> For the complete documentation index, see [llms.txt](https://docs.syntho.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.syntho.ai/release-notes.md).

# Release notes

Use this page to track changes per Syntho release. New releases are listed first.

{% hint style="info" %}
Upgrading a self-hosted deployment? Use the matching guide:

* [Upgrade (Docker Compose)](https://docs.syntho.ai/deploy-syntho/deploy-syntho-using-docker/upgrade.md)
* [Upgrade (Kubernetes / Helm)](https://docs.syntho.ai/deploy-syntho/deploy-syntho-using-kubernetes/upgrade.md)
  {% endhint %}

#### What we include

* **Added**: new features.
* **Improved**: UX, performance, and maintainability changes.
* **Fixed**: bug fixes.
* **Security**: security fixes, CVEs, and dependency upgrades.
* **Breaking changes**: anything that requires action after upgrading.

#### Releases

#### 2026.2.3

**Release date: 2 November 2026**

This release speeds up job cancellation and aligns consistent replacements across free text and structured columns.

<details>

<summary>Changes</summary>

#### Breaking changes

* With consistent mapping enabled, the same detected value receives the same replacement across entities, columns, and tables when the generator, settings, and engine seed match. Regenerating data after upgrading can produce different replacements from earlier runs. See [Keep replacements consistent](https://docs.syntho.ai/configure-a-data-generation-job/configure-column-settings/mask/text/automatic-pii-discovery-and-de-identification-in-free-text-columns#keep-replacements-consistent).

#### Improved

* Cancellation restores indexes and constraints across tables in parallel and shows restoration progress. To skip remaining work, choose **Cancel without restoring destination** or, during cancellation, **Skip restoring destination**. The current database statement finishes first. Check and restore any remaining destination constraints or indexes before using the database.
* Free-text lookup rules run with or without a detection model. Switching models updates the available entities and preserves unsaved edits. If an entity fails validation, Syntho opens it and scrolls to the error. See [Choose the locale and detection model](https://docs.syntho.ai/configure-a-data-generation-job/configure-column-settings/mask/text/automatic-pii-discovery-and-de-identification-in-free-text-columns#choose-the-locale-and-detection-model).
* Database connectors now support special characters in schema, table, column, and constraint names.

#### Fixed

* Tables in a cancelled job could still appear to be in progress.
* Calculated columns now handle mock generators with different display names correctly. Use [VARP](https://docs.syntho.ai/configure-a-data-generation-job/configure-column-settings/calculated-columns#varp) for population variance and [VARS](https://docs.syntho.ai/configure-a-data-generation-job/configure-column-settings/calculated-columns#vars) for sample variance.
* Switching generators clears unused rare-category settings. Selecting an invalid connector schema shows the correct error.
* Fixed an issue that could prevent spaCy detection models from loading.

</details>

#### 2026.2.2

**Release date: 26 October 2026**

This release adds two Databricks authentication options and improves configuration of sensitive entities, generators, and calculated columns.

<details>

<summary>Changes</summary>

#### Added

* Connect to Databricks using a federated identity or a service principal client secret. Connection tests highlight the relevant field for host, catalog, warehouse, and cluster errors. See [Databricks authentication](https://docs.syntho.ai/setup-workspaces/create-a-workspace/connect-to-a-database/databricks#authentication).
* Select and remove multiple sensitive entities in one action. See [Apply bulk actions and remove entities](https://docs.syntho.ai/configure-a-data-generation-job/configure-column-settings/mask/text/automatic-pii-discovery-and-de-identification-in-free-text-columns#apply-bulk-actions-and-remove-entities).

#### Improved

* Generator validation identifies missing formula parameters and explains when generated values are incompatible with a column’s data type.

#### Fixed

* **Select all** includes every schema in databases with more than 100 schemas.
* **From scratch** workspaces wait for a sensitivity scan before suggesting generators.
* Custom formulas for consistent mapping allow **Apply on generated data** to be selected before entering the formula. The toggle is hidden for current-column mapping. See [Choose the mapping input key](https://docs.syntho.ai/configure-a-data-generation-job/configure-column-settings/consistent-mapping#choose-the-mapping-input-key).
* The [BASE function](https://docs.syntho.ai/configure-a-data-generation-job/configure-column-settings/calculated-columns#base) preserves alphabetic digits such as A–F in hexadecimal.
* Workspace actions reflect permissions after loading. Enabling a foreign key in the **Foreign Keys** tab preserves your saved preference.

