Writing extensive context documentation for AI agents is counterproductive because most of it duplicates facts the system already exposes through configs, logs, metadata, and queries, according to a S…
A September Build Lab session, published as a written guide, lays out a four-phase plan for onboarding an AI data agent the way a company hires a data person: orientation, onboard, internship, and hir…
An MCP server exposes a data tool's capabilities to AI agents through the open Model Context Protocol, letting agents such as Claude Code, Cursor, Codex, and ChatGPT call a tool's functions directly i…
Published semantic-layer benchmarks from Snowflake, dbt, Cube, and Denodo conflate two distinct claims — richer business context versus deterministic SQL compilation — so their reported accuracy lifts…
A developer argues that AI agents acting on enterprise data face a different reliability problem than human analysts: stale or ambiguous data that once produced merely bad analysis can now trigger bad…
OpenAI recently introduced a Data agent for ChatGPT Work that can investigate company data and create shareable dashboards, and its earlier account of its in-house data agent sets the operating princi…
A new framework called Spec-Lock-Diff aims to reduce the risks of AI agents writing SQL in dbt development by splitting the workflow into three phases: Spec, Lock, and Diff. The framework's reference …
Motley launched a GitHub integration that stores semantic models in a repository, making the default branch the source of truth and importing configs within seconds of a push. The integration validate…
AngelList replaced its traditional semantic layer with self-generating markdown knowledge and skills files that an AI agent reads, eliminating the need for query-planning services like MetricFlow or S…
Cassis has released an open-source context bootstrap kit on GitHub to help teams assemble initial context for analytics agents from existing data stacks, replacing a token-heavy agent stage that spent…
A Neo4j semantic layer built with Neocarta cut Text2SQL token costs by up to 81% on a 278-table BigQuery Census ACS catalog and up to 54% on a 264-table Databricks catalog, according to a Neo4j soluti…
As of 2026, data tools shipping their own MCP server include Bruin, dbt, Snowflake, Databricks, and ClickHouse, plus community servers for Postgres, BigQuery, DuckDB, and most databases, according to …
Snowflake Inc. has introduced CoCo, an AI coding agent designed for data engineers working with Snowflake, which runs inference within Snowflake's security perimeter and includes native integration an…
A developer recounts how a GenAI assistant caused a $4,200 query failure and downtime on a production database, arguing that Text-to-SQL agents need hard infrastructure constraints rather than blind t…
A developer argues that running recurring analysis as scheduled LLM prompts is flawed because the LLM's nondeterministic query generation confounds metric changes with query variations. The proposed f…
A developer built Safaricom Intelligence, a data pipeline that converts 19 years of Safaricom's financial disclosures into a queryable BigQuery dataset. During the project, the pipeline generated a fa…
Interlace, a new open-source data engineering framework, unifies SQL and Python models, ingestion, and orchestration into a single graph abstraction, eliminating the seams between separate tools. The …
A new analysis compares the dbt Semantic Layer, Cube, and AtScale for enterprise use, finding that while all three define metrics, none addresses whether an AI agent is authorized to execute them. The…
Artefact, a global data and AI consulting company, is hiring a Forward Deployed Engineer for its Utrecht office to build production-grade data pipelines and deploy LLM-based solutions such as RAG syst…
A Databricks-focused consultancy, Zephico, breaks down the real costs of migrating from Snowflake to Databricks, arguing that the true benefits come from moving for ML and streaming workloads rather t…