Composable Analytics: Agent-Built Views, Governed Metrics
Composable analytics lets agents assemble HTML dashboards from governed metrics. See how reusable definitions support generated views and fixed reports.
Read the storyIdeas for a context-aware data stack.
Field notes, product updates, and practical guides from the team building Datus.
In the spotlight
Latest stories
Newest first · by publication date111 stories
Convert Semantic Models to Ossie: Cube, dbt and More
Convert semantic models to Ossie from Cube, dbt, Omni and Power BI. Try ready-made examples, prepare complete source files, and validate the resulting YAML.
Read the story
AI Dashboards: Is the Dashboard Dead?
What is an AI dashboard? See how agents turn a question into a visual report, where semantic metrics keep it consistent, and when fixed dashboards still win.
Read the story
Entity-Attribute-Value (EAV) Model: Examples and Tradeoffs
Learn how the entity-attribute-value (EAV) model stores flexible fields, where analytics counts go wrong, and how to prepare a reliable semantic model.
Read the story
Business Glossary vs Semantic Layer: From Terms to SQL
Business glossary vs semantic layer: see how approved terms become tested metrics. Follow one active-customer example from wording to SQL and agent answers.
Read the story
DOSI 0.1.13 + Datus Agent 0.4.3: Getting the Level of Detail Right
DOSI 0.1.13 adds level of detail calculations for governed metrics, while Datus Agent 0.4.3 brings DOSI into its workflow and adds SQL lineage analysis.
Read the story
Apache Ossie Converters: YAML to dbt, Cube and More
Use Apache Ossie converters to export semantic model YAML to dbt, Cube, Snowflake and more. Try examples, inspect output files, and check conversion limits.
Read the story
Ontology for AI Agents: Five Approaches to Business Context
Explore five approaches to ontology for AI agents, from semantic layers and open standards to knowledge graphs and operational models, with a selection guide.
Read the story
Semantic Model Examples: A Working Apache Ossie Model
See semantic model examples for revenue, customer regions, and average order value. Download a tested Apache Ossie YAML model and check its answers yourself.
Read the story
What Is Headless BI? Shared Metrics Beyond Dashboards
Headless BI separates business metrics from dashboards so apps and AI agents can use them too. Learn when it helps, where it breaks, and how to test it.
Read the story
What Is Conversational BI? From Questions to Trusted Metrics
Conversational BI lets people explore data through follow-up questions. Learn how semantic models preserve metrics, filters, and trust across every turn.
Read the story
Datus September Update: The Semantic Layer in the Agent Loop
Datus's September 2026 update: putting the semantic layer in the agent loop as a deterministic checker, plus Datus Agent 0.4.2 and Dosi 0.1.12 release notes.
Read the story
What Is Agentic Analytics? Why It Needs a Semantic Layer
Agentic analytics uses AI agents to plan and act on data, not just answer questions. See how it differs from conversational BI and needs governed metrics.
Read the story
Cube.dev Alternatives: Stay for Speed or Choose Portability?
Compare Cube.dev alternatives by use case: keep Cube for embedded analytics, use dbt for governed metrics, or use Ossie and Dosi for portable agent queries.
Read the story
Why Text-to-SQL Fails Without a Semantic Layer
Text-to-SQL breaks on real warehouses because the model guesses what your data means. See why NL2SQL fails and how a semantic layer fixes accuracy.
Read the story
Semantic-Layer-Based Ontology: Agent Context on Apache Ossie
A semantic-layer-based ontology starts from governed metrics and relationships, then builds entity context and concept paths for AI agents on Apache Ossie.
Read the story
From Semantic Layer to Ontology: Architecture for AI Agents
AI data agents need more than metrics and more than a glossary. Learn how to build an ontology, an entity plane and typed query functions on a semantic layer.
Read the story
Semantic Layer vs Ontology: Why AI Agents Need Both
Semantic layer vs ontology is the wrong final question. See why AI data agents need both — governed metrics first, then ontology and agent context on top.
