# ABV Documentation ABV is an LLM observability platform that helps developers track, debug, and optimize their AI applications. This documentation covers developer tools, SDKs, security, and compliance information. ## Getting Started - [Quick Links](/developer/quick-links): Not sure where to start with ABV? This guide helps you find the right documentation based on what you're trying to accomplish. - [Quickstart (Python SDK)](/developer/quickstart-python): This quickstart helps you to ingest your first trace in ABV. - [Quickstart (JS/TS SDK)](/developer/quickstart-js-ts): This quickstart helps you to ingest your first trace in ABV. - [Observability Data Model](/developer/observability-data-model): Learn about ABV's observability data model and how to enrich your data with metadata. Understand your users better by leveraging traces and observations to gain valuable insights. ## Basic Features ### Tracing & Observability - [Observability & Tracing](/developer/basic-features/observability-tracing): Unlock powerful LLM observability with ABV's tracing tools. Debug agent behavior, track model costs in real-time, and optimize latency. Get started with our Python & JS SDKs. - [Trace IDs & Distributed Tracing](/developer/basic-features/trace-ids-distributed-tracing): Learn how to implement distributed tracing with custom trace IDs in ABV. Use your own domain-specific IDs with our Python and JS/TS SDKs for deep-linking, evaluating traces, and more. - [Trace URLs](/developer/basic-features/trace-urls): Learn how to manage and share trace URLs in ABV. Get a direct URL for your logs or notebooks, and see how to make traces public via the UI or our Python & JS/TS SDKs. - [Log Levels](/developer/basic-features/log-levels): Control the signal-to-noise ratio of your application logs with ABV's log levels. Learn how to prioritize issues by severity to focus on what matters most and streamline your debugging process. ### Context & Organization - [Metadata](/developer/basic-features/metadata): Enrich traces and observations with metadata to better understand your users and application. Learn how to add or update metadata using the Python and JS/TS SDKs - [Tags](/developer/basic-features/tags): Effectively categorize and filter your traces in ABV with tags. Learn how to add, remove, and use tags to streamline your debugging and analysis workflows. - [Sessions](/developer/basic-features/sessions): Unlock the power of ABV sessions. Learn how to group LLM application traces, create insightful session replays, and enhance your debugging and analysis capabilities. - [User Tracking](/developer/basic-features/user-tracking): Learn how to implement user tracking in ABV. Associate traces with a unique userId using our Python and JS/TS SDKs to segment by token usage and analyze user feedback. ### Optimization & Data Management - [Model Usage & Cost Tracking](/developer/basic-features/model-usage-cost-tracking): Track and manage your LLM costs. Learn how to monitor model usage, analyze token consumption, and accurately calculate expenses for OpenAI, Anthropic, and custom models. - [Cost Tracking Implementation](/developer/basic-features/cost-tracking-implementation): Step-by-step guide to implement cost tracking in your application. Complete code examples for Python and JavaScript/TypeScript SDKs. - [Cost Tracking Reference](/developer/basic-features/cost-tracking-reference): Technical reference for custom model definitions, tokenizers, pricing configuration, and the ABV Models API. - [Sampling](/developer/basic-features/sampling): Control your data volume with ABV's sampling feature. Learn how to set a sample rate to collect a percentage of traces and reduce data for high-traffic applications using our Python and JS/TS SDKs. - [Event Queuing/Batching](/developer/basic-features/event-queuing-batching): Learn about event queuing and batching in ABV. Optimize API calls and network time by configuring batching behavior and manually flushing events in our Python and JS/TS SDKs. - [Masking of Sensitive LLM Data](/developer/basic-features/masking-sensitive-data): Secure your application by masking sensitive LLM data. Our guide shows you how to use custom functions to redact PII, protect user privacy, and meet compliance standards. ### Environment & Deployment - [Releases & Versioning](/developer/basic-features/releases-versioning): Learn how to track and version your LLM app's releases. See the impact of changes on cost, latency, and quality to run effective A/B tests and experiments in production. - [Environments](/developer/basic-features/environments): Learn how to manage different environments in ABV. Our documentation guides you through setting up, configuring, and deploying to development, staging, and production environments for your AI applications. ### Advanced Features - [Multi-Modality and Attachments](/developer/basic-features/multi-modality-and-attachments): Learn how ABV supports multi-modal traces with attachments. Automatically handle base64 encoded data, upload media with the ABVMedia class, and resolve media references in our Python and JS/TS SDKs. - [Agent Graphs](/developer/basic-features/agent-graphs): