIs and connects them through machine-readable statements.
Machine learning workflows are the ordered practices that move from source material and metadata through validation, preparation, training, evaluation and deployment decisions.
Metadata is structured information about a resource, such as title, creator, date, format, source, rights, subject, relation and preservation context.
Microservice architecture structures a software system as independently deployable services aligned with bounded capabilities and communicating through explicit contracts.
Motion design is the use of time, movement, transition, rhythm and sequencing to structure visual communication and interface behavior.
Multimodal AI describes systems that learn from, align, transform or generate more than one modality such as text, image, audio, video, sensor data or structured records.
In knowledge engineering, an ontology is an explicit specification of the kinds of entities, properties, relationships and constraints used to represent a domain.
Open source is a software and cultural practice in which source code is made available under licenses that allow use, study, modification and redistribution.
An open-weight model is a machine-learning model whose learned parameters are distributed for reuse under stated terms, without necessarily providing the training data, training code or freedoms required by open-source definitions.
A personal knowledge system is a practice and tool environment for capturing, linking, revising and retrieving notes, sources, ideas and decisions over time.
Procedural graphics are images or visual systems generated from rules, algorithms, parameters, simulation or code rather than only manually drawn assets.
Provenance is information about the people, activities, sources, transformations and decisions involved in producing a thing or piece of data.
Retrieval-augmented generation is an architecture that retrieves external information at query time and supplies selected evidence to a generative model before or during response production.
Signal archaeology is the interpretation of technical, sonic, visual or archival traces as evidence of hidden processes, transformations and histories.
In VASTE, an Actor is an extension-owned graph identity whose effective observation and action are resolved inside a specific System, Environment, topology and policy context.
Speech datasets are structured collections of recorded speech, transcripts, speaker context and quality metadata prepared for analysis, preservation or downstream machine-learning workflows.
Speech recording is the directed capture of spoken language with enough technical, contextual and consent metadata to support review, reuse and preservation.
Systems thinking is an approach that studies elements through their relationships, feedback, boundaries, delays, stocks, flows and patterns of behavior over time.
Typography is the design and arrangement of written language through typefaces, spacing, hierarchy, rhythm, scale and reading conditions.
VAB is VASTE’s Assisted Boot orchestration path for understanding an initial intent, composing a sealed plan, admitting a Founding Actor and materializing a governed starting graph.
A .vast file is an experimental `vast/1` sealed JSON package carrying a System-relative whole-System or subtree closure, its manifest and integrity hash—not a live Environment.
A VASTE extension is an optional, System-scoped capability unit that declares domain actions, bindings and surfaces while runtime authority remains in the core execution path.
VASTE has a closed primitive roster—Vertex, Tie, Action, Surface and Environment—from which graph identity, topology, admitted change, observation and execution-local context are composed.
Voice technology is the design and engineering of systems that capture, analyze, transform, preserve or present spoken voice as technical and cultural material.
Web audio is the use of browser-based audio APIs and related web technologies to synthesize, process, analyze, route and present sound.
A lightweight vanilla HTML, CSS and JavaScript framework used by Electronic Artefacts for fast prototyping, public showcases and small production surfaces.
Understand A2A agent cards, messages, tasks and artifacts, how A2A differs from MCP, and why agent interoperability still needs identity, policy and audit trails.
Understand the difference between AI agents and AI workflows, when to use each architecture, and how to design reliable hybrid systems.
Understand how AI search changes SEO strategy through helpful content, structured data, crawlable pages, entity identity and knowledge graph architecture.
A technical article on algorithmic composition, rule-based music, generative sound, cybernetics and Electronic Artefacts audio research.
Understand C2PA and Content Credentials for media provenance, generative AI labelling, archive trust and cultural production workflows.
A technical article connecting contextual execution, graph runtime, Runtime Theory and VASTE.
A technical article on teaching creative coding, Processing, p5.js, computational media, open source and Electronic Artefacts learning culture.
A technical article on digital preservation, living archives, file formats, provenance and Electronic Artefacts cultural records.
Prepare creative and cultural AI workflows for EU transparency rules with a layered approach to machine-readable marks, visible disclosure, provenance and editorial records.
Learn event-driven architecture through event streams, delivery guarantees, schema evolution, idempotency, projections and runtime design.
A concise record of the foundational research lineage connecting information architecture, taxonomy, runtime systems and public knowledge structures.
A technical article on generative AI, latent space, creative workflows, provenance, augmented intelligence and responsible production.
A technical article on generative systems, cybernetic feedback, creative coding, algorithmic composition and Electronic Artefacts projects.
Learn how LLMs work, from tokenization and training to attention, context windows, decoding, hallucinations, tools and evaluation.
