Gemini Enterprise Agent Platform and zero data retention  |  Google Cloud Documentation (https://docs.cloud.google.com/vertex-ai/generative-ai/docs/data-governance ; rewritten summary of https://docs.cloud.google.com/gemini-enterprise-agent-platform/resources/zero-data-retention) citeturn148view1 [wordlim: 200] Crawled: today; Content type: text/html; Source: open({"ref_id":"https://docs.cloud.google.com/vertex-ai/generative-ai/docs/data-governance","lineno":null}); Redirected to URL: https://docs.cloud.google.com/gemini-enterprise-agent-platform/resources/zero-data-retention; Total lines: 342 L0: [Button: ] L1: L2: 【0†Documentation】 L3: L4: [Input: Search] L5: L6: `/` L7: L8: 【1†Console†console.cloud.google.com】 L9: L10: * English L11: * Deutsch L12: * Español – América Latina L13: * Français L14: * Indonesia L15: * Italiano L16: * Português – Brasil L17: * עברית L18: * 中文 – 简体 L19: * 中文 – 繁體 L20: * 日本語 L21: * 한국어 L22: Sign in L23: L24: 【2†Start free†console.cloud.google.com】 L25: L26: 【3†Overview】 【4†Studio】 【5†Agents】 【6†Models】 【7†Notebooks】 【8†API reference】 [Button: Pricing ] 【9†Engineering Blog】 L27: L28: [Input: Filter] L29: L30: [Button: ] L31: L32: * Agent Platform documentation L33: L34: * Resources L35: * Agent-related support and resources L36: L37: * Model-related support and resources L38: L39: * Machine learning services L40: L41: * Support policy L42: L43: * AI Agent Ecosystem Program L44: L45: * Pricing L46: L47: * 【10†Agent Platform†cloud.google.com】 L48: * 【11†Generative AI†cloud.google.com】 L49: L50: [Button: Send feedback ] L51: # Gemini Enterprise Agent Platform and zero data retention Stay organized with collections Save and categorize content based on your preferences. L52: Google was the first in the industry to publish an 【12†AI/ML Privacy Commitment†cloud.google.com】, which outlines our belief that customers should have the highest level of security and control over their data that is stored in the cloud. That commitment extends to Google Cloud's generative AI products. Google ensures that its teams are following these commitments through robust data governance practices, which include reviews of the data that Google Cloud uses in the development of its products. L53: More details about how Google processes data can also be found in Google's 【13†Cloud Data Processing Addendum†cloud.google.com】 (CDPA). L54: ## Training restriction L55: L56: As outlined in "Training Restriction" in the 【14†Service Terms section of the Service Specific Terms†cloud.google.com】, Google won't use your data to train or fine-tune any AI/ML models without your prior permission or instruction. This applies to all managed models on Gemini Enterprise Agent Platform, including GA and pre-GA models. L57: ## Customer data retention and achieving zero data retention L58: L59: Customer data is retained in Gemini Enterprise Agent Platform for Models as a Service (MaaS) for limited periods of time in the following scenarios and conditions. To achieve zero data retention, customers must take specific actions within each of these areas: L60: * Prompt logging for abuse monitoring for Google models: As outlined in Section 4.3 "Generative AI Safety and Abuse" of 【15†Google Cloud Platform Terms of Service†cloud.google.com】, Google may log prompts to detect potential abuse and violations of its 【16†Acceptable Use Policy†cloud.google.com】 and 【17†Prohibited Use Policy†policies.google.com】 as part of providing generative AI services to customers. L61: Only customers whose use of Google Cloud is governed by the 【15†Google Cloud Platform Terms of Service†cloud.google.com】 are subject to prompt logging for abuse monitoring. L62: * Prompt and response logging for abuse monitoring for Advanced AI models: Certain models or features may also be subject to additional prompt and response logging to prevent abuse, as described in the 【18†Advanced AI Safety Addendum†cloud.google.com】. Zero data retention may not be possible when using some Advanced AI features. Please contact your account team for clarification. See 【19†Abuse monitoring】 for more information. L63: * Grounding with Google Search: As outlined in Section 20 "Generative AI Services: Grounding with Google Search" of the 【14†Service Specific Terms†cloud.google.com】, Google collects and stores logs, which contains the following Customer Data: queries derived from End User prompts and contextual information that Customer may provide along with the prompts that are not associated with any Customer or its End Users for up to three (3) days, this stored information may be used for debugging of systems that support Grounding with Google Search. L64: There is no way to disable the storage of this information if you use Grounding with Google Search. If you require zero data retention, we recommend using 【20†Web Grounding for Enterprise】. L65: * Grounding with Google Maps: As outlined in Section 20 "Generative AI Services: Grounding with Google Maps" of the 【14†Service Specific Terms†cloud.google.com】, Google stores prompts and contextual information that customers may provide, and generated