</details>

#### 2026.2.1

**Release date: 19 October 2026**

This release expands free-text de-identification and Main Hub filtering, improves workspace recovery, and fixes an issue with passwords in startup logs.

<details>

<summary>Changes</summary>

#### Security

* Syntho now masks source and destination database passwords that could previously appear in startup logs.

#### Added

* Define custom sensitive entities and configure how Syntho detects and handles them in text columns. See [Create a custom entity](https://docs.syntho.ai/configure-a-data-generation-job/configure-column-settings/mask/text/automatic-pii-discovery-and-de-identification-in-free-text-columns#create-a-custom-entity) and [Choose an action for each entity](https://docs.syntho.ai/configure-a-data-generation-job/configure-column-settings/mask/text/automatic-pii-discovery-and-de-identification-in-free-text-columns#choose-an-action-for-each-entity).
* Filter Main Hub columns by additional properties, constraints, and keys. See [Filter columns](https://docs.syntho.ai/configure-a-data-generation-job/privacy-dashboard#filter-columns).

#### Improved

* Seeded mock generators continue their sequence across batches. Regenerating data with the same seed can produce different values from earlier versions.
* Numeric generators give a clearer warning when generated values exceed the destination column’s range and are clipped.
* You can view workspace details during generation. Workspace availability and the latest job status are shown separately.

#### Fixed

* Failed workspace imports roll back partial changes. Invalid connection edits preserve the existing workspace configuration.
* Table and column previews now agree in cases where they previously differed. Table View refreshes after you restore defaults from Main Hub. See [Preview generated data](https://docs.syntho.ai/configure-a-data-generation-job/configure-table-settings#preview-generated-data).
* Editing a formula could close column settings, and background notifications could interrupt workspace editing.
* Successful jobs that truncated destination tables could appear as **Completed with issues**.
* Fixed redirect loops during sign-in and when opening an unavailable workspace.

</details>

#### 2026.2.0

**Release date: 10 September 2026**

Syntho 2026.2.0 introduces Table Preview to inspect generated data while configuring your workspace, more flexible consistent mapping, and parallel database writes. It also reduces generation memory usage and improves connector compatibility and job reliability.

<details>

<summary>Changes</summary>

#### Added

* **Configurable consistent mapping input.** Choose the current column, another column in the same table, or a custom formula as the mapping input key. This lets you keep generated values consistent for a shared identifier or normalize values before mapping. The current column remains the default. See [Consistent Mapping](https://docs.syntho.ai/configure-a-data-generation-job/configure-column-settings/consistent-mapping.md#choose-the-mapping-input-key).
* **Table Preview.** Preview generated data directly in Table View before running a full generation job. Use the **Preview** toggle to switch between transformed values and original source data for up to **100 rows**. Preview is enabled by default for eligible tables and reflects the table mode and configured column generators. Columns without a configured generator retain their original values. Where preview is unavailable or results may differ from full generation, Syntho displays information or warnings. See [Preview generated data](https://docs.syntho.ai/configure-a-data-generation-job/configure-table-settings.md#preview-generated-data).
* **Parallel writes to the same table.** Syntho can now write multiple batches to one table concurrently. Tune the maximum number of connections to balance throughput, memory usage, and database load. See [Advanced generation settings](https://docs.syntho.ai/configure-a-data-generation-job/generation-and-validation/view-and-adjust-generation-settings.md#advanced-generation-settings).

#### Improved

* Reduced peak memory usage during table generation, including Parquet output to local storage, ADLS, and S3. Repeated out-of-memory retries are now limited.
* Enabled SQL Server’s fast batch-writing mode by default. See [Microsoft SQL Server](https://docs.syntho.ai/setup-workspaces/create-a-workspace/connect-to-a-database/microsoft-sql-server.md#fast-execute-many).
* Standardized internal handling of complex Databricks data types as JSON. See [Databricks and supported data types](https://docs.syntho.ai/setup-workspaces/create-a-workspace/connect-to-a-database/databricks.md#supported-data-types).
* Improved handling of schema-name capitalization across database connectors.
* Added timeouts when loading database metadata. Tables whose metadata loading times out are marked unhealthy and excluded from processing, preventing stalled database operations from hanging indefinitely.

