Tag
Graphene is an open-source, everything-as-code data analytics framework designed for coding agents, featuring a SQL-based semantic layer and a dashboard file type for faster data exploration and visualization.
Geom, a startup founded by Shanna Tellerman, launches an AI tool that automates architectural drafting for production-scale homebuilding, integrating with existing CAD workflows to produce permit-ready construction documents.
This paper presents an end-to-end framework for automating the construction of a business semantic layer from raw telemetry data using hierarchical LLM inference and RAG abstraction, significantly improving semantic quality and reducing maintenance effort.
WrenAI is an open-source generative BI engine that allows users to ask questions in natural language to generate SQL, charts, and analysis results, and it features a semantic layer to enhance accuracy.
Ramp developed a semantic layer to attribute AI agent spend to objectives and outcomes, moving from monitoring spend to understanding AI ROI.
This webinar provides a practical engineering-focused approach to building a semantic layer on Neo4j using ontology, emphasizing benefits for AI-driven applications and data consistency.
The paper introduces GROUND, a governed semantic-retrieval framework that constrains LLM-generated analytics to approved business definitions, effectively reducing hallucinations in enterprise data analysis while ensuring compliance with security and data policies.
Replit CEO Amjad Masad describes building a self-driving, self-correcting shared semantic layer over databases, conversations, and docs, making all data queryable and joinable so anyone at Replit can ask complex questions without data scientists.
The article discusses the need for a semantic coordination layer to enable multi-agent systems to collaborate effectively, and introduces Outshift's 'Internet of Cognition' and the open-source project AGNTCY as steps toward distributed artificial superintelligence.
GreptimeDB introduces a semantic layer that preserves OTLP metadata (instrument kind, unit, temporality) which is normally discarded at ingestion, enabling AIOps tools and LLM agents to understand system topology without guessing from column names.
A CIO shares observations on the challenges of applying semantic layers and ontologies to enterprise AI agents, highlighting the need for dynamic context selection, continuous evolution of institutional knowledge, and representing judgment rather than just static facts.
This paper presents a semantic-layer-mediated NL2SQL agent that decouples intent from physical execution by reasoning over a curated semantic model, achieving 94.15% execution accuracy on the Spider2-snow benchmark.
A pattern for giving AI agents reliable access to data warehouses by using a curated semantic layer (Databricks Genie) instead of raw text-to-SQL, improving accuracy and governance. The agent calls Genie's Conversation API as a tool, receiving both natural-language responses and exact SQL.
LUMOS introduces a semantic interaction layer that converts operating system metadata into machine-readable formats, enabling AI agents to interact with computer interfaces more efficiently by reducing dependence on screenshots and visual methods.
Introduces GATE (Grounding After Test from Execution), a method that bootstraps missing semantic groundings from execution feedback to handle under-specified user phrases in text-to-SQL tasks, consistently improving over strong baselines.
A developer describes the challenge of deploying AI agents in environments where business context is spread across multiple tools with conflicting definitions, and asks the community for solutions beyond manual reconciliation.
This article advises on improving ChatGPT's data analysis accuracy by grounding it in a semantic layer through data plugins, which can be built from scratch or integrated with existing systems like Snowflake Cortex and Databricks Genie, requiring sustained organizational commitment.