Semantic layers, agentic analytics, MCP, and shipping governed data to AI agents.https://bonnard.dev/https://bonnard.dev/blog/mcp-charts/https://bonnard.dev/blog/mcp-charts/Give your AI agent a visualize tool and it renders interactive charts inside Claude and ChatGPT, from your real query data. Add it to any MCP server in a few lines with @bonnard/mcp-charts.Thu, 25 Jun 2026 00:00:00 GMThttps://bonnard.dev/blog/how-bonnard-builds-agent-friendly-mcps/https://bonnard.dev/blog/how-bonnard-builds-agent-friendly-mcps/Exposing data over MCP is easy. Designing a tool an agent uses well is the hard part. The techniques behind a chart tool agents call correctly: discovery-first tools, compact responses, instructive errors, and determinism.Tue, 16 Jun 2026 00:00:00 GMThttps://bonnard.dev/blog/turn-your-dbt-into-a-semantic-layer/https://bonnard.dev/blog/turn-your-dbt-into-a-semantic-layer/Turn dbt into a semantic layer for agents: go from models and a manifest to governed metrics agents can query and chart consistently, without rebuilding your stack.Tue, 16 Jun 2026 00:00:00 GMThttps://bonnard.dev/blog/ai-data-analysis/https://bonnard.dev/blog/ai-data-analysis/A guide to AI data analysis for SaaS: the tool categories, the accuracy problem, and the MCP-native way to render charts from your query results inside an agent.Thu, 19 Mar 2026 00:00:00 GMThttps://bonnard.dev/blog/ai-reporting/https://bonnard.dev/blog/ai-reporting/A guide to AI reporting for SaaS: the tool landscape, the trust problem, and the MCP-native way to render charts from your query results inside an agent.Thu, 19 Mar 2026 00:00:00 GMThttps://bonnard.dev/blog/analytics-api/https://bonnard.dev/blog/analytics-api/An analytics API exposes your metrics programmatically. Here's how to build one that serves dashboards, AI agents, and customer integrations from the same definitions.Thu, 19 Mar 2026 00:00:00 GMThttps://bonnard.dev/blog/best-embedded-analytics-tools/https://bonnard.dev/blog/best-embedded-analytics-tools/Comparing the best embedded analytics tools 2026 for B2B SaaS: Metabase, Holistics, Explo, Luzmo, Reveal, GoodData, Looker, Power BI, Tableau, and the MCP-native option for charts in AI agents.Thu, 19 Mar 2026 00:00:00 GMThttps://bonnard.dev/blog/customer-facing-analytics-for-saas/https://bonnard.dev/blog/customer-facing-analytics-for-saas/A guide to customer-facing analytics 2026 for B2B SaaS: the options, the tradeoffs, and the MCP-native way to put interactive charts inside an AI agent.Thu, 19 Mar 2026 00:00:00 GMThttps://bonnard.dev/blog/kpi-dashboard/https://bonnard.dev/blog/kpi-dashboard/KPI dashboards show stale numbers that nobody trusts. Governed metrics served through a semantic layer give every consumer the same live data, from dashboards to AI agents.Thu, 19 Mar 2026 00:00:00 GMThttps://bonnard.dev/blog/real-time-analytics/https://bonnard.dev/blog/real-time-analytics/Not every metric needs real-time data. Here's how to decide what needs sub-second freshness, what can be cached, and how pre-aggregation handles both.Thu, 19 Mar 2026 00:00:00 GMThttps://bonnard.dev/blog/self-service-bi/https://bonnard.dev/blog/self-service-bi/Self-service BI for customers promised to free the data team. Instead it created metric chaos. Here's the category, the tradeoffs, and where charts in an AI agent fit.Thu, 19 Mar 2026 00:00:00 GMThttps://bonnard.dev/blog/what-is-a-semantic-layer/https://bonnard.dev/blog/what-is-a-semantic-layer/A semantic layer defines business metrics once so every consumer gets the same answer, including AI agents. Here's what a semantic layer for AI agents is, how it works, and code examples.Thu, 19 Mar 2026 00:00:00 GMThttps://bonnard.dev/blog/what-is-agentic-semantic-layer/https://bonnard.dev/blog/what-is-agentic-semantic-layer/An agentic semantic layer is a metrics layer built for AI agents. It defines business logic once and exposes it via MCP or API so agents query governed definitions, then chart the result, not raw SQL.Mon, 16 Mar 2026 00:00:00 GMThttps://bonnard.dev/blog/why-ai-agents-need-semantic-layer/https://bonnard.dev/blog/why-ai-agents-need-semantic-layer/Why AI agents need a semantic layer: querying raw SQL produces inconsistent, ungoverned results. Here's what goes wrong without one, and how governed metrics plus a chart tool change the architecture.Mon, 16 Mar 2026 00:00:00 GMThttps://bonnard.dev/blog/connect-ai-agent-data-warehouse/https://bonnard.dev/blog/connect-ai-agent-data-warehouse/Connect an AI agent to your data warehouse: expose governed metrics over MCP, let agents query instead of writing raw SQL, and chart the result in Claude or ChatGPT. Full tutorial in under 30 minutes.Fri, 13 Mar 2026 00:00:00 GMT