Turning an Analytics Question Into a Verified Agentic Graph
September 28, 2026A complete AGS 1.0 graph for governed metric questions, with verification gates, deterministic check scripts, and reconciliation against a semantic layer.
39 posts tagged with "AI Agents"
Twelve Queries That Pass Every Schema Check and Still Return the Wrong Number
September 28, 2026Twelve query patterns that pass schema validation and still return wrong numbers, with detectors, required metadata, and tested code for each.
How Apache Ossie Is Deciding What Agents and BI Tools Can Ask a Semantic Layer
September 21, 2026How Apache Ossie's layered query design gives AI agents both a constrained dimensional interface and a grain-safe SQL interface for semantic layers.
The Plan and the Worker: Two Open Specifications for Agent Harnesses
August 10, 2026Two open specifications, the Agentic Graph Specification and the Open Agent Profile, turn agent plans and agent identity into portable, reviewable files.
Budgeting for Agentic Analytics When Every Question Costs Something Different
August 04, 2026Budgeting for agentic analytics when every question costs something different: token economics, query economics, instrumentation, and the cost controls that actually return.
The Five Layers of an Agentic Lakehouse and Where the MCP Server Sits
August 04, 2026The five layers of an agentic lakehouse and where the MCP server sits: storage, catalog, semantic layer, MCP gateway, and agent surface, plus identity, session isolation, and budgets.
Wiring Analytical Queries to Transactional APIs in Closed-Loop Decision Agents
August 04, 2026Wiring analytical queries to transactional APIs in closed-loop decision agents: conditional writes, sagas with compensations, decision records, and blast radius controls.
Why Agentic AI Needs a Governed Semantic Layer Behind the Model Context Protocol
August 04, 2026Why agentic AI needs a governed semantic layer behind the Model Context Protocol: metric consistency, access control, Apache Ossie for portable definitions, and Apache Polaris for enforcement.
Moving From Supply Chain Dashboards to Decision Loops With the Model Context Protocol
August 04, 2026Moving from supply chain dashboards to decision loops with MCP: sense, decide, act, and verify, with typed action tools, idempotency keys, and graduated human approval.
Metric Contracts as the Interface AI Agents Actually Need
August 04, 2026Metric contracts as the interface AI agents need: calculation, inclusion rules, grain, temporal semantics, ownership, semantic versioning, and testing metrics in CI.
Defending the Lakehouse Gateway Against Prompt Injection and Data Exfiltration
August 04, 2026Defending the lakehouse gateway against prompt injection and data exfiltration: per-user identity, no-SQL tool surfaces, volume bounds, and detection in query behavior.
Guardrails for Analytics Agents That Do More Than Answer Questions
July 28, 2026The risk isn't agents going rogue, it's agents acting correctly on bad input at machine speed. Here's how to classify actions by consequence, gate capability, and design approval steps people actually use.
Building Agent Telemetry Tables in Iceberg That Survive an Audit
July 28, 2026A practical guide to building agent decision traces in Apache Iceberg that support audit reconstruction, governance review, and cost attribution across sessions.
What Agentic Analytics Actually Costs, and How to Keep It Bounded
July 28, 2026Agent analytics generates two cost streams that scale on different variables. Here's the arithmetic, the levers that actually move the number, and how to build attribution before you need it.
When the Query Optimizer Starts Managing Its Own Materializations
July 28, 2026Autonomous materialized view management replaces quarterly review meetings with workload-driven scoring, and it's essential when AI agents generate unpredictable query patterns.
Why AI Agents Fail on Raw Data, and What to Give Them Instead
July 28, 2026Agents fail on raw lake data because business rules live in people's heads. Data products with semantic contracts fix this at the source.
The Five Layers Between Your Lakehouse and a Trustworthy Agent
July 28, 2026Agent reliability is a property of the stack the model sits on. Five layers with distinct owners and failure modes turn the agent is unreliable into a specific diagnosis.
