And now for something completely different: talk to your ontology! 🐍
Claude explores and extends it with you over MCP, with dry runs and undo. No generated slop.
OrionBelt Ontology Builder 1.33 👇
medium.com/@irregularbi/and-…
#Ontology #KnowledgeGraph #SemanticWeb #MCP #AIAgents
🤖 Made with AI
59
And now for something completely different: talk to your ontology! 🐍
I won't let an LLM write my ontology. But letting Claude read, query and extend one with me over MCP, with dry runs and undo? Surprisingly useful.
OrionBelt Ontology Builder 1.33 👇
medium.com/@irregularbi/and-…
71
🚀 OrionBelt Semantic Layer 3.0 brings one semantic model across eight SQL dialects, spanning cloud and on-premise systems.
medium.com/@irregularbi/one-…
#SemanticLayer #DataEngineering #DataFederation #AlAgents #OrionBelt
1
82
Last year at Connected Data London a chat with @juansequeda inspired me to roll my own Protégé, which is n also a year old: OrionBelt Ontology Builder
Let's see if I can get some feedback here!
Recently I optimized it for larger files
#CDL26 #OrionBelt #Ontology #KnowledgeGraphs
1
3
88
I just published Your MCP Server Has a Token Tax. mcp-xray tells you exactly how much. medium.com/p/your-mcp-server…
2
80
Who said vibe coding "on the weekend" (the city never sleeps) can't be fun? Now I have also added a full OrionBelt-Dremio-in-the-loop demo in the actual v2.11 release to show how the OrionBelt Semantic Sidecar can work
lnkd.in/dvTnSuMd
#semanticsidecar #orionbelt #dremio
2
85
Freshness-driven result cache is now shipped with OrionBelt Semantic Layer v2.2.0:
github.com/ralfbecher/orionb…
🤖 Made with AI
2
1
69
Every semantic-layer cache I've seen declares freshness in the wrong place. On the cube. On the saved query. On the datagroup. Not on the source table, which is the only place where refresh actually happens.
medium.com/p/freshness-inher…
72
🚀 MCP sampling now live in OrionBelt Chat v1.1.4 ↔ OrionBelt Analytics v1.5.0.
Official MCP clients matrix: 17 of 113 support sampling. Claude Desktop, ChatGPT, Cursor, Cline, Windsurf, none of them. But we do.
Jebi ga, finally. :D
github.com/ralfbecher/orionb…
#MCP #AgenticAI
1
79
Spent the week writing something nobody asked for: 5 honest comparison pages for OrionBelt Semantic Layer vs dbt, Malloy, LookML, Cube, AtScale.
Each includes a “what OBSL is missing” section — all-green vendor matrices are useless.
ralforion.com/orionbelt-sema…
1
1
56
MetaDada retweeted
🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length.
🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models.
🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice.
Try it now at chat.deepseek.com via Expert Mode / Instant Mode. API is updated & available today!
📄 Tech Report: huggingface.co/deepseek-ai/D…
🤗 Open Weights: huggingface.co/collections/d…
1/n
MetaDada retweeted
Watchdogs say the previous CEO model suspiciously started slowing down immediately after the announcement
Unified Star Schema: I think this concept is outdated in the agentic AI world:
linkedin.com/feed/update/urn…
#agenticai #analytics #businessintelligence
58
🚀 Reaching the next level in AI-Powered Analytics.
Combining schema discovery, ontology-based knowledge modeling, semantic enrichment, and GraphRAG, so AI doesn't just query your data, it ✨ *understands your database*. medium.com/p/orionbelt-analy…
96