#### Fixed

* Fixed SQL Server writes involving `DATETIMEOFFSET` with fast batch writing enabled and string parameters for `hierarchyid`.
* Fixed Oracle query execution when a schema name is specified in the connector. See [Oracle connection setup](https://docs.syntho.ai/setup-workspaces/create-a-workspace/connect-to-a-database/oracle.md).
* Fixed suggested generators receiving unsupported uniqueness parameters, which could prevent workspace creation.
* Fixed missing data-source links for suggested generators that require them.
* Fixed inconsistent generator status and incorrect counts when rejecting suggestions in bulk in Main Hub.
* Corrected final job status handling and added rollback of applied database capabilities when generation is cancelled.
* Disabled cancellation while workspace synchronization changes are being applied. See [Source database validation and synchronization](https://docs.syntho.ai/configure-a-data-generation-job/generation-and-validation/validate-and-synchronize-workspace.md).

#### Breaking changes and upgrade actions

**Review workspace performance settings after upgrading.** The migration:

* Resets the default batch size for every workspace to **500,000 datapoints**, including previously customized values.
* Initializes `default_parallel_writing` to `true`.
* Removes `default_simultaneous_read_write`; its now always enabled.

A datapoint is one cell: rows × columns. Reapply any required batch-size tuning and review connection settings before running large workloads. See [Generation settings](https://docs.syntho.ai/configure-a-data-generation-job/generation-and-validation/view-and-adjust-generation-settings.md#advanced-generation-settings).

For self-hosted installations, follow the [Docker Compose upgrade guide ](https://docs.syntho.ai/deploy-syntho/deploy-syntho-using-docker/upgrade.md)or [Kubernetes / Helm upgrade](https://docs.syntho.ai/deploy-syntho/deploy-syntho-using-kubernetes/upgrade.md) guide.

</details>

#### 2026.1.17

**Release date: 21 August 2026**

Syntho 2026.1.17 improves workspace recovery, generator assignment, and generation progress reporting. It also ensures destination database validation is requested again after every generation job.

<details>

<summary>Changes</summary>

#### Improved

* **More actions for failed workspaces.** Workspaces that failed during creation now support Delete, Transfer ownership, and Share, alongside access to logs. See [View workspaces](https://docs.syntho.ai/setup-workspaces/view-workspaces.md).
* **Destination validation after generation.** After every generation job, whether successful or failed, Syntho requires destination database validation again before subsequent generation. See [Validate destination database](https://docs.syntho.ai/configure-a-data-generation-job/generation-and-validation/validate-and-synchronize-workspace-1.md).
* **Clearer table warnings.** The table sidebar now displays a warning icon only for tables with warnings. Other states use a neutral icon.

#### Fixed

* **Workspace import recovery.** Fixed failed imports leaving a workspace locked. Import errors are now passed to the interface so users can see why the operation failed. See [Import and export workspaces](https://docs.syntho.ai/setup-workspaces/import-and-export-workspaces.md).
* **Generator assignment.** Fixed suggested generators not being correctly assigned when processed in batches, and generators not being correctly marked as applied to a column. See [Main Hub](https://docs.syntho.ai/configure-a-data-generation-job/privacy-dashboard.md).
* **Generation progress updates.** Restored progress updates while data generation is running.
* **Workspace form layout.** Fixed the connection form being cut off when the workspace name field displayed a validation error, such as an existing workspace name.

</details>

#### 2026.1.16

**Release date: 21 August 2026**

<details>

<summary>Changes</summary>

#### Added

* **Dedicated text masking generators.** Shuffle, Rare Category Protection, and free-text sensitive-data obfuscation are now separate generators under **Mask**. Duplicate now focuses on copying values without transformation. See [Text de-identification generator](https://docs.syntho.ai/configure-a-data-generation-job/configure-column-settings/mask/text.md#free-text-pii-obfuscation).
* **Unified job logging.** Job logs now include task-level information, with improved capture of errors and more reliable job and task status updates when failures occur. See [Logs and monitoring](https://docs.syntho.ai/deploy-syntho/logs-and-monitoring.md).
* **Main Hub filters panel.** Access confidence score, sensitive/non-sensitive, and protected/unprotected filters from a dedicated filters button. See [Main Hub](https://docs.syntho.ai/configure-a-data-generation-job/privacy-dashboard.md).