Read the story
What Makes a Semantic Layer Truly AI-Native?
Why we built Dosi: an AI-native semantic layer is an open spec plus a deterministic planner, compiler and runtime, plus an agent-native tool interface.
Read the story
Apache Ossie + Dosi: A 10-Minute Semantic Layer for Your AI Agent
A 10-minute Apache Ossie + Dosi quick start: install Dosi, query a 191K-row DuckDB dataset from the CLI, connect it to Claude Code over MCP, and ask why revenue dropped.
Read the story
Dosi with Cube: OSI Execution and Agentic Analytics in One Stack
How Dosi with Cube stacks API-first semantic serving with OSI-native multi-dialect SQL execution — complementary layers for agents and warehouses.
Read the story
Dosi vs MetricFlow: OSI-Native vs dbt-Centric Runtime
Compare Dosi and dbt MetricFlow as execution engines: same OSI interchange can feed dbt graph runtime or OSI-native multi-dialect compile — when to use each.
Read the story
Dosi MCP Semantic Layer for Agents — No SQL Guessing
How agents query governed OSI metrics via Dosi MCP: structured error codes, Claude Code and Codex patterns, and why semantic MCP beats raw SQL.
Read the story
Why OSI Needs an Execution Engine — Interchange vs Runtime
OSI (Apache Ossie) defines portable semantic metadata, not query execution. Learn the interchange-vs-runtime gap and why native OSI engines matter.
Read the story
Data Agents Need a Better Sandbox Than a Container
Read-only data agents answer questions; write agents deliver work. That needs plugins, permission modes, and a sandbox with checkpoint, branch and merge.
Read the story
First Native Apache Ossie Engine
What a native Apache Ossie (incubating) implementation is, how a native Apache Ossie engine differs from OSI converters, and why execution engines like Dosi matter for portable semantics.
Read the story
What Is the Claude Data Plugin? SQL, Charts & Warehouse MCP
What Anthropic's Data plugin is: Cowork and Claude Code workflows for SQL, charts, and dashboards — plus how it differs from Genie and Cortex Analyst.
Read the story
Introducing Dosi: OSI-Native Semantic Layer for Metrics
Dosi compiles Apache Ossie (OSI) YAML into SQL across 15+ warehouse dialects — CLI, REST, MCP, and Python — so metrics are defined once and used everywhere.
Read the story
What Is Cortex Analyst? Snowflake Natural-Language SQL for BI
What Cortex Analyst is: Snowflake's managed text-to-SQL API grounded in Semantic Views — verified queries, REST integration, and why it is not Cortex Code.
Read the story
What Is Databricks Genie? Agents for Conversational Analytics
What Databricks Genie is: domain-scoped agents (formerly Spaces) that answer with SQL and charts under Unity Catalog — and how they differ from Genie Code.
Read the story
What Is AtScale? Enterprise Semantic Layer for BI, Excel & AI
Virtual OLAP for Excel, Power BI, and agents — AtScale's SML, DSO pricing, MDX/DAX, and MCP, and when the cube is the wrong unit.
Read the story
What Is Timbr? Ontology-Based Semantic Layer Built on SQL
What Timbr.ai is: a SQL-native ontology over your warehouse — how it differs from Cube and AtScale, and when the extra layer is worth it.
Read the story
The Datus OSI Semantic Adapter: OSI In, MetricFlow Out
The Datus OSI (Apache Ossie) semantic adapter authors vendor-neutral YAML, validates it, and queries metrics via MetricFlow without leaking backend fields into source models.
Read the story
Introducing Datus Knowledge: The Memory Layer for Data Engineering Agents
Datus Knowledge stores schema, semantic models, metrics, reference SQL, templates, and platform docs so a data engineering agent retrieves meaning — not a schema dump.
