Analytics

Ask analytics questions in plain English, get charts and dashboards back. The agent picks the right data source, writes and validates the query, and renders the answer as a chart, table, or saved dashboard panel. Analytics also covers uptime monitoring, error tracking, and session replay — the surfaces a team would otherwise split across three or four separate tools.

It's an open-source replacement for Amplitude, Mixpanel, and Looker — for teams that want to own the code, the queries, and the data.

What you can do with it

• Ask data questions in plain English. "What percent of signups last month converted to paid?" or "Show me weekly active users for the past 6 months." The agent picks the right source, writes the SQL, and renders the chart.
• Build reusable dashboards — either SQL dashboards the agent writes, or point-and-click Explorer dashboards over your BigQuery schema — with filters, saved views, and sections.
• Run ad-hoc analyses that cross-reference multiple data sources — saved as re-runnable investigations with the original question, instructions, and findings.
• Maintain a living data dictionary of metrics, tables, and SQL recipes so the agent uses the right column names every time (no more guessed is_closed when it's actually hs_is_closed).
• Watch uptime and triage errors. Add an HTTP uptime check with alerting, publish a public status page, and triage browser exceptions grouped into issues — see Monitoring, Errors, and Session Replay.
• Watch a real session play back. Every recorded session captures the page, console, and network activity, replayable frame by frame with a Chrome-style Dev Tools panel.
• Share dashboards with your team — private by default, shareable per-user or per-org with viewer / editor / admin roles.
• Connect your stack. BigQuery, GA4, Amplitude, Mixpanel, PostHog, HubSpot, Stripe, Slack, Prometheus, Grafana, and a dozen more — see the full catalog in Connecting and Extending Data Sources.

Getting started

Live demo: analytics.agent-native.com.

When you first open the app:

1. Sign in with Google. A demo dashboard installs automatically so there's something to look at right away.
2. Open the Data Sources page from the sidebar.
3. Each source has a walkthrough — connect the ones you need (start with one, like BigQuery, GA4, Amplitude, or first-party tracking).
4. Open a new chat with the agent and ask a question: "How many signups did we get last week?"

The first question is enough to confirm the connection works. From there, ask the agent to "save this as a dashboard" or "build a 4-panel overview dashboard for our key metrics."

Useful prompts

• "Build a dashboard showing weekly active users for the past 6 months."
• "What percent of signups last month converted to paid?"
• "Add a chart comparing revenue by plan to this dashboard."
• "Reorder the panels on this dashboard so the MRR metric comes first."
• "Analyze our closed-lost deals from Q1 and save the analysis."
• "Document this metric in the data dictionary."
• "Add an uptime check for our production API and alert Slack if it goes down."
• "Show me today's open error issues, worst first."

The agent always knows what you're looking at — current dashboard, filters, view — so you can say "this dashboard" or "that panel" without being explicit.

Surfaces at a glance

Analytics is more than dashboards and the dictionary — here's everywhere you'll spend time:

• Dashboards, analyses, and the data dictionary — reusable SQL/Explorer dashboards, one-off investigations, the shared metric vocabulary, plus scheduled email reports and alert rules.
• Monitoring, errors, and session replay — uptime checks with a public status page, Sentry-style error triage, full session recordings with a Dev Tools panel, and traffic/SEO reporting.
• Data sources — every connected provider, reusable workspace integrations, and the escape hatches for anything a canned action doesn't cover.
• Admin home (/agents) — a fleet feature-flag control plane, a dashboard usage audit, and connected-app database admin for organization owners — see Extending Analytics.

For developers

Create an Analytics app from the template via the CLI:

npx --yes @agent-native/core@latest create my-analytics --standalone --template analytics

See Getting Started for the rest of the setup (installing dependencies, running the dev server, environment variables), and Extending Analytics for the data model, action reference, and customization points.

What's next

• Dashboards, Analyses, and the Data Dictionary — the day-to-day surfaces
• Monitoring, Errors, and Session Replay — uptime, error triage, and replay
• Connecting and Extending Data Sources — the full connector catalog and the escape hatches
• Extending Analytics — data model, actions, and customizing the template
• Templates — the Cloneable SaaS model, and every other domain template to start from
• Getting Started — the framework fundamentals: actions, application state, and live sync
• Sharing — the share-grant model dashboards and analyses build on