Product updates

Steep AI can now work with your reports – creating them, finding them, and using them as context for analysis.

Create reports with AI

Turn the insights from a chat session into a report with a single prompt. Or just tell Steep AI to create any kind of dynamic report, exactly the way you want it – with charts, tables, big numbers, and text. Everything it builds is live and fully editable, just like any other Steep report.

Reports as context

Steep AI can now search your reports and read their contents, using them as context for deep analysis. Ask about last month's business review and the agent can find the report, understand it, and build on it.

Mention reports

Bring a specific report into the conversation the same way you mention metrics and time periods – use the @ button or simply type “@” in the chat.

Also in the API and MCP

Creating, listing, and reading reports is available through the Steep API and the Steep MCP as well, so your own tools and agents can work with reports too.

Claude Sonnet 5

Steep AI now runs on Claude Sonnet 5, Anthropic's latest model - for faster, sharper analysis across the board.

Start using Steep AI →

The full semantic model can now live in code. All managed as YAML in Git, with version control, code review, and CI.

Steep syncs automatically from your repository, with code as the source of truth, and everything defined in code works just like anything created in the UI: ready to explore, analyze, and build reports on. Additions in this release:

• Entities: Enable row-level data and drill-downs - going from an aggregated metric to the individual records behind it.

• Derived metrics: Metrics built from other metrics, like a ratio of two existing metrics.

• Slices: Sub-metrics that give you quick, pre-defined cuts of a metric, like a priority market.

• Cohorts: Follow groups over time - like retention by signup month - with retention settings and time grains included.

• Targets: Set goals for your metrics and track progress against them.

• Access policies: Control who sees what with row-level security policies.

Help center: Define in Code →

We've reorganized the left nav to surface what matters most. Metrics and Entities now sit at the top level, above Teams, so you can quickly access your most-used data. Collapse these sections to keep your nav compact, or expand them to see all your metrics and entities at a glance. A new Favorites section at the bottom lets you pin any metric, report, or entity for one-click access.

Customize your visualizations

Rolling calendar periods: Set visualizations and report filters to track current periods, which will update automatically as each new period begins. We've also added the last completed periods (last week, month, quarter, year) for snapshots of finished periods.

To date comparisons: A single click now lets you align comparisons to matching points in time. In the options from any visualization(charts, tables, big numbers and widgets), you can choose whether the comparison period should be the full period or to date. This is availiable for metrics with a daily time grain.

Table period-over period comparisons Period-over-period comparisons are now also available in report tables.

Steep lets your whole organization work from the same trusted metrics and semantic model defined by your data team. The Steep MCP extends that power beyond Steep, into the AI tools and agents you already use every day.

Your data, where you work

Connect any MCP-compatible client to your Steep workspace and query your metrics directly from Claude, Cursor, Codex, VS Code, and more. Browse the metric catalog, query metric and target data, and explore your workspace without switching context.

Governed by default

Every query runs through the same semantic layer and permissions model that powers Steep. Members connect with their own Steep credentials via OAuth, so the AI sees exactly what the member is allowed to see, nothing more. Your data team stays in control. Also works with row-level security.

Getting started

The Steep MCP server is hosted at https://mcp.steep.app/mcp. Authentication is handled through OAuth, and your agent will only see data you have access to in Steep.

Learn more →

Row-level security (RLS) lets workspace admins control which rows of data each member can see.

Define who sees what

Admins can now set access policies directly on any module in Steep's semantic model. A policy filters the data a member sees based on their identity, so an account manager only sees data for their own accounts, or a regional lead only sees data for their market. The policy applies automatically across every metric, entity, and report built on that module.

User-level and custom attribute access

Policies can be set based on individual user email or custom attributes. Define a table mapping each member's email to their attributes, then set policies to filter by those attributes. Policies work with any dimension in your data, whether that's market, region, manager email, or any custom attribute.

Always consistent, always filtered

Once a policy is in place, members always see filtered data, whether they're exploring a metric, viewing a report, or using Steep AI. Members are informed when they're seeing a filtered view. Admins always see everything.

Availability

Row-level security is available on Enterprise plans.

Learn how to get started →