@prefix : . @prefix post: . @prefix schema: . @prefix rdf: . @prefix rdfs: . @prefix owl: . @prefix xsd: . @prefix prov: . @prefix cdx: . @base . # ───────────────────────────────────────────────────────────────────────────── # Meshup document (self-describing CreativeWork) # ───────────────────────────────────────────────────────────────────────────── <> a schema:CreativeWork ; schema:about :meshupThesis ; schema:name "Apps, Agents, and Aggregation — a Stratechery × Semantic Web Meshup"@en ; schema:description "A three-source meshup of Ben Thompson's Stratechery essays — The Gen AI Bridge to the Future (2024), Write Things Down (2026), and Apps, Agents, and Aggregation (2026) — fused through a Semantic Web substrate: writing things down as RDF triples in a Virtuoso knowledge graph, SPARQL as the act of reading the bucket back, and dereferenceable hyperlinks as an aggregation moat without lock-in."@en ; schema:dateCreated "2026-09-28T16:15:00Z"^^xsd:dateTime ; schema:dateModified "2026-09-28T16:15:00Z"^^xsd:dateTime ; schema:author ; schema:hasPart :meshupThesis, :sourceStrip, :glossarySection, :faqSection, post:howTo, :comparisonSection, :memorySection, :messageMediumSection ; prov:wasGeneratedBy , . # ───────────────────────────────────────────────────────────────────────────── # 1. THE THREE SOURCE ARTICLES (Ben Thompson / Stratechery) # ───────────────────────────────────────────────────────────────────────────── a schema:NewsArticle ; schema:name "The Gen AI Bridge to the Future"@en ; schema:headline "The application layer of one computing paradigm provides the bridge to the next — and generative AI is that bridge"@en ; schema:abstract "Ben Thompson traces computing history from mainframe to PC to smartphone and predicts wearables as the next paradigm, whose defining trait is the absence of a direct mechanical input. His central claim: the application layer of one paradigm is the bridge to the next, which is why generative AI — still delivered through today's apps and chatbots — is the bridge that will unlock entirely new paradigms of computing, and why the product overhang from today's models is the real story of 2024."@en ; schema:url "https://stratechery.com/2024/the-gen-ai-bridge-to-the-future/" ; schema:author ; schema:publisher ; schema:datePublished "2024-12-02"^^xsd:date ; schema:mentions , , , , , :applicationLayerBridgeConcept ; schema:isPartOf :sourceStrip . a schema:NewsArticle ; schema:name "Write Things Down"@en ; schema:headline "Writing things down empties working memory into a trusted system — the same act a knowledge graph performs for an AI agent"@en ; schema:abstract "Ben Thompson confesses he could never run OmniFocus himself and instead hired an assistant to be his 'Inbox and task manager', letting him empty his RAM and focus on writing. The essay builds to a definition — AGI is AI that learns continuously — and closes with a warning drawn from Nick Bostrom's superintelligence: no matter how many systems you build, you still have to act, because what we humans wish for is the subject of highest concern."@en ; schema:url "https://stratechery.com/2026/write-things-down/" ; schema:author ; schema:publisher ; schema:datePublished "2026-09-08"^^xsd:date ; schema:mentions , , , , , , , :trustedBucketConcept, :writeThingsDownConcept, :agiDefinitionClaim ; schema:isPartOf :sourceStrip . a schema:NewsArticle ; schema:name "Apps, Agents, and Aggregation"@en ; schema:headline "Messaging is the killer app, pre-built UI is dead, and the fight to be the agent users talk to is aggregation's next act"@en ; schema:abstract "Opening with Steve Jobs' 'three revolutionary products' reveal of the iPhone, Ben Thompson argues that messaging — chatbots now, natural interfaces later — is how we will communicate with AI, that we will not program computers but let AI use them, and that pre-built UI is dead. The stakes resolve into aggregation: agents get better the more context they have about you, so the fight to be the one agent users talk to will be won by Meta and Microsoft, who already have distribution."@en ; schema:url "https://stratechery.com/2026/apps-agents-and-aggregation/" ; schema:author ; schema:publisher ; schema:datePublished "2026-09-28"^^xsd:date ; schema:mentions , , , , , :jobsToBeDoneConcept, :aggregationTheoryConcept, :prebuiltUIDeadClaim, :contextMoatClaim ; schema:isPartOf :sourceStrip . :sourceStrip a schema:ItemList ; schema:name "Meshed source documents"@en ; schema:description "The three Stratechery essays by Ben Thompson fused by this meshup."@en ; schema:numberOfItems 3 ; schema:itemListElement , , . # ───────────────────────────────────────────────────────────────────────────── # 2. THE MESHUP THESIS — the collection's own synthesized argument # ───────────────────────────────────────────────────────────────────────────── :meshupThesis a schema:TechArticle ; schema:name "Write It Down as Triples: A Semantic Web Reframing of Ben Thompson's Trilogy"@en ; schema:headline "Ben Thompson's three essays share one unstated substrate — and Virtuoso makes it explicit"@en ; schema:abstract "The Gen AI Bridge, Write Things Down, and Apps, Agents, and Aggregation are three facets of one move: offloading cognition to an external system. Ben Thompson names that system a 'trusted bucket', a hired assistant, an application-layer bridge, and finally an agent that aggregates by knowing you. A Semantic Web substrate makes each of those concrete: writing things down is asserting RDF triples; the trusted bucket is a named graph in a Virtuoso quad store; 'AI that learns continuously' is a knowledge graph that accumulates dated, provenance-bearing triples; 'getting things done' is an agent issuing a SPARQL query against your graph; and aggregation without lock-in is a Platinum Layer of dereferenceable hyperlinks — your own graph as the interface, not someone else's walled app."@en ; schema:author ; schema:about :claimTriplesNotProse, :claimGraphAsBucket, :claimGraphLearns, :claimQueryAsAction, :claimPlatinumAggregation, :claimMediumIsMessage, :claimMemoryLayer, :claimLooseCoupling, :claimOpal, , , , , , , ; schema:mentions , , , , , , . # ── Source-backed claims (Ben Thompson's theses) ───────────────────────────── :applicationLayerBridgeClaim a schema:Claim ; schema:name "The application layer is the bridge"@en ; schema:text "The application layer on one computing paradigm provides the bridge to the next — which is why generative AI, delivered through today's apps, is the bridge to the future."