Skip to main content

Search Anywhere Framework 6.2 release

November 13, 2026
On November 2, 2026 we shipped SAF 6.1. In this article we walk through the main changes this version brings. For the full list of changes, see our documentation.

AI assistant

Search Anywhere Framework now includes an AI assistant, a chat interface for working with data. Describe a task, and the assistant selects operations, queries data sources and the knowledge base, and prepares a response.
The assistant answers questions about indexes, fields, and platform objects and analyzes events for a specified period. It creates and explains SAFL queries; you can edit and run a suggested query directly in the conversation. Results are displayed in interactive cards with tables and visualizations.

User Behavior Analytics

The User Behavior Analytics module has been redesigned. An object's risk score is now broken down by individual rule contributions, and related detections are grouped into anomalies.
Risk scores now use a 0-100 scale, and the Why This Score page shows each rule's contribution. Watchlists have been added: important objects in a watchlist receive a risk-score bonus or multiplier.

Broker

Broker is a new messaging mechanism in Search Anywhere Framework. Modules send events to it, such as an incident being opened, a risk score changing, or an asset being updated. The broker associates each event with a host, account, or other entity. The object card brings together information from all sources and the object's relationships.

Data Storage

Search Anywhere Framework now supports connections, data units, and search spaces. These make it possible to add ClickHouse alongside OpenSearch and search both storage systems in a single query without depending on the physical location of the data.
A search space combines data units from OpenSearch and ClickHouse, such as recent events and an archive. A query addresses it by name, and processing runs on the storage side.

Active Actions

Active Actions are now shared across the platform: configure each action once and use it in different modules. Actions can be run from scheduler jobs, manually for one or more incidents, in workflow transitions, and in SLA.

Database Observability

The new Database Observability module monitors PostgreSQL health and incorporates DB clusters and instances into Search Anywhere Framework operational processes. It collects telemetry from system views, Patroni, PgBouncer, and logs and links it to Inventory assets, the Service Monitor Toolkit health model, and Incident Manager cards.
The module includes eight PostgreSQL operations dashboards and 28 jobs, 24 of which register incidents for events such as instance unavailability, connection saturation, locks, and replication failures. Agentless collection is configured on the database server.

Interface and Dashboards

The interface appearance has been updated for a consistent look and behavior across all sections.
Scheduled PDF export of dashboards is available, with the status of the five latest runs; regular exports are also faster. Running visualizations can be stopped or restarted all at once, and filter application can be deferred until all values are entered.

Job Scheduler

Suppression can be configured for an individual event field value, such as a specific host. You can also configure an exception so that a job always triggers for a matching event.
The Send E-mail active action lets you select a sender for an individual job, and the webhook action can now send requests through an HTTP proxy.

Incident Manager

Incident comments and files can now be edited and deleted. All Inventory information is now visible directly in the incident card.

Inventory

Watchlists have been added: named sets of asset objects for use by other modules. Their composition is defined by a rule and can be supplemented with pinned objects. Repeated asset collection is faster, and unchanged data is no longer overwritten.

AI Observability

The AI Observability module now provides organization-level Claude Code usage analytics: members and subscription seats, work outcomes, spending, and subscription limits. Five analytics dashboards have been added, and subscription alerts register incidents when a limit window is exhausted or limit data collection stops.

AI Security

The AI Security module now performs semantic checks of LLM prompts and can detect prompt injection even when an attacker changes the wording. It uses a local embedding model fine-tuned on examples of attacks and safe prompts in Russian and English.

Cyber Security

More than 200 detection rules have been added to the Cyber Security module for Windows and Active Directory, Linux, Kubernetes, and the web perimeter. The module now contains 713 rules covering 126 MITRE ATT&CK techniques and sub-techniques. Ready-to-use data collection configurations are available for all nine sources, and the incident card now includes an investigation playbook.

If you are interested in the Search Anywhere Framework, you can contact us to discuss the details 🔥