Read the story
Introducing Datus Subagents: Specialized Workers for SQL and KPIs
Datus 0.3 ships built-in task subagents. AskMetrics answers KPIs from governed metrics; gen_sql and explore handle SQL and schema — not one universal chat.
Read the story
What Is an Ontology? Definition, Three Productizations & AI Agents
Ontology in data and AI: classes, relationships, and rules — and the three productizations buyers confuse in 2026: OWL/RDF, Palantir, and SQL ontologies.
Read the story
Apache Ossie (OSI) vs Cube: Headless Semantic Layer Meets Open Standard
Apache Ossie (formerly Open Semantic Interchange, OSI) vs Cube: open standard meets headless semantic layer — format, execution, governance, AI access.
Read the story
Apache Ossie (OSI) vs RDF/OWL: Two Generations of Semantics Compared
Apache Ossie (formerly Open Semantic Interchange, OSI) vs RDF/OWL: how formal Semantic Web ontologies differ from lightweight YAML interchange.
Read the story
From ChatBI to Data Agent: What Changes and What Doesn't
A year of building Datus: models, frameworks and interfaces change fast, but building and maintaining good context is still the hardest part of a data agent.
Read the story
Semantic vs Syntactic Interoperability: Difference & Why It Matters
Syntactic interoperability is shared format; semantic interoperability is shared meaning. See the difference, failure modes, and why it matters for AI agents.
Read the story
Apache Ossie (OSI) vs Warehouse-Native Semantics: Snowflake and Databricks Compared
Apache Ossie (formerly Open Semantic Interchange, OSI) vs warehouse-native semantics: Snowflake, Databricks, portability, lock-in, and AI grounding.
Read the story
Apache Ossie (OSI) vs LookML: Can Open Standards Replace Looker's Modeling Language?
Apache Ossie (formerly Open Semantic Interchange, OSI) vs LookML: lock-in trade-offs, migration paths, and metric portability for AI agents.
Read the story
Apache Ossie (OSI) vs dbt MetricFlow: Key Differences & Why It Matters for AI Agents
Apache Ossie (formerly Open Semantic Interchange, OSI) vs dbt MetricFlow: definition vs execution, portability, and why both matter for AI agents.
Read the story
What Is Snowflake OSI? Semantic Views, Cortex Analyst & Ossie
Snowflake OSI is search shorthand for Snowflake's role in Open Semantic Interchange — now Apache Ossie — plus Semantic View import/export via Ossie YAML.
Read the story
Datus: The Cursor for Data Engineering
"Cursor for data engineering" means an agent that runs your data system — warehouses, metrics, and reference SQL — with evolvable context, not autocomplete.
Read the story
13 Months from ChatBI to DataAgent: A Field Report
Thirteen months inside a restaurant chain's move from ChatBI to a DataAgent: the paradigm shift, layering by determinism, security hooks, and the pits we hit.
Read the story
Semantic Layer Tools Compared: Stack Fit & Apache Ossie
Compare 16 semantic layer tools for dbt metrics, embedded BI, warehouse-native views and portable AI agents. See Dosi's Apache Ossie path and each tool's fit.
Read the story
What Is Change Data Capture (CDC)? Methods & Use Cases
Change data capture (CDC) definition, the three CDC methods — log-based, trigger, query — plus real-time use cases, pitfalls, and CDC to the lakehouse.
Read the story
What Is Apache Hudi? Upserts, Copy-on-Write vs Merge-on-Read & CDC
Apache Hudi definition, how copy-on-write and merge-on-read tables, record-level upserts and incremental queries work, Hudi vs Iceberg vs Delta, and agent context.
Read the story
What Is Apache Iceberg? Table Format, Features & Iceberg vs Delta Lake
Apache Iceberg definition, how its hidden partitioning, snapshots and schema evolution work, Iceberg vs Delta Lake vs Hudi, and why AI agents need table-aware context.
Read the story
What Is Medallion Architecture? Bronze, Silver & Gold Layers
Medallion architecture definition: Bronze, Silver, and Gold lakehouse layers, what belongs in each, the anti-patterns, and which layer an AI agent should query.