@en ; schema:about :applicationLayerBridgeConcept ; schema:author ; schema:isPartOf :sourceStrip . :agiDefinitionClaim a schema:Claim ; schema:name "AGI is AI that learns continuously"@en ; schema:text "Ben Thompson's personal definition of AGI: 'AI that learns continuously.' Current large language models do not qualify because they do not keep learning after training."@en ; schema:about ; schema:author ; schema:isPartOf :sourceStrip . :prebuiltUIDeadClaim a schema:Claim ; schema:name "Pre-built UI is dead"@en ; schema:text "Not only will we not program computers, we will not use them — AI will. Pre-built UI, 'write once, run everywhere, for everyone', is dead, replaced by agents and computer use."@en ; schema:author ; schema:isPartOf :sourceStrip . :contextMoatClaim a schema:Claim ; schema:name "Agents aggregate through context"@en ; schema:text "Models are relatively substitutable, but agents operate better the more context they have about you and the more access they have to your logins and files — so most people will have one agent, not multiple, and the moat is distribution."@en ; schema:about :aggregationTheoryConcept ; schema:author ; schema:isPartOf :sourceStrip . :actClaim a schema:Claim ; schema:name "You still have to act"@en ; schema:text "No matter how many systems you build, you still have to act. Writing things down is unbelievably powerful, but its power will always pale in comparison to getting things done."@en ; schema:about ; schema:author ; schema:isPartOf :sourceStrip . # ── Meshup claims (the Virtuoso / Semantic Web reframing — load-bearing bullets) ─ :claimTriplesNotProse a schema:Claim ; schema:name "Writing things down = asserting triples"@en ; schema:text "What Ben Thompson calls 'writing things down' is, on a Semantic Web, asserting subject-predicate-object triples. A note in prose becomes a fact: a named thing, a relation, and a value — each identifiable by its own hyperlink."@en ; schema:about ; schema:author . :claimGraphAsBucket a schema:Claim ; schema:name "The trusted bucket is a named graph in Virtuoso"@en ; schema:text "David Allen's 'trusted bucket' — the external store you know you will review — is a named graph in a Virtuoso quad store. It holds more than RAM, it never forgets, and it is queryable by SQL and SPARQL from one engine."@en ; schema:about :trustedBucketConcept ; schema:author . :claimGraphLearns a schema:Claim ; schema:name "A knowledge graph is AI that learns continuously"@en ; schema:text "Ben Thompson says AGI is 'AI that learns continuously.' A knowledge graph that keeps accepting dated, provenance-bearing triples does exactly that: it accumulates, it is auditable, and it learns without retraining a model."@en ; schema:about ; schema:author . :claimQueryAsAction a schema:Claim ; schema:name "Getting things done is a SPARQL query"@en ; schema:text "The assistant Ben Thompson hired to run his inbox becomes, in this meshup, an AI agent that reads the bucket back with a query. SPARQL is the formula the agent runs to turn 'written down' into 'done'."@en ; schema:about ; schema:author . :claimPlatinumAggregation a schema:Claim ; schema:name "Aggregation without lock-in is the Platinum Layer"@en ; schema:text "Ben Thompson says the aggregation moat is owning the interface. On a Semantic Web the interface is a dereferenceable hyperlink: your graph, addressed by stable IRIs, aggregates attention and context without a walled app — a Platinum Layer over Bronze, Silver and Gold."@en ; schema:about :platinumLayerConcept ; schema:author . # ───────────────────────────────────────────────────────────────────────────── # 3. PEOPLE # ───────────────────────────────────────────────────────────────────────────── a schema:Person ; schema:name "Ben Thompson"@en ; schema:description "Author of Stratechery, the strategy newsletter whose three essays — The Gen AI Bridge to the Future, Write Things Down, and Apps, Agents, and Aggregation — form this meshup."@en ; schema:jobTitle "Author, Stratechery"@en ; schema:worksFor . a schema:Person ; schema:name "Jensen Huang"@en ; schema:description "NVIDIA CEO who declared on X in September 2026 that AGI had arrived with GPT-6 Astra, a claim Ben Thompson disputes using his own definition of AGI."@en ; schema:worksFor . a schema:Person ; schema:name "Steve Jobs"@en ; schema:description "Apple co-founder whose 2007 iPhone reveal — 'three revolutionary products' that were one device — Ben Thompson uses to frame the 2026 collapse of apps, messaging, and agents into a single reality."@en . a schema:Person ; schema:name "Mark Zuckerberg"@en ; schema:description "Meta CEO whose 2013 claim that 'apps aren't the center of the world, people are' Ben Thompson contested with Jobs to Be Done — and whose distribution now positions Meta to win the agent era."@en . a schema:Person ; schema:name "David Allen"@en ; schema:description "Author of Getting Things Done, whose RAM metaphor — the mind is a focusing tool, not a storage place — grounds Ben Thompson's argument that writing things down is how we empty working memory."@en . a schema:Person ; schema:name "Merlin Mann"@en ; schema:description "The 43folders writer who introduced Ben Thompson to Getting Things Done, and whose unfinished book project anchors the essay's coda: systems are not the same as doing."@en . a schema:Person ; schema:name "Tim Berners-Lee"@en ; schema:description "Inventor of the World Wide Web whose founding move — name anything of interest with a hyperlink — underlies the Semantic Web substrate this meshup maps onto Ben Thompson's trilogy."@en . # ───────────────────────────────────────────────────────────────────────────── # 4. ORGANIZATIONS AND PRODUCTS # ───────────────────────────────────────────────────────────────────────────── a schema:Organization ; schema:name "Stratechery"@en ; schema:description "Ben Thompson's technology strategy publication and publisher of the three meshed essays."@en ; schema:url "https://stratechery.com/" . a schema:Organization ; schema:name "Apple"@en ; schema:description "Maker of the iPhone, whose 2007 reveal Ben Thompson repurposes to describe 2026's reality of messaging, agents, and the death of pre-built UI."