Product updates

Add images and files to reports

Reports can now hold images and files alongside your existing blocks, so a screenshot, a mockup, or a supporting doc can live right in the report. Files can be dropped in directly or added as a block, and image blocks open full screen with the option to download. Free plans are capped at 10 MB per file; paid plans have no limit.

Upload files to Steep AI

You can now add images, PDFs, and text files as context for Steep AI, dropped in directly or added from the + button, one at a time or several together. Available on the United States model.

Choose your AI model region

Workspaces can now choose where their AI processing runs, United States or EU, and can update this at any time. The model itself is the same regardless of location.

Drill down from pivot tables and cohort tables into the row-level entities behind them - the same drill-down experience already available elsewhere in Steep, now extended to these two table types. Click any cell in a pivot or cohort table and select an entity to see the underlying data.

Targets in big number blocks

Big number blocks can now show progress against a target, right alongside the metric itself - no need to build a separate visualization just to see how a number compares to its goal.

Metric descriptions now support Markdown

Metric descriptions now render as Markdown, so you can use standard syntax to format them. Make your descriptions more readable by adding headings, formatting, links, lists, tables, code blocks and more. Steep support most basic syntax as well as tables and code blocks from the extended syntax.

The Steep API and MCP keep expanding. Reports join the programmatic surface, metrics get more precise endpoints and filters, and server-to-server integrations get a dedicated way to authenticate - all still governed by your semantic model.

Reports in the API and MCP: Create, list, and read reports programmatically - the same capabilities that power Reports in Steep AI.

Individual metric endpoint: Fetch a single metric with GET /metrics/:id, also available as a tool in the MCP.

Filter what you fetch: Filter the metrics list by an array of identifiers across list endpoints, and use the new parameters on /targets to get just the target series you need.

Explore the API reference →

Steep in the ChatGPT app store

Steep is now available directly in the ChatGPT app store - connect your workspace and query your governed metrics without leaving ChatGPT.

Steep in ChatGPT app store →

New authentication options

Confidential OAuth clients: A new way to authorize server-to-server integrations. Create a client with an ID and secret to connect trusted backend services to the Steep API or MCP server - no user in the loop. This also enables the Steep MCP server to be used with Gemini Enterprise.

Multiple API keys: Create several API keys per workspace, each with its own permissions - one key per integration, scoped to exactly what it needs.

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 →