A technical article on HCI, creative tools, interface design, augmented intelligence, accessibility and Electronic Artefacts systems.
A technical article on hypertext, augmented intelligence, linked pages, knowledge graphs and Electronic Artefacts knowledge publishing.
Understand IIIF as presentation infrastructure for compound cultural objects, archives, manifests, canvases and annotations.
A technical article on knowledge graphs, cultural heritage, provenance and public knowledge pages, connected to Vestiges and the Electronic Artefacts graph.
A technical article on Linked Data, JSON-LD, canonical URLs, identifiers and SEO for static knowledge platforms.
Understand local AI and open-source AI systems, including model weights, quantization, llama.cpp, privacy, hardware and licensing.
A technical article on metadata, cataloguing, cultural memory, preservation standards and Electronic Artefacts graph records.
Learn when microservices make sense, why modular monoliths are often the better starting point, and how to define durable system boundaries.
Understand Model Context Protocol through hosts, clients, servers, resources, prompts, tools, security boundaries and contextual execution.
A technical article on motion design, web animation, interface state, accessibility and temporal visual systems.
Learn how multimodal AI connects text, images, audio and video, and how to evaluate cross-modal systems for creative and cultural use.
Understand observability for AI agents and tool-calling systems through traces, metrics, logs, audit events and OpenTelemetry.
Understand the differences between taxonomies and ontologies and learn how to design a durable knowledge model without overengineering.
A technical article on open source software, maintainership, creative coding, infrastructure and Electronic Artefacts knowledge culture.
A technical article on personal knowledge systems, digital gardens, backlinks, research memory and public knowledge hubs.
A technical article on procedural graphics, shaders, WebGL, creative coding and generative visual systems.
Understand prompt injection in AI knowledge systems through retrieval, agents, MCP tools, permissions, untrusted content and contextual execution.
Learn how Redis Streams works and how to use consumer groups, pending entries and idempotent workers for reliable orchestration.
Learn how responsible AI governance applies to creative technology, cultural infrastructure, archives, generative media and AI-assisted knowledge workflows.
Learn how retrieval-augmented generation works and how to build source-grounded RAG systems with metadata, knowledge graphs and evaluation.
Understand runtime engines and domain operating systems, and how shared entities, permissions and events can support many applications.
A technical article on signal archaeology, audio memory, machine listening, ORETH and Palimpsests.
Learn systems thinking through creative practice, software, studios and cultural projects, with practical mapping and intervention methods.
A technical article on typography, reading systems, web interfaces, accessibility and Electronic Artefacts editorial design.
Understand how verifiable credentials can support creator identity, archive provenance, rights workflows and trusted claims in cultural knowledge systems.
A technical article on Web Audio, audio graphs, browser sound, ORETH, machine listening and interactive media.
Explore WebMCP, structured browser tools, declarative forms, permissions and why an agent-readable website still needs semantic HTML and accessible human interfaces.
Understand WebNN as a browser API for hardware-accelerated neural-network inference and local AI interaction design.
Learn when graph models outperform folder hierarchies, why relationships matter, and how to keep folders as useful projections over connected data.
An active Electronic Artefacts research field connecting the archived VOID codebase, ARCA, VASTE and the definition of graph runtime.
A public Electronic Artefacts research question about first-contact understanding, conversational onboarding and graph-shaped user context.
A public Electronic Artefacts research question about self-explaining software, knowledge graphs, generated documentation and semantic public surfaces.
A public Electronic Artefacts research question about reproducible speech datasets, local-first recording and metadata-rich voice workflows.
A technology record for federated network culture and social web infrastructure.
A canonical guide to A2A agent cards, messages, tasks, artifacts, protocol bindings, security boundaries and its relationship with MCP.
A technology record for C2PA and Content Credentials as provenance infrastructure for digital media.
A technology record for interoperable event metadata across services and platforms.
A technology record for IIIF as interoperable presentation infrastructure for compound cultural objects.
A technology record for JSON-LD as the structured data format used by Electronic Artefacts canonical pages.
A technology record for local model inference, quantization and portable AI deployment.
A technology record for MCP as an integration protocol for tool-using AI applications, resources and contextual workflows.
A technology record for OpenTelemetry as telemetry infrastructure for distributed systems and AI tool workflows.
A technology record for RDF as a reference model behind knowledge graphs, Linked Data and semantic publication.
A technology record for event streams, orchestration and real-time processing.
A technology record for controlled vocabularies and lightweight semantic organization.
A technology record for the architecture underlying many modern language and multimodal models.
A technology record for animation timing, synchronization and interface motion on the web.
A technology record for browser-native audio processing and synthesis.
A maturity-aware record of WebMCP, in-page tools, browser mediation, origins, permissions and human-agent collaboration.