@en . a schema:Organization ; schema:name "Microsoft"@en ; schema:description "One of the two companies Ben Thompson argues will win the agent era, reaching nearly every employee through established distribution."@en . a schema:Organization ; schema:name "Meta"@en ; schema:description "Owner of WhatsApp and the messaging layer that reaches nearly every person on earth — Ben Thompson's other predicted winner of the fight to be the agent users talk to."@en . a schema:Organization ; schema:name "OpenAI"@en ; schema:description "Maker of GPT-6 Astra, the model Jensen Huang declared to be AGI in September 2026."@en . a schema:Organization ; schema:name "NVIDIA"@en ; schema:description "The chipmaker whose Grace Blackwell NVLink72 systems trained GPT-6 Astra, and whose CEO made the AGI declaration Ben Thompson disputes."@en . a schema:Organization ; schema:name "OpenLink Software"@en ; schema:description "Maker of Virtuoso and URIBurner — the quad-store database and Linked Data service that supply the Semantic Web substrate for this meshup's reframing."@en ; schema:url "https://www.openlinksw.com/" . # ── Software applications (Virtuoso / URIBurner / skills) ──────────────────── a schema:SoftwareApplication ; schema:name "Virtuoso Universal Server"@en ; schema:description "OpenLink's converged virtual DBMS: relational tables and RDF graphs in one quad-store engine, queried in SQL, SPARQL, SPASQL and GraphQL, with named graphs, RDFS/OWL-subset inference, and RDF Views — the 'trusted bucket' in which this meshup's knowledge graph lives."@en ; schema:url "https://virtuoso.openlinksw.com/" ; schema:publisher . a schema:SoftwareApplication ; schema:name "URIBurner"@en ; schema:description "OpenLink's Linked Data service: a Virtuoso-backed SPARQL endpoint, RDF sponger, and describe/resolver used to run this collection's live queries and to resolve its entity hyperlinks."@en ; schema:url "https://linkeddata.uriburner.com/" ; schema:isBasedOn ; schema:publisher . a schema:SoftwareApplication ; schema:name "kg-generator"@en ; schema:description "AI agent skill that generated this meshup's RDF knowledge graph from three Stratechery source documents."@en ; schema:url "https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/kg-generator" . a schema:SoftwareApplication ; schema:name "rdf-infographic-skill"@en ; schema:description "AI agent skill that rendered this RDF knowledge graph as an interactive HTML infographic under a strict harness contract."@en ; schema:url "https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/rdf-infographic-skill" . # ───────────────────────────────────────────────────────────────────────────── # 5. GLOSSARY — DefinedTermSet with ≥10 DefinedTerms # ───────────────────────────────────────────────────────────────────────────── :glossarySection a schema:DefinedTermSet ; schema:name "Glossary — Stratechery × Semantic Web Meshup"@en ; schema:hasDefinedTerm :aggregationTheoryConcept, :jobsToBeDoneConcept, :applicationLayerBridgeConcept, :generativeAIBridgeConcept, :writeThingsDownConcept, :trustedBucketConcept, :namedGraphConcept, :quadStoreConcept, :platinumLayerConcept, , , , , , , , :looseCouplingConcept, :agentMemoryConcept, :a2aConcept, :agentMdConcept, :skillsMdConcept, :openapiConcept, , , , :intentConcept, :crudConcept, :capabilityConcept, :authorizationConcept, :writtenRecordConcept, :webidConcept, :aclConcept, :httpConcept . :aggregationTheoryConcept a schema:DefinedTerm ; schema:name "Aggregation Theory"@en ; schema:description "Ben Thompson's signature framework: on the internet, whoever owns the interface between suppliers and consumers aggregates demand and captures the value — next applied to the fight to be the one agent users talk to."@en ; schema:inDefinedTermSet :glossarySection . :jobsToBeDoneConcept a schema:DefinedTerm ; schema:name "Jobs to Be Done"@en ; schema:description "The framework Ben Thompson used to rebut Mark Zuckerberg's 'apps vs. people' dichotomy: users hire products to do specific jobs, so people matter through the jobs they hire apps to do."@en ; schema:inDefinedTermSet :glossarySection . :applicationLayerBridgeConcept a schema:DefinedTerm ; schema:name "The Application Layer as Bridge"@en ; schema:description "Ben Thompson's claim that the application layer of one computing paradigm provides the bridge to the next — the mechanism by which generative AI, delivered through today's apps, unlocks future paradigms."@en ; schema:inDefinedTermSet :glossarySection . :generativeAIBridgeConcept a schema:DefinedTerm ; schema:name "Generative AI Bridge"@en ; schema:description "The thesis that generative AI is valuable now as a bridge technology — chatbots and copilots delivered on today's devices — while the product overhang from today's models is what will build the application layer of the next paradigm."@en ; schema:inDefinedTermSet :glossarySection . :writeThingsDownConcept a schema:DefinedTerm ; schema:name "Writing Things Down"@en ; schema:description "The practice — from David Allen's Getting Things Done — of moving incomplete thoughts out of working memory into a trusted external system, the human act this meshup maps onto asserting RDF triples."@en ; schema:inDefinedTermSet :glossarySection . :trustedBucketConcept a schema:DefinedTerm ; schema:name "Trusted Bucket"@en ; schema:description "David Allen's term for an external store you know you will review — offloading RAM into a container. In this meshup the trusted bucket is a named graph in Virtuoso."@en ; schema:inDefinedTermSet :glossarySection . :namedGraphConcept a schema:DefinedTerm ; schema:name "Named Graph"@en ; schema:description "A set of RDF triples identified by its own IRI — the unit of provenance in a quad store, letting a knowledge graph track who asserted each fact and when."@en ; schema:inDefinedTermSet :glossarySection . :quadStoreConcept a schema:DefinedTerm ; schema:name "Quad Store"@en ; schema:description "A database that stores RDF quads (subject, predicate, object, graph) rather than triples, so multiple named graphs coexist and are addressable — the engine Virtuoso provides alongside its relational tables."@en ; schema:inDefinedTermSet :glossarySection . :platinumLayerConcept a schema:DefinedTerm ; schema:name "Platinum Layer"@en ; schema:description "Kingsley Idehen's extension to the medallion architecture: using dereferenceable hyperlinks as stable, standardized identifiers so a knowledge graph becomes an aggregation and identity surface — a Semantic Web interface without a walled app."