--- sourceDocument: Zurich Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/zurich/intelligent-experiences Release : - zurich ft:locale : - en-US ft:publication_title : - Zurich Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Group Action Framework # Group Action Framework {#ariaid-title1} Release version: Zurich Updated July 21, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 3 minutes to read Summarize ![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete. ## Summary of Group Action Framework The Group Action Framework (GAF) is an advanced intelligence feature within the ServiceNow AI Platform that clusters related records---such as incidents, cases, and knowledge base articles---and applies actions to them using large language models (LLMs). It enhances AI agents and generative AI capabilities by identifying representative records from clusters, improving the quality and consistency of AI outputs while reducing the cost of LLM calls. GAF efficiently scales to handle large datasets by focusing processing on representative records. Show full answer Show less GAF operates through two main processes: grouping, which clusters similar records, and actioning, which maps new records to these clusters and selects representative records. Topic-labeling during setup assigns human-readable labels to clusters, aiding identification. ## Key Features * **Modular Skills:** GAF uses several specialized skills---grouping, topic-labeling, action strategy, action mapper, and action reducer---to manage clustering and summarization tasks. These skills work exclusively within GAF and cannot be used independently in custom workflows. * **Integration with AI Search:** GAF leverages AI Search to enhance clustering effectiveness and serves as a fallback when no GAF results are found. Enabling AI Search boosts clustering capacity up to 500,000 records and improves response times. * **Flexible Configuration:** The Grouping inputs configuration allows customers to tailor clustering behavior by specifying the source table, fields for clustering, filters, and options like taxonomy usage and HTML preprocessing. Dimensionality reduction and clustering parameters (UMAP and HDBScan) provide control over how records are compared and clustered. * **Scalability and Efficiency:** By focusing on representative records, GAF reduces LLM call costs and supports large-scale data processing, with default parameter settings suitable for most use cases. ## Practical Guidance for Customers * Ensure your dataset contains at least 2,000 records after filtering to enable effective clustering. * Enable HTML preprocessing if your source records include HTML content to improve clustering accuracy. * Use the default UMAP and HDBScan parameters initially; adjust only if you need to refine cluster size or similarity thresholds based on your data. * Monitor GAF activity and troubleshoot issues using the Generative AI Log and system logs filtered by GAF scope. * Note that GAF currently does not support domain separation, which may affect multi-domain implementations. ## Expected Results * Implementing GAF will lead to more consistent and higher-quality AI-driven actions by leveraging the best examples from grouped records. Customers will experience reduced operational costs related to LLM usage and improved scalability when handling large volumes of records. The framework's modular skill design and AI Search integration further enhance performance and adaptability to various data sets. Group Action Framework (GAF) is an intelligence feature on the ServiceNow AI Platform that groups related records and applies actions to them using LLMs. ## GAF overview GAF is composed of two processes. The grouping process identifies clusters of similar records (incident, cases, KB articles, and the actioning process maps new records to clusters and selects the representative record. Topic-labeling occurs during the setup process and labels the different clusters, which form the Description field of records on the GAF record groups \[sn_gaf_record_group\] table. GAF processes together benefit your AI agents and generative AI features in multiple ways. * Improves consistency and quality of agentic and generative AI features by using the best examples from groups of records. * Reduces the cost of LLM calls by only executing on the representative records. * Scales to accommodate large amounts of data because selected records can represent any size cluster. ## Skills used in GAF Multiple skills are involved in GAF setup and execution. They are modular, so not all executions will use all skills, but they can be used together in tandem. These skills are used exclusively for GAF and currently cannot be included on their own in custom agentic workflows. Grouping skill : Clusters related records using machine learning techniques. Topic-labeling skill : Adds human-readable names to the clusters using an LLM to make the clusters easier to identify. Action strategy skill : Selects representative records from each cluster for the mapper and reducer skills to use. Action mapper skill : Runs LLM inference calls for the selected representative records, producing a record summary for the selected records. Action reducer skill : Uses the generated summaries created by the mapper skill to produce a single summary for the entire cluster. ## GAF and AI Search GAF uses AI Search to improve its effectiveness and uses it as a fallback option in case GAF does not return any results. When AI Search is enabled, then GAF can utilize its optimized prediction. The optimized prediction feature increases clustering capacity up to 500,000 records and improves recall speed. See [Install AI Search](https://www.servicenow.com/docs/access?context=install-now-assist-ais&version=zurich&pubname=zurich-platform-administration&ft:locale=en-US) and [Set up AI Search for Group Action Framework](https://www.servicenow.com/docs/bG9L4EfjRtLg_Ym3mytZtA "Configure AI Search to enable Group Action Framework (GAF) to improve quality and consistency of agentic AI and generative AI on the ServiceNow AI Platform.") for more information on configuring AI Search for GAF. ## Grouping inputs When you configure GAF, the Grouping inputs record in the Now Assist Skill Config Var Set defines what records are clustered and how clustering behaves. The default values work for most configurations, but the following parameters are available if you need to adjust them. Table : The source table whose records are clustered. For example, the Incident \[incident\] table for ITSM. Fields : The field or fields used as the basis for clustering. GAF compares the content of these fields across records to identify similar ones. Filter : Conditions that determine which records from the source table are included in the grouping. You should have at least 2,000 records after filters are applied for clustering to complete successfully. Use taxonomy : When enabled, applies a taxonomy to improve the categorization of clusters. HTML Preprocessing : When enabled, strips HTML markup from field content before clustering. Enable this if your source records contain HTML-formatted text. Dimensionality reduction parameters (UMAP) : Controls how GAF compares records to each other before clustering. The n_neighbors parameter \[2--100\] sets how many similar records GAF considers when deciding which cluster a record belongs to. The n_components parameter \[5--100\] sets how many characteristics of each record GAF tracks during that comparison. Clustering parameters (HDBScan) : Controls how clusters are formed from the compared records. The min_samples parameter \[2--10\] sets how many similar records must exist before GAF treats a pattern as a real cluster rather than noise. The min_cluster_size parameter \[2--100\] sets the minimum number of records required to form a cluster. The cluster_selection_epsilon parameter \[0.01--0.99\] controls how similar two clusters need to be before GAF merges them into one. Note: The default values for UMAP and HDBScan parameters work for most configurations. Larger, denser clusters represent more common issue patterns and are surfaced more frequently. GAF's retrieval logic also handles smaller clusters, so less common patterns are still accessible. ## Diagnosing and troubleshooting GAF To find logs where GAF is used on your instance, go to the Generative AI Log \[sys_generative_ai_log\] table and filter based on the skill that used GAF. You can also filter the Log \[syslog\] table for the scope containing sn-gaf. Actions performed by skills, AI agents, and agentic workflows that use GAF all generate logs. For more information about common errors and possible resolution steps, see [Troubleshooting GAF](https://www.servicenow.com/docs/wQgp8kfDVwLUuptUPm6Wpg "Troubleshoot common errors associated with configuring GAF, such as failed action strategy job trigger or the scheduled job failing to execute."). ## Additional information GAF does not support domain separation at this time.