The Semantic Intelligence Platform Pronounced /koʊˈdʒɛnɪti/ or in simpler terms: koh-JEN-uh-teehttps://bsky.app/profile/coginiti.cohttps://bsky.app/profile/coginiti.co/post/3mzlc5er74y2oCoginiti 26.10 imports Apache Ossie models as native semantic entities and exports Coginiti models as Ossie. Semantic definitions can now move in and out of Coginiti in an open, vendor-neutral format. https://coginiti.co/blog/coginiti-26-10-release-notes/05 Nov 2026 16:31 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mzlc5er74y2ohttps://bsky.app/profile/coginiti.co/post/3mzirokyujt2vCoginiti 26.10: the MCP server adds OAuth, catalog write tools and admin-set result limits, and the semantic layer gets domain-level permissions. Agents can do more, inside boundaries you set. https://coginiti.co/blog/coginiti-26-10-release-notes/04 Nov 2026 16:31 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mzirokyujt2vhttps://bsky.app/profile/coginiti.co/post/3mzg5sn4a6a2gCoginiti 26.10 is out: Analytics Playbooks, unified lineage from source transformation to published metric, domain-level semantic permissions, Apache Ossie import and export, and Forge authoring the semantic layer. https://coginiti.co/blog/coginiti-26-10-release-notes/03 Nov 2026 15:30 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mzg5sn4a6a2ghttps://bsky.app/profile/coginiti.co/post/3mz3ymy54r22cThings that go bump below the semantic layer: zombie metrics, phantom rows from fan traps, haunted pipelines, metrics with no owner. Happy Halloween from Coginiti.30 Oct 2026 14:31 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mz3ymy54r22chttps://bsky.app/profile/coginiti.co/post/3myzi5twxwj2jGartner warns about overprivileged agents. Fair. The quieter failure sits next to it: the under-informed agent, fully authorized, reading context nobody checked. A query can be authorized and still be wrong.29 Oct 2026 14:31 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3myzi5twxwj2jhttps://bsky.app/profile/coginiti.co/post/3mywxpdz46s2cContext without tests is a confident guess. A metric can pass every column test and still mean the wrong thing. If agents act on your definitions, the definitions need tests too.28 Oct 2026 14:31 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mywxpdz46s2chttps://bsky.app/profile/coginiti.co/post/3myuhaszld22vGartner says organizations that prioritize semantics in AI-ready data will see up to 80% better agent accuracy by 2027. Note the verb. Not buy. Not install. Prioritize.27 Oct 2026 14:31 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3myuhaszld22vhttps://bsky.app/profile/coginiti.co/post/3myrwqrqtmd2jGartner put AI Context Platforms on its 2027 trends list. Short version: meaning is infrastructure now. Infrastructure gets tested, versioned, reviewed and monitored. Context should too.26 Oct 2026 14:30 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3myrwqrqtmd2jhttps://bsky.app/profile/coginiti.co/post/3mykein4jdv2eAsk a question, get an answer, build an agent. That's the tip. An agent's answer is only as trustworthy as its definitions, and those are only as trustworthy as everything underneath. Trust lives below the waterline. https://coginiti.co/blog/semantic-layer-tip-of-the-iceberg/23 Oct 2026 14:15 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mykein4jdv2ehttps://bsky.app/profile/coginiti.co/post/3myfdkiqw7r2oSemantic layer vendors are building up: NL interfaces, agents, viz, APIs. Sensible. Also all above the waterline. Coginiti builds down too: transformation, testing, lineage, review, deployment, and audit, in the same platform as the semantic layer.21 Oct 2026 14:15 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3myfdkiqw7r2ohttps://bsky.app/profile/coginiti.co/post/3myacmlqk3q2uA source team renames a column. A transform changes how refunds are handled. Both change what "revenue" means to every agent that asks tomorrow. Lineage from source to semantic definition is how you find out before the board deck does.19 Oct 2026 14:15 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3myacmlqk3q2uhttps://bsky.app/profile/coginiti.co/post/3mxwaqtvui32iAgents querying raw tables bill twice: once in tokens, once in warehouse compute. Through a governed semantic layer, customers have seen token spend fall by as much as 70%. The messier the source schema, the bigger the gap. The savings come from the modeling underneath.15 Oct 2026 14:15 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mxwaqtvui32ihttps://bsky.app/profile/coginiti.co/post/3mxr7sr7vl42qBelow the semantic layer: modeling, transformation, testing, lineage, versioning, review, governance, orchestration, deployment, monitoring. None of it disappears when you add a semantic layer. Agents just make it obvious when it's missing.13 Oct 2026 14:15 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mxr7sr7vl42qhttps://bsky.app/profile/coginiti.co/post/3mxeq3y62dl2wRichard Hall's Big Data LDN talk is now on YouTube. "The Context Stack": semantic models, ontologies and context engineering get sold as interchangeable. They solve different problems, and picking the wrong one first is expensive. 