@en ; schema:inDefinedTermSet :glossarySection . a schema:DefinedTerm ; schema:name "Knowledge Graph"@en ; schema:description "A network of entities and relationships expressed as structured, machine-readable statements — the substrate this meshup substitutes for undifferentiated prose notes."@en ; schema:inDefinedTermSet :glossarySection . a schema:DefinedTerm ; schema:name "RDF"@en ; schema:description "The Resource Description Framework — a W3C entity-description model loosely coupled to serializations, in which every statement is a subject-predicate-object triple."@en ; schema:inDefinedTermSet :glossarySection . a schema:DefinedTerm ; schema:name "SPARQL"@en ; schema:description "The W3C query language for RDF graphs — the formula an agent runs to read a knowledge graph back and turn 'written down' into 'done'."@en ; schema:inDefinedTermSet :glossarySection . a schema:DefinedTerm ; schema:name "Semantic Web"@en ; schema:description "Tim Berners-Lee's project to name anything of interest with a hyperlink, giving machines an entity-description layer that the Web gave documents."@en ; schema:inDefinedTermSet :glossarySection . a schema:DefinedTerm ; schema:name "AGI"@en ; schema:description "Artificial general intelligence — which Ben Thompson defines as 'AI that learns continuously', a definition Jensen Huang's 'AGI has arrived' claim does not satisfy."@en ; schema:inDefinedTermSet :glossarySection . a schema:DefinedTerm ; schema:name "Getting Things Done"@en ; schema:description "David Allen's productivity methodology: capture every open loop into a trusted system so the mind can focus — whose RAM analogy anchors the Write Things Down essay."@en ; schema:inDefinedTermSet :glossarySection . a schema:DefinedTerm ; schema:name "URI (Hyperlink)"@en ; schema:description "A Uniform Resource Identifier — the dereferenceable hyperlink that names a person, place, concept, or thing, and the atomic unit of both the Web and this meshup's aggregation-without-lock-in."@en ; schema:inDefinedTermSet :glossarySection . # ───────────────────────────────────────────────────────────────────────────── # 6. COMPARISON — Stratechery framing vs. Semantic Web / Virtuoso reframing # ───────────────────────────────────────────────────────────────────────────── :comparisonSection a schema:ItemList ; schema:name "Comparison — Ben Thompson's framing vs. a Semantic Web substrate"@en ; schema:description "Six load-bearing concepts from the three essays, each restated in the language of RDF, SPARQL, and Virtuoso. The reframing preserves every insight while upgrading the substrate from prose and walled apps to triples and dereferenceable hyperlinks."@en ; schema:itemListElement :dimOffloadCognition, :dimContinuousLearning, :dimParadigmBridge, :dimInterface, :dimAggregationMoat, :dimAction, :dimMemory . :dimOffloadCognition a cdx:ComparisonDimension ; schema:name "Offloading cognition"@en ; schema:description "How an overflowing working memory is emptied into an external system."@en ; schema:additionalProperty [ a schema:PropertyValue ; schema:name "Stratechery framing"@en ; schema:value "Write things down into a trusted bucket, or hire an assistant to run your OmniFocus inbox for you."@en ], [ a schema:PropertyValue ; schema:name "Semantic Web reframing"@en ; schema:value "Assert subject-predicate-object triples into a named graph — a note becomes a queryable fact with its own IRI."@en ] . :dimContinuousLearning a cdx:ComparisonDimension ; schema:name "Continuous learning"@en ; schema:description "What it means for an intelligence to keep learning after its initial training."@en ; schema:additionalProperty [ a schema:PropertyValue ; schema:name "Stratechery framing"@en ; schema:value "AGI is 'AI that learns continuously' — which today's frozen large language models do not do."@en ], [ a schema:PropertyValue ; schema:name "Semantic Web reframing"@en ; schema:value "A knowledge graph that keeps accepting dated, provenance-bearing triples learns continuously, without retraining a model."@en ] . :dimParadigmBridge a cdx:ComparisonDimension ; schema:name "Paradigm bridge"@en ; schema:description "The mechanism that carries computing from one paradigm to the next."@en ; schema:additionalProperty [ a schema:PropertyValue ; schema:name "Stratechery framing"@en ; schema:value "The application layer of one paradigm is the bridge to the next — generative AI is today's bridge."@en ], [ a schema:PropertyValue ; schema:name "Semantic Web reframing"@en ; schema:value "SQL + RDF Views + SPARQL bridge the relational silo to a Semantic Web, so data itself becomes the application layer."@en ] . :dimInterface a cdx:ComparisonDimension ; schema:name "Interface"@en ; schema:description "What the user actually touches to command the machine."@en ; schema:additionalProperty [ a schema:PropertyValue ; schema:name "Stratechery framing"@en ; schema:value "Pre-built UI is dead; agents and computer use replace the screen-by-screen app."@en ], [ a schema:PropertyValue ; schema:name "Semantic Web reframing"@en ; schema:value "The graph is the interface: a query replaces a screen, and a dereferenceable hyperlink is the affordance."@en ] . :dimAggregationMoat a cdx:ComparisonDimension ; schema:name "Aggregation moat"@en ; schema:description "Where durable advantage lives once everyone can build the same thing."@en ; schema:additionalProperty [ a schema:PropertyValue ; schema:name "Stratechery framing"@en ; schema:value "Own the agent users talk to; win with distribution and accumulated personal context."@en ], [ a schema:PropertyValue ; schema:name "Semantic Web reframing"@en ; schema:value "Own your graph's dereferenceable hyperlinks — a Platinum Layer that aggregates context without a walled app."@en ] . :dimAction a cdx:ComparisonDimension ; schema:name "From system to action"@en ; schema:description "The gap between building a system and actually doing the thing."@en ; schema:additionalProperty [ a schema:PropertyValue ; schema:name "Stratechery framing"@en ; schema:value "No matter how many systems you build, you still have to act — writing things down pales next to getting things done."@en ], [ a schema:PropertyValue ; schema:name "Semantic Web reframing"@en ; schema:value "Getting things done is the query the agent runs: SPARQL turns 'written down' into an action the graph can drive."@en ] . # ───────────────────────────────────────────────────────────────────────────── # 7. FAQ — FAQPage with ≥12 Questions and named Answers # ───────────────────────────────────────────────────────────────────────────── :faqSection a schema:FAQPage ; schema:name "Frequently Asked Questions — Stratechery × Semantic Web Meshup"@en ; schema:mainEntity :q1, :q2, :q3, :q4, :q5, :q6, :q7, :q8, :q9, :q10, :q11, :q12, :q13, :q14 . :q1 a schema:Question ; schema:name "What do these three Stratechery essays have in common?"@en ; schema:acceptedAnswer :a1 ; schema:isPartOf :faqSection . :a1 a schema:Answer ; schema:answer "All three describe the same move — offloading cognition to an external system. The Gen AI Bridge locates it in the application layer, Write Things Down locates it in a trusted bucket that empties working memory, and Apps, Agents, and Aggregation locates it in an agent that knows you. Each is a facet of writing things down so something else can act on them."@en . :q2 a schema:Question ; schema:name "What is the meshup's central thesis?"@en ; schema:acceptedAnswer :a2 ; schema:isPartOf :faqSection . :a2 a schema:Answer ; schema:answer "That Ben Thompson's trilogy is best realized on a Semantic Web substrate. Writing things down becomes asserting RDF triples; the trusted bucket becomes a named graph in a Virtuoso quad store; 'AI that learns continuously' becomes a knowledge graph that accumulates provenance; 'getting things done' becomes a SPARQL query; and aggregation without lock-in becomes a Platinum Layer of dereferenceable hyperlinks."@en . :q3 a schema:Question ; schema:name "Why map 'writing things down' onto RDF triples rather than prose notes?"@en ; schema:acceptedAnswer :a3 ; schema:isPartOf :faqSection . :a3 a schema:Answer ; schema:answer "Prose notes are searchable but not queryable: a computer cannot tell you which entities a note relates, or join two notes the way you would. An RDF triple makes each thing a named subject, each relationship a predicate, and each value an object — so an agent can retrieve, filter, and combine them with SPARQL exactly as you would reason over them yourself."@en . :q4 a schema:Question ; schema:name "What does Virtuoso contribute that a plain text file cannot?"@en ; schema:acceptedAnswer :a4 ; schema:isPartOf :faqSection . :a4 a schema:Answer ; schema:answer "Virtuoso is a converged quad store and relational database in one engine. A text file holds statements; Virtuoso indexes them, answers SQL and SPARQL over the same data, supports named graphs for provenance, applies RDFS/OWL inference, and serves them as Linked Data over HTTP — turning 'written down' into 'retrievable, joinable, and resolvable'."@en . :q5 a schema:Question ; schema:name "How does Ben Thompson define AGI, and why does he disagree with Jensen Huang?"@en ; schema:acceptedAnswer :a5 ; schema:isPartOf :faqSection . :a5 a schema:Answer ; schema:answer "Ben Thompson defines AGI as 'AI that learns continuously.' Jensen Huang declared GPT-6 Astra to be AGI, but a large language model is frozen after training — it does not keep learning — so by Ben's definition it does not qualify. The meshup observes that a continuously updated knowledge graph satisfies the definition without needing a new model."@en . :q6 a schema:Question ; schema:name "What is Aggregation Theory and how does it apply to agents?"@en ; schema:acceptedAnswer :a6 ; schema:isPartOf :faqSection . :a6 a schema:Answer ; schema:answer "Aggregation Theory holds that whoever owns the interface between suppliers and consumers captures the value. Applied to agents, the interface is the assistant you talk to: agents get better the more context they have about you, so most people will keep only one — and the winners will be Meta and Microsoft, who already have distribution to nearly every person and employee."@en . :q7 a schema:Question ; schema:name "What is the 'Platinum Layer' and why is it the meshup's answer to lock-in?"@en ; schema:acceptedAnswer :a7 ; schema:isPartOf :faqSection . :a7 a schema:Answer ; schema:answer "The Platinum Layer is Kingsley Idehen's extension of the medallion architecture: using dereferenceable hyperlinks as stable, standardized identifiers. If your graph is addressed by hyperlinks you control, your agent, context, and relationships are portable — you aggregate attention and context through identifiers rather than being locked into one vendor's walled app."@en . :q8 a schema:Question ; schema:name "What does 'pre-built UI is dead' mean, and what replaces it?"@en ; schema:acceptedAnswer :a8 ; schema:isPartOf :faqSection . :a8 a schema:Answer ; schema:answer "Ben Thompson argues we will not program computers, and eventually we will not even use them directly — AI will. Fixed, write-once-run-everywhere interfaces give way to natural language and computer use, where an agent drives the software on your behalf. The meshup's version: the graph is the interface, and a query replaces the screen."@en . :q9 a schema:Question ; schema:name "How does 'getting things done' become a query?"@en ; schema:acceptedAnswer :a9 ; schema:isPartOf :faqSection . :a9 a schema:Answer ; schema:answer "Ben Thompson hired an assistant to run his OmniFocus so he never had to open it. The meshup's assistant is an agent that issues a SPARQL query against your knowledge graph: the query is the formula that selects the next action from everything you wrote down, closing the loop from 'written down' to 'done'."@en . :q10 a schema:Question ; schema:name "What is the application layer 'bridge' and why does it matter for AI?"@en ; schema:acceptedAnswer :a10 ; schema:isPartOf :faqSection . :a10 a schema:Answer ; schema:answer "Ben Thompson shows that each computing paradigm — mainframe, PC, smartphone — hands off to the next through its application layer: the terminal bridged batch to interactive, the app bridged PC to phone. Generative AI matters because it is today's bridge: delivered through current apps while the product overhang from today's models builds the application layer of the next paradigm."@en . :q11 a schema:Question ; schema:name "Is this a comparison of competing products?"@en ; schema:acceptedAnswer :a11 ; schema:isPartOf :faqSection . :a11 a schema:Answer ; schema:answer "Not a product bake-off — a conceptual reframing. The comparison table restates six of Ben Thompson's concepts in the language of RDF, SPARQL, and Virtuoso, to show the insight is preserved while the substrate is upgraded from prose and walled apps to triples and dereferenceable hyperlinks."@en . :q12 a schema:Question ; schema:name "How can I explore this knowledge graph myself?"@en ; schema:acceptedAnswer :a12 ; schema:isPartOf :faqSection . :a12 a schema:Answer ; schema:answer "Use the Knowledge Graph Explorer below to browse entities and relationships, and the SPARQL Workbench to run live queries against the graph's named graph in URIBurner. Every visible entity — people, concepts, FAQ answers, and comparison dimensions — is a dereferenceable hyperlink resolved through URIBurner."@en . # ───────────────────────────────────────────────────────────────────────────── # 8. HOW-TO — seven steps with absolute IRIs (post: prefix) # ───────────────────────────────────────────────────────────────────────────── post:howTo a schema:HowTo ; schema:name "Build the Trusted Bucket: a Personal Knowledge Graph in Virtuoso"@en ; schema:description "Seven steps that turn Ben Thompson's 'write things down' into a live Semantic Web practice — from naming things with hyperlinks to acting on the graph."@en ; schema:step post:step1, post:step2, post:step3, post:step4, post:step5, post:step6, post:step7 ; schema:isPartOf <> . post:step1 a schema:HowToStep ; schema:position 1 ; schema:name "Name anything of interest with a hyperlink"@en ; schema:text "Before writing anything down, give each person, project, concept, and thing a stable IRI — a dereferenceable hyperlink. This is the move Tim Berners-Lee proved for documents and that RDF extends to everything else; the IRI is the 'name' a query will later use to find the note."@en ; schema:isPartOf post:howTo . post:step2 a schema:HowToStep ; schema:position 2 ; schema:name "Assert triples instead of prose"@en ; schema:text "Capture each thought as subject-predicate-object: who did what to whom, what relates to what. A prose paragraph becomes several triples, each independently queryable. This is 'writing things down' with the shape a machine can reason over."@en ; schema:isPartOf post:howTo . post:step3 a schema:HowToStep ; schema:position 3 ; schema:name "Store them in a named graph"@en ; schema:text "Load the triples into a named graph in a Virtuoso quad store. The named graph is David Allen's trusted bucket made concrete: an external store that outlives your context window, indexed for SQL and SPARQL, and traceable to who asserted each fact."@en ; schema:isPartOf post:howTo . post:step4 a schema:HowToStep ; schema:position 4 ; schema:name "Let the graph learn continuously"@en ; schema:text "Keep appending dated, provenance-bearing triples instead of retraining a model. A knowledge graph that accumulates with dateCreated and dateModified satisfies Ben Thompson's definition of AGI — it learns continuously, and every change is auditable."@en ; schema:isPartOf post:howTo . post:step5 a schema:HowToStep ; schema:position 5 ; schema:name "Read it back with SPARQL"@en ; schema:text "Issue SPARQL queries to retrieve, join, and filter what you wrote down. This is the assistant you never have to open: a query selects the next action, surfaces a relationship, or answers a question, turning 'written down' into 'getting things done'."@en ; schema:isPartOf post:howTo . post:step6 a schema:HowToStep ; schema:position 6 ; schema:name "Expose a Platinum Layer of dereferenceable hyperlinks"@en ; schema:text "Serve your graph as Linked Data so every entity resolves to its description. Stable hyperlinks aggregate context and identity without a walled app — your own interface, portable across agents, replacing the pre-built UI Ben Thompson declares dead."@en ; schema:isPartOf post:howTo . post:step7 a schema:HowToStep ; schema:position 7 ; schema:name "Act — a system is only as good as its outcomes"@en ; schema:text "No matter how many systems you build, you still have to act. The graph amplifies getting things done, but the coda of the Write Things Down essay holds: writing things down will always pale in comparison to doing the things."@en ; schema:isPartOf post:howTo . # ───────────────────────────────────────────────────────────────────────────── # 9. SPARQL RECIPES — schema:SoftwareSourceCode examples # ───────────────────────────────────────────────────────────────────────────── :sparqlSummary a schema:SoftwareSourceCode ; schema:name "Entity-type summary"@en ; schema:programmingLanguage "SPARQL"@en ; schema:codeSampleType "SPARQLQuery"@en ; schema:text """PREFIX rdf: PREFIX rdfs: SELECT ?typeIri (COUNT(?s) AS ?count) (SAMPLE(?label) AS ?sampleLabel) WHERE { GRAPH { ?s a ?typeIri . OPTIONAL { ?s rdfs:label ?label } } } GROUP BY ?typeIri ORDER BY DESC(?count)"""@en ; schema:target . :sparqlSources a schema:SoftwareSourceCode ; schema:name "The three source essays and their authors"@en ; schema:programmingLanguage "SPARQL"@en ; schema:codeSampleType "SPARQLQuery"@en ; schema:text """PREFIX schema: SELECT ?articleIri ?article ?authorIri ?author ?date WHERE { GRAPH { ?articleIri a schema:NewsArticle ; schema:name ?article ; schema:datePublished ?date ; schema:author ?authorIri . ?authorIri schema:name ?author . } } ORDER BY ?date"""@en ; schema:target . :sparqlClaims a schema:SoftwareSourceCode ; schema:name "Every claim in the meshup, with its author"@en ; schema:programmingLanguage "SPARQL"@en ; schema:codeSampleType "SPARQLQuery"@en ; schema:text """PREFIX schema: SELECT ?claimIri ?claim ?authorIri ?author WHERE { GRAPH { ?claimIri a schema:Claim ; schema:name ?claim ; schema:author ?authorIri . ?authorIri schema:name ?author . } } ORDER BY ?author ?claim"""@en ; schema:target . :sparqlComparison a schema:SoftwareSourceCode ; schema:name "Comparison dimensions and their two framings"@en ; schema:programmingLanguage "SPARQL"@en ; schema:codeSampleType "SPARQLQuery"@en ; schema:text """PREFIX schema: PREFIX cdx: SELECT ?dimIri ?dimension ?side ?value WHERE { GRAPH { ?dimIri a cdx:ComparisonDimension ; schema:name ?dimension ; schema:additionalProperty ?pv . ?pv schema:name ?side ; schema:value ?value . } } ORDER BY ?dimension ?side"""@en ; schema:target . :sparqlHowTo a schema:SoftwareSourceCode ; schema:name "The seven How-To steps, in order"@en ; schema:programmingLanguage "SPARQL"@en ; schema:codeSampleType "SPARQLQuery"@en ; schema:text """PREFIX schema: SELECT ?stepIri ?step ?position WHERE { GRAPH { ?stepIri a schema:HowToStep ; schema:name ?step ; schema:position ?position . } } ORDER BY ?position"""@en ; schema:target . :sparqlGlossary a schema:SoftwareSourceCode ; schema:name "Glossary terms and their definitions"@en ; schema:programmingLanguage "SPARQL"@en ; schema:codeSampleType "SPARQLQuery"@en ; schema:text """PREFIX schema: SELECT ?termIri ?term ?definition WHERE { GRAPH { ?termIri a schema:DefinedTerm ; schema:name ?term ; schema:description ?definition . } } ORDER BY ?term"""@en ; schema:target . # ───────────────────────────────────────────────────────────────────────────── # 10. AGENT MEMORY LAYER — agent-rdf-memory + OPAL (the trusted bucket, implemented) # ───────────────────────────────────────────────────────────────────────────── a schema:SoftwareApplication ; schema:name "agent-rdf-memory"@en ; schema:description "A loosely coupled memory and context layer for AI agents, informed by a Semantic Web: machine-computable entity relationships (identity in core.ttl, a queryable behavioral contract in preferences.ttl, episodic sessions, semantic entities, and procedural how-tos) are asserted in RDF and addressed by dereferenceable hyperlinks — the trusted bucket of the Write Things Down essay, implemented as a portable knowledge graph any agent can load."@en ; schema:url "https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/agent-rdf-memory" ; schema:isBasedOn ; schema:publisher . a schema:SoftwareApplication ; schema:name "OPAL — the OpenLink AI Layer"@en ; schema:description "OpenLink Software's AI-agent framework that composes loosely coupled pieces of the puzzle into any agent: AGENT.md behavioral bootstrap, SKILLS.md capability contracts, A2A (Agent2Agent) for agent-to-agent tasking, MCP for tools and context, and OpenAPI-compliant API specs — all over a Virtuoso-backed Semantic Web where entities and relationships are hyperlink-addressed."@en ; schema:url "https://www.openlinksw.com/opal/" ; owl:sameAs ; schema:isBasedOn ; schema:publisher . :memorySection a schema:CreativeWork ; schema:name "agent-rdf-memory — the trusted bucket, implemented"@en ; schema:description "How the Write Things Down essay becomes a real, loosely coupled memory and context layer: agent-rdf-memory as RDF, and OPAL as the runtime that composes AGENT.md, SKILLS.md, A2A, MCP, and OpenAPI into any agent."@en ; schema:about :claimMemoryLayer, :claimLooseCoupling, :claimOpal, , ; schema:isPartOf <> . :claimMemoryLayer a schema:Claim ; schema:name "agent-rdf-memory is the trusted bucket implemented"@en ; schema:text "The Write Things Down essay's hired assistant and trusted bucket exist today as agent-rdf-memory: an RDF memory harness where identity, preferences, sessions, and entities are machine-computable relationships informed by an ontology, all addressed by hyperlinks — memory and context any agent can load and query."@en ; schema:about ; schema:author . :claimLooseCoupling a schema:Claim ; schema:name "Loose coupling through open contracts"@en ; schema:text "Because agent-rdf-memory speaks RDF over hyperlinks and reads its contract from AGENT.md and SKILLS.md, it is a loosely coupled piece of the puzzle: it plugs into any agent that supports AGENT.md, SKILLS.md, A2A, MCP, and OpenAPI-compliant API specs — no rewrite, no lock-in."@en ; schema:about :looseCouplingConcept ; schema:author . :claimOpal a schema:Claim ; schema:name "OPAL composes the loosely coupled pieces"@en ; schema:text "The OpenLink AI Layer (OPAL) is the runtime that composes these loosely coupled pieces — memory, skills, models, tools, and APIs — into one agent over a Virtuoso-backed Semantic Web."@en ; schema:about ; schema:author . :looseCouplingConcept a schema:DefinedTerm ; schema:name "Loose Coupling"@en ; schema:description "Composing independent, swappable pieces through open contracts instead of a monolith — the design principle that lets a memory layer, a skill, a model, and a tool plug into any agent."@en ; schema:inDefinedTermSet :glossarySection . :agentMemoryConcept a schema:DefinedTerm ; schema:name "Agent Memory"@en ; schema:description "Durable, queryable memory for an AI agent — identity, preferences, episodic sessions, and entities stored as RDF and retrieved by SPARQL instead of held only in a context window."@en ; schema:inDefinedTermSet :glossarySection . :a2aConcept a schema:DefinedTerm ; schema:name "A2A (Agent2Agent)"@en ; schema:description "A protocol for one agent to delegate tasks to another across boundaries — a loose-coupling connector in the agentic stack."@en ; schema:inDefinedTermSet :glossarySection . :agentMdConcept a schema:DefinedTerm ; schema:name "AGENT.md"@en ; schema:description "A project-level instruction file that bootstraps an agent's operating rules — the entry point through which an RDF memory protocol and a skill contract are injected."@en ; schema:inDefinedTermSet :glossarySection . :skillsMdConcept a schema:DefinedTerm ; schema:name "SKILLS.md"@en ; schema:description "A capability contract that declares what a skill does and when to invoke it — a reusable, loosely coupled unit of agent capability."@en ; schema:inDefinedTermSet :glossarySection . :openapiConcept a schema:DefinedTerm ; schema:name "OpenAPI Specification"@en ; schema:description "A machine-readable contract for HTTP APIs — the spec that makes a service discoverable and callable by any compliant agent or tool."@en ; schema:inDefinedTermSet :glossarySection . a schema:DefinedTerm ; schema:name "Model Context Protocol (MCP)"@en ; schema:description "An open protocol for exposing tools, resources, and prompts to AI agent clients — the de facto standard for AI-to-tool communication."@en ; schema:inDefinedTermSet :glossarySection . a schema:DefinedTerm ; schema:name "Ontology"@en ; schema:description "A formal vocabulary of classes and relationships that gives a knowledge graph its meaning — the shared schema that keeps machine-computable relationships consistent across agents."