Read the story
What Is a Data Contract? Definition, Schema Enforcement & Examples
Data contract definition: a machine-checked producer–consumer agreement on schema, semantics, quality, and SLAs. Tools, enforcement, and the agent angle.
Read the story
What Is a Lakehouse Catalog? Hive, Glue, Unity, Polaris & Horizon
A lakehouse catalog tracks table metadata for query engines. Compare Hive Metastore, AWS Glue, Unity Catalog, Apache Polaris and Snowflake Horizon.
Read the story
Apache Ossie (OSI) vs MetricFlow: Semantic Standard vs Execution Engine
Apache Ossie (formerly Open Semantic Interchange, OSI) vs MetricFlow: portable semantic standard vs dbt's execution engine, and when to use each.
Read the story
What Is a Data Lake? Definition, Architecture & Data Lake vs Data Warehouse
Data lake definition, schema-on-read architecture, zones and file formats, the data swamp problem, data lake vs data warehouse, and what AI agents need to query one.
Read the story
What Is a Data Warehouse? Definition, Architecture & How It Differs From a Data Lake
Data warehouse definition, architecture (ETL, dimensional models, columnar MPP), how it differs from a data lake and lakehouse, and what AI agents need to query one.
Read the story
What Is a Lakehouse? Definition, Architecture & Open Table Formats Explained
Lakehouse definition, how it differs from data lakes and warehouses, open table formats (Iceberg, Delta, Hudi), and why AI agents need lakehouse-aware context.
Read the story
How Datus Turns AI-Generated SQL into Trusted Data
Why reliable AI data engineering needs knowledge, planning, review, controlled execution, and reconciliation, not just SQL generation.
Read the story
AI-Native Data Platforms: Why the Next Generation Needs Data Engineering Agents, Not Just Copilots
What defines an AI-native data platform, how it differs from platforms with bolted-on AI features, and why data engineering agents are the missing infrastructure layer.
Read the story
Best Data Engineering Agents in 2026: An Honest Comparison
Best data engineering agents in 2026 compared by stack fit, context, openness, and enterprise readiness.
Read the story
Platform-Native Data Engineering Agents Compared: Cortex Code, Genie Code, and BigQuery DE Agent
A detailed comparison of Snowflake Cortex Code, Databricks Genie Code, and Google BigQuery Data Engineering Agent — and the case for open, cross-stack alternatives.
Read the story
GoodData: How a 17-Year BI Company Became an AI-Native Analytics Platform
GoodData's evolution from cloud BI startup to GoodData.AI — what it reveals about the industry shift toward AI-native analytics and the role of the semantic layer.
Read the story
Cube.dev: From Semantic Layer Pioneer to Agentic Analytics Platform
How Cube.dev evolved from an open-source semantic layer to the D3 Agentic Analytics platform, and what its trajectory means for data engineering.
Read the story
dbt MetricFlow Explained: Best Fit, Limits & OSI Options
MetricFlow fits dbt teams that govern metrics in Git. See where it works, when an Apache Ossie runtime such as Dosi helps, and how to choose for AI agents.
Read the story
Open Semantic Interchange (OSI): What the New Standard Means for Data Engineering and AI Agents
A complete guide to Open Semantic Interchange (OSI) — now Apache Ossie (incubating): what it standardizes, who's behind it, and why portable semantics matter.
Read the story
Ontology vs Semantic Layer: Definitions and When You Need Each
What an ontology is, what a semantic layer is, where the two overlap, and the signals that tell you when a data team actually needs a formal ontology.
Read the story
What Is a Data Agent? How It Differs From a Data Engineering Agent
Data agent definition, types, capabilities, and how a data engineering agent fits as the specialized subclass that builds and evolves data context.
Read the story
What Is Data Mesh? Definition, Principles & How Domain Agents Map to It
Data mesh definition, four principles, comparison to data fabric, and how subject trees and subagents align with domain ownership.
