Blog
Semantic layers, agentic analytics, and shipping governed data to AI agents.
MCP ChartsMCP Charts: Add Interactive Charts to Your MCP ServerGive 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.MCP ChartsHow Bonnard Builds Agent-Friendly MCPsExposing 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.Semantic LayerTurn Your dbt Project Into a Semantic Layer for AgentsTurn 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.Agentic AnalyticsAI Data Analysis: Why Governed Metrics Beat Raw SQL GenerationA 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.Agentic AnalyticsAI Reporting: How to Automate Reports Without Losing TrustA 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.AnalyticsAnalytics API: How to Serve Governed Metrics to Any ConsumerAn analytics API exposes your metrics programmatically. Here's how to build one that serves dashboards, AI agents, and customer integrations from the same definitions.AnalyticsBest Embedded Analytics Tools for SaaS in 2026Comparing 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.AnalyticsHow to Build Customer-Facing Analytics for B2B SaaSA 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.AnalyticsKPI Dashboards Are Broken. Here's What Replaces Them.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.AnalyticsReal-Time Analytics: When You Need It and When You Don'tNot 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.Semantic LayerSelf-Service BI Is a Lie (Unless You Govern the Metrics)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.Semantic LayerWhat Is a Semantic Layer? A Practical Guide for Data EngineersA 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.Agentic AnalyticsWhat Is an 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.Agentic AnalyticsWhy Your AI Agents Need a Semantic LayerWhy 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.Agentic AnalyticsHow to Connect an AI Agent to Your Data WarehouseConnect 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.