#### Improved

* **Persistent generation settings.** Configure advanced generation defaults in Workspace settings for reuse across jobs. Values entered in the final generation step are also remembered when returning to that step for the same workspace. See [Workspace settings](https://docs.syntho.ai/setup-workspaces/workspace-default-settings.md).
* Improved database metadata loading performance, including batched row counting.
* Improved data-type mapping across connectors.
* Added job status to job summary details.
* Made sensitivity and foreign-key scan interactions more responsive.
* Added field-level connection errors to help identify incorrect database connection details.
* Reduced unnecessary health-check logs and workspace update messages.

#### Fixed

* Fixed AI synthesis settings sending cardinality and rare-category replacement values at the wrong configuration level.
* Fixed MySQL index management attempting to remove a unique index required by an auto-increment column.
* Fixed row-count settings not resetting correctly.
* Fixed unexpected schema changes appearing during workspace synchronization for columns excluded from writing. See [Source database validation and synchronization](https://docs.syntho.ai/configure-a-data-generation-job/generation-and-validation/validate-and-synchronize-workspace.md).
* Fixed workspace creation and update jobs not refreshing correctly in the jobs list.
* Fixed Main Hub actions marking or unmarking the wrong sensitive selections when filters were active.
* Removed generator suggestions for columns excluded from database writes.
* Restored missing generator suggestions after a manual sensitivity scan in From Scratch workspaces.
* Fixed foreign-key notifications and fallback error handling during row counting.
* Fixed sequence-value handling during categorical conversion.
* Fixed Ray dashboard loading behind a reverse proxy.
* Fixed the backend worker health check in Docker Compose deployments.

#### Breaking changes and upgrade actions

* **“Synthesize all” workspace initialization mode has been removed.** Existing workspaces using this mode are migrated to **De-identify**. Review affected workspace configurations after upgrading. See [Workspace modes](https://docs.syntho.ai/setup-workspaces/create-a-workspace/workspace-modes.md).
* **Text masking options have moved out of Duplicate.** Existing configurations are migrated to dedicated Mask generators. Review configurations that combined multiple legacy Duplicate options, especially Shuffle with sensitive-data obfuscation: the Shuffle migration removes the old obfuscation option. See [Duplicate](https://docs.syntho.ai/configure-a-data-generation-job/configure-column-settings/duplicate.md) and [Text de-identification generator](https://docs.syntho.ai/configure-a-data-generation-job/configure-column-settings/mask/text.md#free-text-pii-obfuscation).
* **The Generate key-generation method is now controlled by a feature flag and hidden by default.** Deployments requiring this method must enable `feature_key_generation_generate`.

</details>

#### 2026.1.15

**Release date: 6 June 2026**

<details>

<summary>Changes</summary>

**Improved**

* Updated Random Character Swap 2.0 to be case-insensitive w/ consistent mapping ON.
* Improved validation for generator schema parameters.
* Improved table validation by skipping unnecessary `n_rows` checks.
* Improved Parquet output handling for `INT64` precision.
* Renamed Redis-related artifacts to queue for clearer terminology.

**Fixed**

* Fixed date formulas in Computed mockers on `DATE` columns.
* Fixed handling of implied unique generators.
* Databricks: Updated token handling.

</details>

#### 2026.1.14

**Release date: 4 June 2026**

<details>

<summary>Changes</summary>

**Added**

* Added support for generating rows based on the source row count.

**Improved**

* Improved the job summary to make generation checks clearer.
* Improved column syncing performance by removing an unnecessary generator preview step.
* Simplified generation settings by removing the read random subset option.

</details>

#### 2026.1.13

**Release date: 29 May, 2026**

<details>

<summary>Changes</summary>

**Improved**

* Improved migration `bf5a008a9e78` to only consider `CURRENT` databases and safely remove stale rows.

**Fixed**

* Fixed an issue where the build artifact step did not use the specified version.