30 minutes on which is which. https://youtu.be/Z1hiw9mmvQU08 Oct 2026 15:02 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mxeq3y62dl2whttps://bsky.app/profile/coginiti.co/post/3mwbjo2wdmw2lLast few hours at Big Data LDN. Stand E34 until close. If you caught either talk and want to see the ideas running rather than described, there's a live environment on the stand and no queue at this hour. #BigDataLDN24 Sep 2026 15:03 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mwbjo2wdmw2lhttps://bsky.app/profile/coginiti.co/post/3mwbaqgsp6y2d"Semantic layers are too rigid for AI" The opposite. The more probabilistic the interface, the more it needs a deterministic contract underneath. Without one, the same question gives different answers by prompt wording or model version. https://coginiti.co/blog/semantic-layers-agents-fud/24 Sep 2026 12:24 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mwbaqgsp6y2dhttps://bsky.app/profile/coginiti.co/post/3mwaw6pbh7t2qDay two, 25 minutes out. AI Context Theatre, 10:40. Richard Hall on what semantic models, ontologies and context engineering each actually do, and when to reach for which. Stand E34 after. #BigDataLDN24 Sep 2026 09:15 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mwaw6pbh7t2qhttps://bsky.app/profile/coginiti.co/post/3mw6fpnbijb2zStarting in 25 minutes. Lightning Talks Theatre, 10:40. Matthew Mullins on context, governance and cost control for AI agents. Stand E34 after. #BigDataLDN23 Sep 2026 09:15 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mw6fpnbijb2zhttps://bsky.app/profile/coginiti.co/post/3mw47slny762s"Nobody agrees on the definitions anyway." That's the point. Disagreement is the reason semantic layers exist. Without one, four teams' definitions of "customer" get encoded silently into dashboards and queries. With one, disagreement becomes a governed decision. https://coginiti.co/blog/semantic-layers-agents-fud/22 Sep 2026 12:24 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mw47slny762shttps://bsky.app/profile/coginiti.co/post/3mvzuvolxay25Big Data LDN this week. Stand E34, both days. Wed 23rd, 10:40, Lightning Talks Theatre: Matthew Mullins, Not Your Mum's Semantic Layer. Thu 24th, 10:40, AI Context Theatre: Richard Hall, The Context Stack. Still time to register free. #BigDataLDN https://www.bigdataldn.com/en-gb/register.html?code=1718125174025894-MKP21 Sep 2026 14:03 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mvzuvolxay25https://bsky.app/profile/coginiti.co/post/3mvpwdva6al2zNobody budgets for the tokens an agent spends finding its way around. Lists tables. Samples rows. Tries a join, fails, tries another. Then rediscovers the whole schema on the next question. Token spend is an architecture problem. #BigDataLDN #FinOps17 Sep 2026 15:02 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mvpwdva6al2zhttps://bsky.app/profile/coginiti.co/post/3mvpnhzth6n2b"Semantic layers are only useful after the data is perfect." The perfection trap. Nobody has perfect data, and waiting for it means waiting forever. The semantic layer is part of how you make data usable. Start with the metrics that matter most, not day-one everything. https://coginiti.co/blog/semantic-layers-agents-fud/17 Sep 2026 12:24 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mvpnhzth6n2bhttps://bsky.app/profile/coginiti.co/post/3mvkvhugqxj2sThe failure mode of an agent on raw schemas isn't that it breaks. It's that it succeeds. Counterintuitive right? The agent returns some number. Correctly formatted, plausible, wrong, because it picked orders.amount and you define revenue net of returns. Nobody catches it. #BigDataLDN15 Sep 2026 15:03 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mvkvhugqxj2shttps://bsky.app/profile/coginiti.co/post/3mvkmk7xr3y2s"We can solve this with prompt engineering." A prompt that says "use approved revenue" is not a governed revenue measure enforced in the execution path. Prompts are hard to audit, version, and test. Prompts guide behavior. A semantic layer governs meaning. https://coginiti.co/blog/semantic-layers-agents-fud/15 Sep 2026 12:24 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mvkmk7xr3y2shttps://bsky.app/profile/coginiti.co/post/3mv6d6a37cs26An analyst joining your company gets onboarding and a colleague to ask. An agent gets a connection string. No institutional memory, nobody to ask, machine speed. When it guesses wrong about revenue it does so confidently and at scale. #BigDataLDN #AIAgents10 Sep 2026 15:04 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mv6d6a37cs26https://bsky.app/profile/coginiti.co/post/3mv627lbruy2b"Governance kills agent autonomy." A self-driving car still needs traffic laws and lane markings. Let agents explore freely. But when one answers an enterprise metric question, it shouldn't invent the definition. Autonomy to explore, governed semantics to answer. https://coginiti.co/blog/semantic-layers-agents-fud/10 Sep 2026 12:24 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mv627lbruy2bhttps://bsky.app/profile/coginiti.co/post/3mv3n63gars2uAgents stopped failing at SQL. For the strongest model tested, 60%+ of remaining failures were semantic: wrong metric, wrong source, wrong join key. New research on what survives as models absorb the stack. https://coginiti.co/blog/model-eats-the-stack-semantic-context/09 Sep 2026 13:25 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mv3n63gars2uhttps://bsky.app/profile/coginiti.co/post/3muzc5oojyg2nSemantic model. Ontology. Context engineering. Three terms used interchangeably by people selling three different things. Richard Hall sorts them out at Big Data LDN. AI Context Theatre, Thu 24 Sept, 10:40. What each one does, and when it doesn't. #BigDataLDN08 Sep 2026 15:02 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3muzc5oojyg2nhttps://bsky.app/profile/coginiti.co/post/3muyzbqu3bb2d"It's just an old BI idea with new marketing." The idea is decades old. That's a strength. What changed is the number of consumers: agents, notebooks, workflows, embedded apps, decision systems. AI multiplied the systems that need governed access to meaning. https://coginiti.co/blog/semantic-layers-agents-fud/08 Sep 2026 12:24 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3muyzbqu3bb2dhttps://bsky.app/profile/coginiti.co/post/3mumpt6lf4t2mFor 20 years the semantic layer was a BI convenience. Friendly names so nobody had to remember which table held revenue. That was built for humans clicking dashboards. The user has changed. Matthew Mullins, Big Data LDN, Wed 23 Sept 10:40, Lightning Talks Theatre. #BigDataLDN03 Sep 2026 15:02 +0000at://did:plc:giu5o7uzub4qsjdxjipiizem/app.bsky.feed.post/3mumpt6lf4t2m