SherloqData

Enables multiple team members to simultaneously write, edit, and execute SQL queries against connected databases within a shared workspace. The platform implements operational transformation or CRDT-based conflict resolution to merge concurrent edits, maintains a live execution context that reflects the latest query state, and broadcasts query results to all connected clients in real-time. This eliminates the need for manual query sharing via email or chat and ensures all collaborators work against the same query version and result set.

Maintains a complete version history of all SQL queries with Git-like branching semantics, allowing teams to create isolated query branches, merge changes, and revert to previous versions. Each query version is tagged with author, timestamp, and execution metadata. The system stores diffs at the query text level and tracks which team member executed which version against which database, creating an immutable audit trail for compliance and debugging. This is implemented as a dedicated version control layer separate from the query execution engine.

Allows queries to fetch data from external APIs (REST, GraphQL) and combine it with database query results. The platform provides a connector framework where users can define API endpoints, authentication, and response parsing. Query results can be exported to external systems (data warehouses, BI tools, cloud storage) via pre-built connectors or custom webhooks. Integration is configured through the UI without requiring code.

Provides workspace-level organization where teams can create isolated environments with separate databases, queries, and user access. Workspaces support multiple users with role-based access control (admin, editor, viewer). User provisioning can be automated via SAML/OAuth or managed manually. Workspace settings control features (caching, scheduling, integrations) and enforce organizational policies. Audit logs track all user actions within a workspace.

Enforces fine-grained access policies at multiple levels: database connections (which users can access which databases), query visibility (who can view/edit/execute specific queries), and data row/column access (via integration with database-native row-level security). The system implements a permission matrix where roles are assigned to users, and permissions are inherited hierarchically (workspace > database > query). Access decisions are evaluated at query execution time, preventing unauthorized data access even if a user has network access to the database.

Executes SQL queries against multiple database backends (PostgreSQL, MySQL, Snowflake, BigQuery, etc.) through a unified interface. The platform maintains persistent connection pools to each configured database, reusing connections across query executions to reduce latency. Query execution is asynchronous — the client submits a query and receives a job ID, then polls for results or subscribes to a WebSocket for real-time result streaming. The execution engine handles query timeouts, resource limits, and graceful error reporting.

Automatically caches query results in memory or persistent storage, allowing subsequent identical queries to return results instantly without re-executing against the database. The caching layer uses query text (with parameter normalization) as the cache key and respects user-defined TTLs (time-to-live). Teams can also explicitly materialize query results as temporary tables or snapshots for downstream use. Cache invalidation is manual (user-triggered) or automatic (based on TTL or detected schema changes).

Allows queries to be written with named parameters (e.g., `WHERE date >= :start_date`) that can be bound at execution time without modifying the query text. The platform provides a parameter UI where users input values, and the execution engine substitutes parameters into the query before sending to the database. Templates can be saved with default parameter values, enabling non-technical users to execute complex queries by simply filling in a form. Parameter types (date, number, string) are validated client-side and server-side.

Allows users to attach rich documentation to queries, including descriptions, expected output schemas, usage examples, and inline code comments. Documentation is versioned alongside query code and searchable. The platform supports Markdown formatting for documentation and can auto-generate schema documentation from query result metadata. Annotations can be added to specific query sections (e.g., 'this JOIN is expensive, consider materialization'). Documentation is displayed in the IDE alongside the query and is accessible to all team members.

Enables users to schedule queries to run on a recurring basis (hourly, daily, weekly, monthly) or on-demand via webhooks. Scheduled queries execute asynchronously and results are stored in a results table or exported to external systems (email, Slack, S3, data warehouse). The scheduling engine supports cron expressions for complex schedules and includes retry logic for failed executions. Execution history is tracked with logs and error messages. Scheduled queries inherit the permissions of the user who created them, ensuring data access controls are maintained.

Tracks data lineage by analyzing query dependencies — which tables/columns are read by each query and which downstream queries depend on those results. The system builds a directed acyclic graph (DAG) of query dependencies and can visualize the lineage. Impact analysis allows users to see which queries will be affected if a table schema changes or if a source query is modified. Lineage is automatically extracted from query text parsing (table/column references) and can be manually annotated for complex cases.

Analyzes query execution plans to identify performance bottlenecks (full table scans, missing indexes, inefficient joins). The system fetches the query plan from the database, parses it, and generates optimization suggestions (e.g., 'add index on column X', 'rewrite JOIN to use hash join'). Suggestions are ranked by estimated performance impact. The platform also tracks query execution time over time and alerts users if a query's performance degrades. Performance metrics are stored and can be compared across query versions.