# Cloudsquid docs ## Docs - [cloudsquid Documentation](https://docs.cloudsquid.io/index.md): AI agents that work your finance and operations processes — with your SOPs, your data, and your approval. - [Quickstart: your first agent-worked process](https://docs.cloudsquid.io/quickstart.md): From empty project to an agent-worked, human-approved process in about 15 minutes. - [Projects](https://docs.cloudsquid.io/concepts/projects.md): A project is the workspace for one domain of work — its files, tables, SOPs, integrations, and the agent that works them. - [Tables: reconcile, storage, extraction](https://docs.cloudsquid.io/concepts/tables.md): Reconcile tables run your processes, storage tables hold your master data, extraction tables structure documents at volume. - [SOPs: teaching the agent your process](https://docs.cloudsquid.io/concepts/sops.md): Your standard operating procedure as a Markdown file the agent follows — readable, diffable, approvable, and written together with the agent. - [The improvement loop](https://docs.cloudsquid.io/concepts/improvement-loop.md): Review feedback flows back into the SOP — the process gets better exactly where it failed, and every change is documented and approved. - [From audit to prevention](https://docs.cloudsquid.io/concepts/audit-to-prevention.md): The adoption path in three stages — start read-only on historical data, turn findings into recoveries, then run the same checks continuously on live events. - [The agent runtime](https://docs.cloudsquid.io/concepts/agent-runtime.md): Each agent works in its own environment — SQL over granted tables, project files, integration tokens, and the ability to run code when the task calls for it. - [Review & approvals](https://docs.cloudsquid.io/concepts/review-approvals.md): Statuses, assignment, evidence, and approval gates — with an approval agent for the routine cases and humans for the exceptions. - [Integrations](https://docs.cloudsquid.io/concepts/integrations.md): Workflows for deterministic plumbing, agent tokens for contextual action — and how to choose between them. - [Data access & governance](https://docs.cloudsquid.io/concepts/governance.md): Per-table grants, approval gates, a full audit trail, zero retention, SOC 2, ISO 27001, and EU data residency. - [Skills](https://docs.cloudsquid.io/concepts/skills.md): Packaged instructions, reusable code, and templates that teach a project a new capability. - [MCP servers](https://docs.cloudsquid.io/concepts/mcp-servers.md): Connect external MCP servers to extend what your project's agent can reach. - [Cookbooks](https://docs.cloudsquid.io/cookbooks/index.md): Complete recipes for real finance and operations processes — each with a copy-paste starter SOP, sample data, and a full walkthrough. - [Run an audit](https://docs.cloudsquid.io/cookbooks/run-an-audit.md): Point an agent at 12–24 months of your own AP history, read-only, and get evidence-backed findings — duplicates, unapplied credits, split invoices, bank-detail changes. - [Order processing: PO matching](https://docs.cloudsquid.io/cookbooks/po-matching.md): Purchase orders arrive in every shape. Match the buyer to customer master, line items to item master, resolve shipping, draft the confirmation — with a starter SOP you can copy. - [Invoice automation: vendor invoice audit](https://docs.cloudsquid.io/cookbooks/invoice-audit.md): Cross-reference vendor invoices against POs and receipts — catch duplicates, price and quantity mismatches, and missed credits, with a starter SOP you can copy. - [Quickstart: extraction](https://docs.cloudsquid.io/quickstart-extraction.md): Turn a batch of documents into structured rows — as its own job, or as input to a reconcile process. - [Extraction pipelines](https://docs.cloudsquid.io/concepts/pipelines.md): Model configurations for extraction tables and the extraction API — choose between cloudsquid-flash and cloudsquid-pro based on your accuracy and speed requirements. - [Async Run Pattern](https://docs.cloudsquid.io/concepts/async-run-pattern.md): Upload a file, start an AI run, and poll for results — the standard pattern for extraction at scale. - [Developer Setup](https://docs.cloudsquid.io/development.md): Get your API key and make your first API call. - [API Introduction](https://docs.cloudsquid.io/api-reference/introduction.md): Base URL, authentication, and your first API call. - [Create a New Project](https://docs.cloudsquid.io/api-reference/projects/post-projects.md): Create a new Project. - [Get All Projects](https://docs.cloudsquid.io/api-reference/projects/get-projects.md): Get all projects in the organisation. - [Delete a Project](https://docs.cloudsquid.io/api-reference/projects/delete-projects.md): Delete a project. - [Upload File by Path](https://docs.cloudsquid.io/api-reference/filesystem/upload-file-by-path.md): Upload a file to a path inside the project filesystem. Parent folders are created automatically. - [Read by Path](https://docs.cloudsquid.io/api-reference/filesystem/read-by-path.md): Resolve a path: returns a presigned URL for a file, or a listing for a folder. - [Delete by Path](https://docs.cloudsquid.io/api-reference/filesystem/delete-by-path.md): Delete the file or folder at a path. Folders are deleted recursively. - [Create Table](https://docs.cloudsquid.io/api-reference/tables/create-a-new-table.md): Create a new table (extraction, reconciliation, storage). - [Get a Table](https://docs.cloudsquid.io/api-reference/tables/get-projects-tables.md): Retrieve a table and its metadata. - [List all Tables](https://docs.cloudsquid.io/api-reference/tables/get-projects-tables-1.md): List all tables inside the project - [Delete Table](https://docs.cloudsquid.io/api-reference/tables/delete-projects-tables.md): Delete table with all the data inside. - [Get Table Schema](https://docs.cloudsquid.io/api-reference/tables/get-projects-tables-schema.md): Retrieve the data schema for a table. - [Update Table Schema](https://docs.cloudsquid.io/api-reference/tables/post-projects-tables-schema.md): Update the data schema for a table. - [Get Table Data](https://docs.cloudsquid.io/api-reference/tables/get-projects-tables-data.md): Retrieve all data from a table. - [Start AI run (asynchronous)](https://docs.cloudsquid.io/api-reference/tables/request-starts-the-analyze-process-for-a-table.md): Start AI processing for a row in an extraction or reconciliation table. This is an asynchronous operation; use the returned run_id to check status and retrieve results. - [Get Run Status and Result](https://docs.cloudsquid.io/api-reference/tables/get-ai-run-status-&-result.md): Poll an async AI run for its status and retrieve results when complete. Returns the current status of the run, and if the run is done, includes the extracted data or reconciliation results. - [Create a Reconciliation Row](https://docs.cloudsquid.io/api-reference/tables/create-a-reonciliation-task.md): Create a Task without executing it. - [Reconcile Data (synchronous)](https://docs.cloudsquid.io/api-reference/unified/synchronous-reconciliation-run.md): Run reconciliation on data. - [Upload File to Extraction Table](https://docs.cloudsquid.io/api-reference/tables/upload-a-new-file-into-a-table.md): Upload a file to an extraction table to create a new row associated with it. This doesn't start an extraction run - use the /run endpoint to start processing the file after uploading. - [Data Extraction (synchronous)](https://docs.cloudsquid.io/api-reference/unified/synchronous-extraction-for-a-file-end-to-end.md): Upload a file and extract its content. - [Upload CSV to Storage Table](https://docs.cloudsquid.io/api-reference/tables/put-projects-tables.md): Overwrite or append csv data to a storage table. - [Upload Data into Table](https://docs.cloudsquid.io/api-reference/tables/post-projects-tables-data.md): Upload JSON data into a table. ## OpenAPI Specs - [public_api](https://docs.cloudsquid.io/api-reference/public_api.yaml) - [openapi](https://docs.cloudsquid.io/api-reference/openapi.json) ## Optional - [Blog](https://cloudsquid.substack.com/)