Read the story
What Is a Metric Layer? Definition, Examples & How It Differs From a Semantic Layer
Metric layer definition, MetricFlow examples, semantic layer vs metric layer differences, and why AI agents need standardized metrics.
Read the story
What Is a Semantic Model? Definition, Examples & How It Differs From a Semantic View
Semantic model definition, key components, how it fits into a semantic layer, and how it differs from warehouse-native semantic views.
Read the story
What Is RAG for Data Engineering? Retrieval, Context & Agent Accuracy
RAG definition for data engineering: retrieving schema, metrics, and SQL history to ground NL2SQL and data engineering agents.
Read the story
What Is a Data Catalog? Definition, Tools & How It Differs From Agent Context
Data catalog definition, popular tools, and why data engineering agents need context engines beyond discovery metadata.
Read the story
What Is Schema Linking? Definition, Challenges & How Agents Map NL to Columns
Schema linking definition for text-to-SQL, common failure modes, and how dual-dimension context improves column resolution.
Read the story
What Is Text-to-SQL? Definition, How It Works & Why Context Matters
Text-to-SQL definition, NL2SQL pipeline stages, accuracy limits, and how data engineering agents improve with persistent context.
Read the story
Data Engineering Agent vs. SQL Copilot: What's the Real Difference?
Data engineering agent vs SQL copilot: persistence, feedback, team context, and when each tool fits.
Read the story
One-Person Data Team: How a Data Engineering Agent Multiplies Your Output
How a one-person data team uses a data engineering agent to reduce SQL translation work and ship self-service analytics.
Read the story
Subagents: How to Ship Domain-Specific Data Agents Without Training a Model
Subagents explained: domain-specific data agents built from scoped context, feedback, and governed access.
Read the story
How to Build Your First Data Engineering Agent in 15 Minutes
Build a first data engineering agent with Datus: install, ask questions, generate context, and create a subagent.
Read the story
Data Engineering Agent vs. Claude Code: When to Use Which
Data engineering agent vs Claude Code: when persistent data context matters and when a coding agent is enough.
Read the story
What an Enterprise Data Engineering Agent Actually Needs
Enterprise data engineering agent requirements: shared context, RBAC, auditability, reliability, and governance.
Read the story
Best Data Engineering Agents in 2026: An Honest Comparison
Best data engineering agents in 2026 compared by stack fit, context, openness, and enterprise readiness.
Read the story
MCP and Data Engineering: The Protocol That Connects Your Entire Stack
MCP for data engineering: how agents connect to databases, orchestrators, quality tools, and context services.
Read the story
Open-Source Data Engineering Agents: Private Deployment
Compare open-source data engineering agents and learn what a private deployment must check: model endpoint, data flow, credentials, and access controls.
Read the story
How a Context Engine Makes Data Engineering Agents More Accurate
How a context engine improves data engineering agent accuracy with schemas, validated SQL, and feedback loops.
Read the story
Contextual Data Engineering: Why Every Data Engineering Agent Needs Evolvable Context
Contextual data engineering explained: schemas, semantics, and feedback loops for durable data agents.
Read the story
What Is a Data Engineering Agent? Definition, Examples & a 2026 Comparison
Four products now ship as a data engineering agent — but they are not the same thing. Working definition, side-by-side comparison, and where persistent context separates agents from chat windows.
Read the story
What Is a Semantic Layer? Definition, Examples & How It Differs From a Metric Layer
Semantic layer defined: the business translation layer between raw tables and analysts, what it includes (metrics, dimensions, entities), how it differs from metric layers and catalogs, and why static models break under AI agents.
Read the story
The Full-Stack Data Engineer: Three Skills and a Harness
Why the one-person data team is coming, the three skills a full-stack data engineer needs, and why validation — not SQL generation — is now the real bottleneck.
