Meta tags:
description=Rill projects are defined as YAML and SQL files, which makes them a natural fit for AI coding agents. This guide walks through using an AI agent like Claude Code or Cursor to build a Rill project from scratch.;

Headings (most frequently used words):

with, step, agent, rill, ai, project, instructions, build, building, projects, prerequisites, initialize, start, in, preview, mode, your, next, steps, adding, to, an, existing, connect, data, source, create, models, define, metrics, dashboards, iterate,

Text of the page (most frequently used words):
rill (36), project (28), agent (26), your (16), the (16), and (15), with (11), instructions (10), claude (10), mcp (9), #create (8), data (7), step (7), for (7), build (6), #dashboards (6), metrics (6), you (6), code (6), init (6), models (5), connect (5), developer (5), server (5), files (5), this (5), start (4), preview (4), existing (4), quickstart (4), cloud (4), projects (4), add (4), configuration (4), yaml (4), bids (4), will (4), cursor (4), next (3), source (3), mode (3), ask (3), deploy (3), status (3), errors (3), resource (3), can (3), dashboard (3), auction (3), view (3), that (3), file (3), building (3), are (3), olap (3), engine (3), get (3), policy (2), steps (2), iterate (2), define (2), adding (2), initialize (2), prerequisites (2), install (2), other (2), natural (2), from (2), check (2), see (2), types (2), schemas (2), new (2), measures (2), what (2), total (2), win (2), rate (2), time (2), table (2), domain (2), model (2), bid (2), like (2), type (2), automatically (2), parquet (2), directory (2), run (2), queries (2), sql (2), which (2), local (2), setup (2), json (2), all (2), tool (2), agents (2), different (2), prompt (2), using (2), views (2), skills (2), name (2), coding (2), cli (2), guide (2), agentic (2), started (2), api (2), 2026, inc, contributing, community, terms, service, privacy, previous, desktop, chatgpt, clients, improve, responses, ai_instructions, questions, about, language, chat, share, team, something, isn, working, connection, lets, parse, reconciliation, failures, health, directly, has, full, context, fix, refactor, restructure, just, describe, want, canvas, kpi, cards, series, chart, breakdown, explore, average, price, broken, down, dimensions, device, bucket, cleans, filter, out, null, column, groups, into, ranges, bid_bucket, ingest, rilldata, public, auction_data, running, open, here, some, examples, read, write, operations, analytical, against, inspect, columns, sample, resources, healthy, errored, pending, gives, access, also, starts, generated, via, config, additional, required, http, localhost, 9009, launch, clean, only, while, handles, already, have, without, affecting, formats, once, agentsmd, agnostic, format, rules, select, option, use, flag, connects, detailed, each, etc, entry, point, tells, load, development, creates, clickhouse, interactive, another, compatible, installed, defined, makes, them, fit, walks, through, scratch, page, home, release, notes, tutorials, postmessage, iframe, embed, managing, configure, deployment, credentials, debugging, external, ide, integration, organize, alerts, custom, apis, connectors, first, why, search, github, blog, contact, rest, url, parameters, iso, 8601, syntax, reference, developers, skip, main, content,

Text of the page (random words):
building rill projects with ai rill skip to main content developers guide reference project files time syntax rill iso 8601 url parameters cli rest api contact us blog github search get started install rill developer agentic quickstart quickstart why rill build your first project connectors models metrics views dashboards custom apis alerts project configuration ai configuration organize your code files external ide integration debugging in rill developer deploy rill cloud vs rill developer configure deployment credentials deploy dashboards managing project errors embed iframe postmessage api tutorials other release notes home get started agentic quickstart on this page building rill projects with ai rill projects are defined as yaml and sql files which makes them a natural fit for ai coding agents this guide walks through using an ai agent like claude code or cursor to build a rill project from scratch prerequisites rill cli installed an ai coding agent claude code cursor or another mcp compatible tool step 1 initialize a project with agent instructions run rill init to create a new project the interactive setup will prompt you for a project name olap engine and agent instructions rill init project name my rill project olap engine clickhouse agent instructions claude this creates a project directory with rill yaml project configuration claude claude md entry point that tells claude code to load rill development skills claude skills detailed instructions for each resource type models metrics views dashboards etc mcp json connects claude code to rill s local mcp server using a different ai agent select a different option in the agent instructions prompt or use the agent flag cursor rules rill init my project agent cursor tool agnostic agents md format rill init my project agent agentsmd all formats at once rill init my project agent all adding agent instructions to an existing project if you already have a rill project you can add agent instructions without affecting your existing files rill init my existing project agent claude step 2 start rill in preview mode launch rill developer in preview mode to get a clean dashboard only view while your ai agent handles the code rill start my project preview this also starts a local mcp server at http localhost 9009 mcp if you generated agent instructions in step 1 your ai agent will connect to this server automatically via the mcp json config no additional setup required the mcp server gives your ai agent access to project status see which resources are healthy errored or pending table schemas inspect columns types and sample data sql queries run analytical queries against your olap engine file operations read and write project files step 3 build with your ai agent with rill running open your ai agent in the project directory and start building here are some examples of what you can ask connect a data source connect to the parquet file at gs rilldata public auction_data parquet the agent will create a source yaml file and rill will automatically ingest the data create models create a model that cleans the auction data filter out null bids and add a bid_bucket column that groups bids into 0 1 1 5 5 10 and 10 ranges define metrics create a metrics view on the auction model with measures for total bids average bid price and win rate broken down by dimensions like domain device type and bid bucket build dashboards create an explore dashboard for the auction metrics view create a canvas dashboard with kpi cards for total bids and win rate a time series chart and a breakdown table by domain iterate the agent has full context on rill s resource types and yaml schemas it can fix errors refactor models add new measures and restructure your project just describe what you want check project status if something isn t working ask your agent to check the project status the mcp connection lets it see parse errors reconciliation failures and resource health directly next steps deploy to rill cloud share your dashboards with your team ai chat ask questions about your data in natural language from rill cloud ai configuration add ai_instructions to improve ai responses for your project rill mcp server connect claude desktop chatgpt or other ai clients to rill cloud projects previous install rill developer next quickstart prerequisites step 1 initialize a project with agent instructions adding agent instructions to an existing project step 2 start rill in preview mode step 3 build with your ai agent connect a data source create models define metrics build dashboards iterate next steps 2026 rill data inc privacy policy terms of service community policy contributing