output for thirty (30) days for the purposes of creating grounded results, and this stored information may only be used for reliability engineering, such as debugging in case of service issues, of systems that support grounding with Google Maps. L66: There is no way to disable the storage of this information if you use Grounding with Google Maps. L67: * Request-response logging: This feature is disabled by default. It can be enabled using a configuration setting on a per-model, per-project basis. Enabling this logging causes certain requests and responses to the specified model to be written to a designated BigQuery table. To achieve zero data retention, do not enable this feature. For more information about this feature, including how to enable or disable it, or read the current configuration setting, see 【21†Log requests and responses】. L68: * Interactions API: When using the 【22†Interactions API】 with `store = true`, Google stores user data (such as prompts, responses, and conversation state) to enable multi-turn conversations and later retrieval. If you do not specify a value for `store`, it defaults to `true` for all models. To achieve zero data retention, explicitly set `store = false` in your API requests. L69: L70: This applies to all managed models on Gemini Enterprise Agent Platform, including GA and pre-GA models. L71: ## Agent products L72: L73: To achieve zero data retention for agent products, customers must adhere to the following conditions and retention schedules for each product: L74: * CodeMender session data — To enable resumption of long-running find and fix scans, 【23†CodeMender】 stores session state in Spanner. While a scan is in progress, session data — including target source code snippets, diffs, configuration, and analysis checkpoints — is stored encrypted for up to seven (7) days from session creation. L75: When a session reaches a terminal state, source code and related content are cleared within seconds; the remaining session record is deleted automatically at the seven-day TTL. Customers can delete a session (removing all associated data) before the TTL expires. L76: * Deep Research agent session data — Google stores prompts and session data - including search results and generated images - via the Interactions API for a period of seven (7) days. This session data is encrypted at rest, and is deleted automatically at the end of the seven-day TTL. Customers can delete a session (removing all associated data) before the TTL expires. This feature cannot be disabled when using the Deep Research agent. L77: * Agent Platform Sandbox Snapshots: If you use the Snapshot API to persist Sandbox state, these snapshots are stored only for the duration of the Sandbox TTL. To achieve zero-data-retention, don't use the Sandbox API. L78: ## Google models L79: L80: To achieve zero data retention for Google trained models, customers must take additional specific actions within each of these areas: L81: ### Session resumption for Gemini Live API L82: Session resumption for Gemini Live API is disabled by default. It must be enabled by the user every time they call the API by specifying the field in the API request, and project-level privacy is enforced for cached data. Enabling Session Resumption allows the user to reconnect to a previous session within 24 hours by storing cached data, including text, video, and audio prompt data and model outputs, for up to 24 hours. To achieve zero data retention, do not enable this feature. L83: For more information about this feature, including how to enable it, see 【24†Gemini Live API】. L84: ### Implicit data caching L85: L86: By default, Google's published Gemini models cache Customer Data to reduce latency and accelerate responses. Implicit caching uses two storage tiers: L87: L88: * In-memory caching: Enabled by default for supported Gemini models. L89: * Durable caching: Enabled by default for supported Gemini models. For the list of supported models, see 【25†Context caching overview】. L90: #### In-memory data caching L91: L92: Implicit caching stores Customer Data (inputs, outputs, and derived data) in memory. In-memory cached data has the following properties: L93: L94: * It's stored only in memory, not at rest. L95: * It's scoped to your project and is never served to another project. L96: * It's deleted no later than 24 hours after it's written. L97: * It's processed in the region that serves the request. L98: * It's used only to serve your requests faster, and is never used to train or fine-tune models. L99: #### Durable data caching L100: L101: On models that support durable caching, when in-memory cache capacity is exhausted, Google stores derived cache data (key-value representations computed from your inputs) in durable storage within the Agent Platform serving environment. Durable cached data has the following properties: L102: * It's stored at rest and encrypted with Google default encryption. L103: * It's scoped to your project and is never served to another project. L104: * It's deleted no later than 24 hours after it's written, and is often evicted sooner.