Read the story
Beyond SQL: How Datus Integrates With Your Entire Data Toolchain
Learn how MCP and Skills connect Datus to your data catalog, metric layer, scripts, and quality workflows across the full data toolchain.
Read the story
Make Data Agents Usable: Ask, Explore, and Control with Confidence
See how Ask User, session management, Explore, and action display make Datus data agents easier to trust, control, and use every day.
Read the story
Datus Storage Layer: A Foundation Built for Every Environment
Pluggable storage adapters that separate relational and vector storage from the agent core for enterprise flexibility.
Read the story
Meet the General Chat Agent: Your Data Co-Pilot That Actually Thinks
The General Chat Agent goes beyond SQL generation to support exploration, investigation, and knowledge-building.
Read the story
Datus 0.2.6 Release: Equipping the Agent with a Brain
Datus 0.2.6 adds a more general chat agent, stronger planning flows, deeper data exploration, and broader support across the data stack.
Read the story
Agentic Data Engineering vs Traditional Data Engineering
Compare agentic and traditional data engineering across workflows, tooling, team structure, and reliability in production.
Read the story
Agentic ETL: What Changes Beyond Traditional ETL
See how agentic ETL adds context-aware planning, validation, workflow-state reasoning, and human review beyond traditional ETL.
Read the story
AI Data Pipeline Automation: Use Cases, Architecture, and Tradeoffs
Learn where AI data pipeline automation works, how to design the architecture, and which tradeoffs matter before scaling it.
Read the story
How MCP Changes Data Workflow Automation
Learn how MCP improves data workflow automation with structured tool access, safer execution paths, and tighter system integration.
Read the story
How Structured Context Improves AI Agent Output
Learn how structured context improves AI agent output by grounding reasoning in metrics, semantics, and workflow state.
Read the story
Semantic Modeling for Agentic Analytics Workflows
Learn how semantic modeling improves agentic analytics by grounding AI agents in shared metric definitions and governed business context.
Read the story
The Operating Model of an Agentic Data Team
Learn how an agentic data team operates with clear roles, review loops, guardrails, and human-in-the-loop control across planning, execution, and governance.
Read the story
Using MCP Extensions in Data Engineering Workflows
Learn how MCP extensions give data engineering agents controlled tool access, safer execution paths, and more reliable automation.
Read the story
What Autonomous Data Engineering Actually Looks Like in Practice
See what autonomous data engineering looks like in practice with structured context, bounded agent actions, human review, and workflow automation.
Read the story
Why AI Agents Need Semantic Context to Work Reliably
Learn why semantic context helps AI agents reason reliably across data systems by grounding definitions, relationships, and constraints.
Read the story
Why Data Engineering Needs Agents, Not Just Copilots
Learn why data engineering needs agents, not just copilots, and how agentic workflows improve execution, reliability, and control.
Read the story
Why Reliable Data Agents Need More Than Good Prompts
Learn why reliable data agents need structured context, workflow state, metrics, semantic models, and guardrails beyond good prompts.
Read the story
From Human-First Data Systems to the Agentic Data Stack
Learn why the Agentic Data Stack goes beyond AI SQL tools by combining context, semantics, workflows, and governed execution.
Read the story
Data Engineering Agent Architecture for Production
A practical architecture blueprint for data engineering agents, with Datus patterns for context, subagents, and governed execution.
Read the story
7 High-Impact Data Engineering Agent Use Cases (Powered by Datus)
Explore practical data engineering agent use cases and how Datus helps teams improve speed, quality, and governance.
Read the story
What Is a Data Engineering Agent? A Practical Guide with Datus
Learn what a data engineering agent is, why context matters, and how Datus turns AI into reliable, production-ready data workflows.
Read the story
SQL agents are broken without context. Meet Datus.
Learn why SQL agents fail without governed context and how Datus uses contextual engineering and subagents for reliable workflows.
Read the story
Welcome to Datus Blog
Introducing the Datus blog with insights on AI-native data engineering, context engineering, and reliable data workflows.
Read the story