@en ; schema:inDefinedTermSet :glossarySection . a schema:DefinedTerm ; schema:name "Linked Data"@en ; schema:description "Publishing structured data so it can be interlinked across the Web via dereferenceable hyperlinks — the connectivity this meshup's memory layer is built on."@en ; schema:inDefinedTermSet :glossarySection . :dimMemory a cdx:ComparisonDimension ; schema:name "Memory substrate"@en ; schema:description "Where an agent keeps what it knows about you between turns."@en ; schema:additionalProperty [ a schema:PropertyValue ; schema:name "Stratechery framing"@en ; schema:value "Hire an assistant to run your OmniFocus, or trust a human to be your Inbox and task manager."@en ], [ a schema:PropertyValue ; schema:name "Semantic Web reframing"@en ; schema:value "agent-rdf-memory: an RDF knowledge graph the agent queries with SPARQL — a loosely coupled memory layer that plugs into any agent."@en ] . :q13 a schema:Question ; schema:name "What is agent-rdf-memory, and how does it realize the trusted bucket?"@en ; schema:acceptedAnswer :a13 ; schema:isPartOf :faqSection . :a13 a schema:Answer ; schema:answer "agent-rdf-memory is an RDF-based memory and context harness — the public GitHub project at github.com/OpenLinkSoftware/ai-agent-skills/tree/main/agent-rdf-memory. It stores identity, a queryable behavioral contract, episodic sessions, and semantic entities as RDF triples addressed by hyperlinks, informed by an ontology. That is David Allen's trusted bucket — and Ben Thompson's hired assistant — made machine-computable: the agent writes things down as triples and reads them back with SPARQL instead of holding everything in a context window."@en . :q14 a schema:Question ; schema:name "What is OPAL, and how does it compose AGENT.md, SKILLS.md, A2A, MCP, and OpenAPI?"@en ; schema:acceptedAnswer :a14 ; schema:isPartOf :faqSection . :a14 a schema:Answer ; schema:answer "OPAL — the OpenLink AI Layer — is OpenLink Software's agent framework for composing loosely coupled pieces into any agent. AGENT.md bootstraps behavior, SKILLS.md declares reusable capabilities, A2A lets agents delegate to one another, MCP exposes tools and context, and OpenAPI-compliant specs make any service callable. Because each piece is a swappable contract over a Virtuoso-backed Semantic Web, a memory layer like agent-rdf-memory plugs in without lock-in."@en . # ───────────────────────────────────────────────────────────────────────────── # 11. THE MESSAGE AND THE EVOLVING MEDIUM — intent → document, via open standards # ───────────────────────────────────────────────────────────────────────────── :messageMediumSection a schema:CreativeWork ; schema:name "The Message and the Evolving Medium"@en ; schema:description "An animated illustration of how an intention — fundamentally a CRUD operation — reaches its target document without distraction, courtesy of open standards. The medium (HTTP/RDF/SPARQL/WebID/ACL/agent protocols) is the message: its frictionless smoothness is what carries intent to content in one unbroken hop."@en ; schema:about :intentConcept, :crudConcept, :capabilityConcept, :authorizationConcept, :writtenRecordConcept, :claimMediumIsMessage ; schema:isPartOf <> . :claimMediumIsMessage a schema:Claim ; schema:name "The medium is the message"@en ; schema:text "McLuhan's point, restated for the Semantic Web: as open-standards adoption broadened, the medium became so frictionless that its smoothness is the message. An intention — fundamentally a CRUD operation — now reaches content in a document in one standard-mediated hop, without the distraction of proprietary relays."@en ; schema:about :intentConcept ; schema:author . :intentConcept a schema:DefinedTerm ; schema:name "Intent"@en ; schema:description "A named goal — the 'what' a job is for. Underneath, every intent is fundamentally a CRUD operation on content in a document."@en ; schema:inDefinedTermSet :glossarySection . :crudConcept a schema:DefinedTerm ; schema:name "CRUD"@en ; schema:description "Create, Read, Update, Delete — the four operations every intention ultimately reduces to when it reaches a document."@en ; schema:inDefinedTermSet :glossarySection . :createVerb a schema:DefinedTerm ; schema:name "CREATE"@en ; schema:description "The CRUD verb that inserts new content into a document."@en . :readVerb a schema:DefinedTerm ; schema:name "READ"@en ; schema:description "The CRUD verb that retrieves content from a document."@en . :updateVerb a schema:DefinedTerm ; schema:name "UPDATE"@en ; schema:description "The CRUD verb that mutates existing content in a document."@en . :deleteVerb a schema:DefinedTerm ; schema:name "DELETE"@en ; schema:description "The CRUD verb that removes content from a document."@en . :capabilityConcept a schema:DefinedTerm ; schema:name "Capability"@en ; schema:description "What a fit-for-purpose agent can do — its skills and tools, declared via SKILLS.md and exposed through MCP — the 'can' that shapes an intention into executable work."@en ; schema:inDefinedTermSet :glossarySection . :authorizationConcept a schema:DefinedTerm ; schema:name "Authorization"@en ; schema:description "Who may do what — identity (WebID) plus per-resource access control (WebACL) gate every CRUD operation, so the agent acts only within what is allowed."@en ; schema:inDefinedTermSet :glossarySection . :writtenRecordConcept a schema:DefinedTerm ; schema:name "Written Record"@en ; schema:description "Durable context carried forward — what gets written down as RDF triples so the next hop has the useful context it needs, the write-things-down loop made machine-computable."@en ; schema:inDefinedTermSet :glossarySection . :webidConcept a schema:DefinedTerm ; schema:name "WebID"@en ; schema:description "A decentralized identity mechanism: a dereferenceable profile document, often paired with an X.509 certificate, that makes a person or agent its own authority."@en ; schema:inDefinedTermSet :glossarySection . :aclConcept a schema:DefinedTerm ; schema:name "WebACL"@en ; schema:description "Web Access Control — per-resource authorization (read, write, append, control) for resources on the Web."@en ; schema:inDefinedTermSet :glossarySection . :httpConcept a schema:DefinedTerm ; schema:name "HTTP"@en ; schema:description "Hypertext Transfer Protocol — the application protocol of the Web; the wire over which hyperlinks, RDF, and SPARQL all travel."@en ; schema:inDefinedTermSet :glossarySection .