Agentic schema. Reliable outputs.

Query and build on data reliably and fast. Definitions baked in at source, so agents get predictable results without guessing.

npm install -g @bonnard/cli
Read the docs →
Open source. Apache 2.0.
Erblotse+15 users

Predictable results, every query

Bonnard isn't another AI layer that claims to understand your business on day one. It's where your team codifies metric definitions, business rules, and access policies, so agents execute on real context, not hallucinated guesses.

View docs →

Predictable agent responses

A strong semantic layer means agents produce accurate results every time. Users trust the outputs, so this doesn't become another low-uptake agent project.

View docs →

Governed access by default

Agents only see the metrics and dimensions they need. Row-level security, role scoping, and audit trails are built into the schema, not bolted on after.

View docs →

Any agent, any app

REST, GraphQL, Python, JS SDKs. Connect from LangChain, custom agents, or internal tools. One schema serves every consumer.

Schema
Search...⌘K
NAMEDESCRIPTIONFIELDS
Vorders_overview
Joins orders, customers, and line_items. Pre-aggregated AOV, fulfillment rate, repeat %.15
Vrevenue_analytics
Net revenue, refunds, and MRR by region, channel, and cohort month.13
Vproduct_performance
SKU-level sell-through, return rate, and contribution margin.12
Vcustomer_360
LTV, order frequency, RFM segment, and churn probability per customer.15
Corders
Source: warehouse.public.orders. One row per transaction.14
Ccustomers
Source: warehouse.public.customers. Deduplicated on email.13
Cproducts
Source: warehouse.public.products. Includes variants and pricing tiers.8
Cline_items
Source: warehouse.public.line_items. Quantity, unit price, discount applied.9
Cstores
Source: warehouse.public.stores. Physical and online locations with region.5

One schema, many surfaces

A semantic layer embeds your business knowledge at the source. Agents, apps, and dashboards query governed definitions instead of raw tables.

review 2025 revenue using bonnard
Let me start by exploring the available data sources to understand what's available for revenue analysis.
Used Bonnard MCP integration>
Now let me pull 2025 revenue data with a monthly breakdown:
Bonnard MCPvisualize
</>
40.0M30.0M20.0M10.0M0
JanFebMarAprMayJunJulAugSepOctNovDec

Give every agent your metrics

Deploy an MCP server with bon deploy. Agents query governed metrics directly, no complicated SQL. Context spent on analysis, not interpretation.

View docs →
v21d ago
Key Metrics
Total Revenue$184,211,057
Total Cost$80,278,885
Transactions40,315
Avg Order Value$4,569.29
Revenue Over Time
Monthly Revenue
AugSepOctNovDec2026JanFeb

Dashboards that ship like code

Write dashboards in Markdown. Pick a chart, deploy from the terminal. Version-controlled and reviewable like everything else in your repo.

View docs →
page.tsx
1"use client"
2
3import { PageHeader } from "@/components/page-header"
4import {
5 BarChart,
6 LineChart,
7 BigValue,
8 useBonnardQuery,
9} from "@bonnard/react"
10
11function ChartCard({ title, children }) {
12 return (
13 <Card className="bg-secondary/30">
14 <CardHeader>
15 <CardTitle>{title}</CardTitle>
16 </CardHeader>
17 <CardContent>{children}</CardContent>
18 </Card>
19 )
20}
21
22function PromoCountBigValue() {
23 const { data, loading } = useBonnardQuery({
24 query: {
25 measures: ["promotion_data.count"],
26 },
27 })

SDK for every consumer

REST for apps. SQL for analysts. React for frontends. Same model, every consumer.

View docs →
Schema›sales_performance›avg_order_value
sales_performance.avg_order_value
Average revenue per transaction
DEFINITION
TYPEavg
SQLsales_amount
CHANGE HISTORY
added23 Feb 2026, 20:01
Included from salesDeploy: Initial semantic layer: sales, product, store
+ description: "Average revenue per transaction"
+ name: "avg_order_value"
+ origin_cube: "sales"
+ sql: "sales_amount"
+ type: "avg"

A UI when you need one

Browse your schema, run queries, check results. For the times you want to look before you ship.

View docs →

Your agents deserve
real answers

npm install -g @bonnard/cli
Read the docs/GitHub/Discord