Surviving Commit Conflicts When Dozens of Writers Hit the Same Iceberg Table
July 28, 2026Commit conflicts multiply with writer count, and AI agents introduce unpredictable write patterns. Here's how to diagnose, tune, and architect around Iceberg's optimistic concurrency.
Wiring an AI Agent to Apache Polaris with the Model Context Protocol
July 28, 2026The catalog is the right attachment point for AI agents working against a lakehouse. Here's how to wire the official Polaris MCP Server and add the read path it deliberately leaves out.
Active Analytics Loops for AI Action Agents
July 13, 2026An in-depth exploration of active analytics loops for ai action agents
Data Lakehouse Open Standards for AI Agents
July 13, 2026An in-depth exploration of data lakehouse open standards for ai agents
The Chase-Catch Gap in Enterprise AI Agents
July 13, 2026An in-depth exploration of the chase-catch gap in enterprise ai agents
Five-Layer Agentic Lakehouse Architecture
July 13, 2026An in-depth exploration of five-layer agentic lakehouse architecture
GSA MCP Servers for Open Data AI Agents
July 13, 2026An in-depth exploration of gsa mcp servers for open data ai agents
Iceberg Concurrency for AI Agent Writes
July 13, 2026An in-depth exploration of iceberg concurrency for ai agent writes
MCP Stateless Gateways for Data Agents
July 13, 2026An in-depth exploration of mcp stateless gateways for data agents
Semantic View Autopilot for AI Governance
July 13, 2026An in-depth exploration of semantic view autopilot for ai governance
Data Platform Native AI Agent Tooling in 2026
May 31, 2026A comprehensive comparison of AI agent tooling across Dremio, Snowflake, Databricks, Microsoft Fabric, AWS, Google Cloud, ClickHouse, VeloDB, SpiceAI, Bauplan, and Qlik.
A Journey from AI to LLMs and MCP - 10 - Sampling and Prompts in MCP – Making Agent Workflows Smarter and Safer
April 14, 2025Sampling and Prompts in MCP : Making Agent Workflows Smarter and Safer
A Journey from AI to LLMs and MCP - 9 - Tools in MCP – Giving LLMs the Power to Act
April 13, 2025Tools in MCP : Giving LLMs the Power to Act
A Journey from AI to LLMs and MCP - 8 - Resources in MCP – Serving Relevant Data Securely to LLMs
April 12, 2025Resources in MCP : Serving Relevant Data Securely to LLMs
A Journey from AI to LLMs and MCP - 7 - Under the Hood – The Architecture of MCP and Its Core Components
April 11, 2025Under the Hood : The Architecture of MCP and Its Core Components
Journey from AI to LLMs and MCP - 6 - Enter the Model Context Protocol (MCP) – The Interoperability Layer for AI Agents
April 10, 2025Enter the Model Context Protocol (MCP) : The Interoperability Layer for AI Agents
A Journey from AI to LLMs and MCP - 5 - AI Agent Frameworks – Benefits and Limitations
April 09, 2025AI Agent Frameworks : Benefits and Limitations
A Journey from AI to LLMs and MCP - 4 - What Are AI Agents – And Why They're the Future of LLM Applications
April 08, 2025What Are AI Agents : And Why They're the Future of LLM Applications
A Journey from AI to LLMs and MCP - 3 - Boosting LLM Performance – Fine-Tuning, Prompt Engineering, and RAG
April 07, 2025Boosting LLM Performance : Fine-Tuning, Prompt Engineering, and RAG
A Journey from AI to LLMs and MCP - 2 - How LLMs Work – Embeddings, Vectors, and Context Windows
April 06, 2025How LLMs Work : Embeddings, Vectors, and Context Windows
A Journey from AI to LLMs and MCP - 1 - What Is AI and How It Evolved Into LLMs
April 05, 2025What Is AI and How It Evolved Into LLMs
Building a Basic MCP Server with Python
April 04, 2025The Basics of Building a Basic MCP Server