</details>

#### 2026.1.12

**Release date: 22 May, 2026**

<details>

<summary>Changes</summary>

**Improved**

* Avoided loading the full workspace when possible to improve the speed of workspace operations.

</details>

#### 2026.1.11

**Release date: 15 May, 2026**

<details>

<summary>Changes</summary>

**Improved**

* Enabled identity writing by default.
* Combined table warnings into a single warning tooltip.
* Improved application messaging for clearer and more consistent communication.
* Improved alignment of permission-limited action buttons across the UI.
* Improved tooltip visibility for excluded tables.
* Improved engine import performance by adding an index to the column configuration table.
* Read and write batch sizes are now unified into one parameter.

**Fixed**

* Fixed various small UI issues.
* Fixed duplicate owner handling.
* Fixed issues in custom string generation.
* Fixed job timestamp serialization in the jobs endpoint.

**Security**

* Fixed CVE-2026-39892.
* Fixed CVE-2026-40192.
* Fixed CVE-2026-3902.
* Fixed CVE-2026-28684.
* Fixed CVE-2026-33672.
* Fixed CVE-2025-69277.
* Fixed AIKIDO-2026-10385.
* Fixed AIKIDO-2026-10369.

</details>

#### 2026.1.10

**Release date: 13 April, 2026**

<details>

<summary>Changes</summary>

**Added**

* Datasource caching to improve performance and reduce repeated data fetching.

</details>

#### 2026.1.9

**Release date: 13 April, 2026**

<details>

<summary>Changes</summary>

**Added**

* Workspace export and import, making it easier to move workspace configurations between environments.
* Support for generating empty tables when needed.

**Improved**

* Main hub and Hash key generator are no longer marked as beta.
* Calculated columns behavior for `DATEDIFF` and `DATEADD`, including better handling of nullable columns, RAND-based intervals, pasted expressions, and int-like values generated by mockers.
* Generator selection in the table view, including better ordering and hiding generator types that are not compatible with the column data type.
* Workspace synchronization flow, including a reset of the active workspace after sync actions and fresher table data after updates.
* UI refinements across the platform, including improved hover tooltips, bulk include/exclude toggle alignment, table scrolling in sync mode, and icon sizing in job confirmation summaries.
* API notebook improvements.

**Fixed**

* An issue that could prevent a generator from being serialized.
* Datetime-like data clamping behavior.
* Decimal clamping validation.
* Computed formulas on nullable columns.
* Hardcoded sensitive-data modification for key columns.

**Security**

* Implemented CSP and Permissions-Policy headers.
* Fixed CVE-2026-27459.
* Fixed CVE-2026-30922.
* Fixed CVE-2026-4800.
* Fixed CVE-2026-32597.
* Fixed CVE-2026-22815.

</details>

#### 2026.1.8

**Release date: 27 March, 2026**

<details>

<summary>Changes</summary>

**Added**

* Workspace export and import functionality to move configurations between environments.

**Improved**

* Decimal clamping validation to ensure more accurate handling of numeric limits.

</details>

#### 2026.1.7

**Release date: 24 March, 2026**

<details>

<summary>Changes</summary>

**Added**

* Column Privacy Ranking in the privacy audit flow, to help prioritize columns based on privacy status.
* A warning for Databricks cases where a case statement result is truncated.
* Support for configuring the maximum parallel jobs through an environment variable.

**Improved**

* Target form validation in the generation flow.
* Capabilities handling for better overall performance.

**Fixed**

* Fixed update engine conditions for update engine jobs.

**Security**

* None.

</details>

#### 2026.1.6

Release date: **19 March 2026**

<details>

<summary><strong>Changes</strong></summary>

**Added**

* Support for configuring core application settings through environment variables.
* Initial supported variables: `DATABRICKS_READ_STMT_MAX_ATTEMPTS`, `DATABRICKS_READ_STMT_INITIAL_WAIT`, and `LOG_LEVEL`.

**Security**

* Fixed security issues.
* Addressed dependency advisories for: `CVE-2025-69223`, `CVE-2026-21441`, `CVE-2026-21226`, `CVE-2026-23490`, `CVE-2025-69277`, `CVE-2025-66034`, `CVE-2026-0994`, `CVE-2025-14550`, `GHSA-h25m-26qc-wcjf`, `CVE-2026-22036`, `CVE-2025-13465`, and `CVE-2026-24486`.

