Offline evaluations using questions with fixed, verified answers let teams measure and catch regressions in the semantic layers that AI data agents rely on, according to a Motley blog post. The post r…
MotleyAI published two example notebooks showing how its SLayer semantic layer can be combined with DuckDB to query a remote dataset in a handful of lines, with one notebook driven from the CLI and on…
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…
An evaluation by the SLayer team found that an AI agent using the open-source version of Cube, an incumbent open-core semantic layer, solved zero of 10 tasks from the LiveSQLBench-Lite benchmark, whil…
Motley AI's open-source semantic layer SLayer improved text-to-SQL accuracy by over 34% on production-scale databases, with the SLayer agent passing 153 of 265 tasks (57.7%) versus 114 (43.0%) for a r…
Motley has launched user-facing MCP, a governed, read-only interface that lets customers connect AI agents such as Claude, Codex, or Cursor to their own data through Motley's semantic layer. The featu…
Motley AI achieved a 75.3% pass rate on the BIRD-INTERACT benchmark using the Claude SDK and its open-source semantic layer SLayer, far surpassing the official best of 36.33%. The agent harness provid…
Building an in-house analytics MCP server for customer AI agents may seem cheap initially but incurs hidden costs in multi-tenant isolation, identity propagation, governed metrics, observability, and …
Building an analytics MCP server requires choosing between wrapping an existing API or implementing a semantic layer. Wrapping an API is faster but leads to inconsistent metrics and chatty queries, wh…
SaaS products are adopting analytics MCP servers to expose customer data to AI agents via the Model Context Protocol, enabling use cases like in-product copilots, customer-owned agents, automated work…
SaaS product teams evaluating embedded analytics now face a newer option: MCP analytics, which exposes governed data to AI agents rather than rendering dashboards for humans. Embedded analytics delive…
SaaS products are shifting from embedding dashboards for human users to exposing customer-facing MCP servers that AI agents can query directly, driven by customer demand for agent-native data access. …
An analytics MCP server is an endpoint that lets AI agents query a product's data through the Model Context Protocol, returning governed, permission-scoped answers instead of raw table access. It diff…
Vertical software companies are transforming analytics from a dashboard feature into the core product, driven by AI agents that let customers query data in plain language. Mews acquired DataChat for h…
Motley AI achieved a 75.3% pass rate on the BIRD-INTERACT benchmark using the Claude SDK and its open-source semantic layer SLayer, far exceeding the official best of 36.33%. The agent harness provide…
Cube and SLayer are two open-source semantic layers that help developers govern AI agent access to structured data. Cube runs as a standalone service, while SLayer can run in-process as a Python libra…