Grid82
grid82.comJoin the waitlist
BuildStudio assistant

Studio assistant

Ask the Studio assistant to model tables, build pages, adjust permissions, or import spreadsheets using explicit change proposals.

The Studio assistant lives inside the Studio beside your data, roles, interfaces, and workflows. Instead of blindly mutating your schema or deleting data, it works on one core principle: the assistant proposes, you apply.

What the Studio assistant can build

  • Data models. Design multi-table schemas (Companies, Contacts, Deals) with typed fields, symmetric links, rollups, and formulas in a single atomic proposal.
  • Permissions and access reviews. Draft new roles, add record filters or field-level edit masks, and run rules.simulate to verify what a role sees before modifying anything.
  • Interface pages. Generate React code using @grid82/sdk, @grid82/ui, and @grid82/blocks, compile it against real SDK types, inspect sampled records, and open a version preview for you to publish.
  • TypeScript automations. Write workflows, check them against the workflow compiler (workflows.check), run safe simulated tests (workflows.test), and hand the working draft to you to activate.
  • Spreadsheet imports (up to 25 MB). Drop a .csv, .tsv, .xlsx, or .json file into chat. The assistant profiles columns in a sandbox, proposes a field mapping for confirmation, and imports records in batches of up to 500 without stuffing raw records into the prompt context.

Propose, review, apply

  1. Every write proposed by the assistant renders an interactive approval card showing the exact action and target (for example, adding 4 fields to Deals or creating a Sales Rep role).
  2. Destructive proposals (dropping a table, field, or deleting records) highlight in red and require explicit confirmation.
  3. Every applied proposal is stamped as a revertible changeset in the app’s Log tab, with a snapshot taken before destructive schema changes.

Models and AI credits

Assistant turns consume your organisation’s AI credits (10,000 credits = $1.00 list model price). On Pro and Custom plans, builders can choose which model presets are available and assign monthly per-role AI budgets for Runtime users under Settings.

Use these docs with your AI tools

An AI agent can read this documentation directly. You do not need an account or an API key. Everything here is public and read-only.

Query these docs via MCP

Recommended

Add this server to Claude, Claude Code, Cursor, Mistral, or any tool that supports MCP. Your agent can then search Grid82 documentation and read it in full, instead of answering from memory.

https://grid82.com/docs/mcp
  • searchFind the passages that answer a question.
  • fetchRead one page in full, as Markdown.
  • list_pagesSee every page in this documentation.

Query these docs over HTTP

The same tools also work as plain web requests. Use this for scripts, or for any tool that does not support MCP. There is one endpoint per tool. Arguments go in the query string, and the answer comes back as JSON.

https://grid82.com/docs/api/docs/search?query=custom+domain

Read the OpenAPI description. It is built from the same definitions as the tools, so it always matches what the endpoints do.

Read these docs as Markdown

Add .md to any page URL to get its Markdown source. You can also send the headerAccept: text/markdown to the page URL itself.

To read the whole documentation in one file, open llms-full.txt. For a short index of every page, open llms.txt.