The BI that talks back
Chat with your data. Build dashboards with AI. Powered by your dbt semantic layer — at a fraction of the cost.
BI shouldn't be this hard
dbt Cloud costs $300+/user/month. Traditional BI tools require weeks of training. And AI features? Bolted on as an afterthought.
Expensive
dbt Cloud Enterprise + Semantic Layer + separate BI tool = $5,000+/month for a small team
Complex
Business users can't write SQL. They shouldn't need to learn Looker or Tableau either.
AI as afterthought
Most BI tools added "Ask AI" as a feature. It's not the core experience.
A better way to explore your data
Metricly is built from the ground up around conversation. Chat isn't a feature — it's the entire interface.
No dbt Cloud required
Upload your dbt semantic manifest directly. Get the full power of MetricFlow without the Cloud subscription.
LLM-native by design
Every interaction is conversational. Ask questions, build dashboards, explore data — all through natural language.
Chat with everything
Query data, design dashboards, and soon — edit metric definitions themselves. All through conversation.
Up and running in minutes
No complex setup. No JDBC configuration. No vendor negotiations.
Connect your warehouse
Link your BigQuery or DuckDB warehouse. Snowflake, Databricks, and more coming soon.
Upload your manifest
Run dbt parse locally and upload the semantic manifest.
Start asking questions
Your metrics are immediately queryable. Ask in plain English, get instant answers.
Ship your dbt metrics to the business
You've built a beautiful semantic layer in dbt. Now expose it without paying for dbt Cloud or building custom tooling.
- Works with dbt Core — no Cloud subscription needed
- Native MetricFlow engine for consistent metrics
- Version-controllable JSON dashboard definitions
- Save $300+/user/month vs dbt Cloud Enterprise
Ask your data anything
No SQL. No training. No waiting for the data team. Just ask questions in plain English and get instant, accurate answers.
- Natural language queries that actually work
- Instant visualizations from your questions
- One-click "Add to Dashboard" for any result
- Metrics defined by your data team, always consistent
Works where you work
Query metrics from ChatGPT, Claude, Cursor, your terminal, or any MCP-compatible tool. Metricly meets developers and AI agents where they are.
Query metrics from any AI assistant
Metricly speaks MCP — the open standard for AI tool integration backed by Anthropic, OpenAI, Microsoft, and Google. Connect your metrics to virtually any AI assistant.
- Works with ChatGPT, Claude, Copilot, and more
- Native support in Cursor, Windsurf, and VS Code
- Open standard — future-proof your integrations
Metrics for humans and agents
A CLI built for both humans and coding agents. Claude Code, Codex, Devin, and other AI assistants can query your metrics and manage dashboards autonomously.
- Agent-friendly output formats (JSON, CSV, YAML)
- Works great with Claude Code, Codex, and Devin
- CI/CD friendly for automated metric validation
AI-native BI for the modern stack
No SQL required. No context switching. Whether you're using ChatGPT, coding with Claude, or automating with agents — Metricly speaks your language.
Same semantic layer power. Fraction of the cost.
Metricly uses the same MetricFlow engine that powers dbt's Semantic Layer. You get enterprise-grade metric consistency without the enterprise price tag.
Ready to talk to your data?
Join the waitlist for early access and founding member pricing.