</details>

#### 2026.1.5

Release date: **19 March 2026**

<details>

<summary>Changes</summary>

**Added**

* **Databricks**: Added a retry mechanism with exponential backoff for warehouse reads to handle the 1-hour limit on available data chunks.

</details>

#### 2026.1.4

Release date: **16 March 2026**

<details>

<summary>Changes</summary>

**Added**

* Added support for the Generators domain model.
* Added a new sync condition to trigger source sync after target sync.

**Improved**

* Databricks: Added a timeout when retrieving statement results to improve connector reliability.
* Improved handling of target schema updates when connection details change.

**Fixed**

* Fixed an issue where the Noise generator could fail on decimal values.

</details>

#### 2026.1.3

Release date: **9 March 2026**

<details>

<summary>Changes</summary>

**Added**

* Added include and exclude states to table ordering for easier table selection management. This aligns with Syntho’s include/exclude table workflow in Table view.

**Improved**

* Removed subsetting-related code from Backend and CoreAPI to simplify internal maintenance. Syntho documents subsetting as a dedicated workflow, so this change appears to streamline separation of concerns.
* Databricks: Updated Warehouse ID handling. Syntho supports an optional Warehouse ID for Databricks workspaces, where it is recommended for faster and more stable querying.
* Added the missing `light_version` parameter on the engine repository call.
* Introduced the [Privacy audit report](https://docs.syntho.ai/configure-a-data-generation-job/privacy-audit-report.md).

**Fixed**

* Fixed an issue affecting custom string and Custom sampler behavior. Custom sampler is a documented generator in Syntho.
* Oracle: Removed an issue related to `DROP INDEX` compilation.
* Fixed a regression introduced in an earlier release.
* Fixed internal connector/backend behavior related to custom string and sampling configuration.

**Security**

* No CVE IDs were listed for this release.

</details>

#### 2026.1.2

Release date: **24 February 2026**

<details>

<summary>Changes</summary>

**Added**

* Added a substring method to version and build information to truncate long strings.

**Improved**

* Refactored API endpoints to use services instead of repositories, improving maintainability and separation of concerns.
* Databricks: Made the Warehouse ID parameter optional when configuring the connection.

**Fixed**

* MySQL: Fixed the query used to check `DROP INDEX` operations.

**Security**

* No CVE IDs were listed for this release.

</details>

#### 2026.1.1

Release date: **17 February 2026**

<details>

<summary>Changes</summary>

**Improved**

Implementation of data reading by utilizing Databricks API for better memory performance and faster data read.

</details>

#### 2026.1.0

Release date: **16 February 2026**

<details>

<summary>Changes</summary>

**Added**

* Job attachment support.
* Source sync when editing a job.
* Bulk selection toggle for all subcategories.
* GitBook AI assistant integration.
* Feature functionality management enabled by default.

**Improved**

* Faster engine settings update.
* Refactored engine and connection forms.
* Long table names now display with a middle ellipsis.
* Optimized CI/CD pipeline.
* Upgraded core Ray base image to `2.53.0`.
* Updated `oracledb` to the latest version.
* Removed unused packages in the core module.

**Fixed**

* Schema issues in status updates.
* Unstable schema views rendering.
* Workspace creation status updates.
* Capability selection reset after validation.
* Protected/unprotected key sensitive columns classification.
* Workspace sync issues when using a filesystem-based target connector.
* Default settings update.
* Job status issues.
* Inheritance issue in CoreAPI services.
* Generate page layout issue.

**Security**

* Improved security by addressing a template injection vulnerability in GitHub Workflows Action.

**Dependency advisories fixed**

* CVE-2025-69223
* CVE-2026-21441
* CVE-2026-21226
* CVE-2026-23490
* CVE-2025-69277
* CVE-2025-66034
* CVE-2026-0994
* CVE-2025-14550
* GHSA-h25m-26qc-wcjf
* CVE-2026-22036
* CVE-2025-13465
* CVE-2026-24486

**Breaking changes**

None.

</details>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.syntho.ai/release-notes.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
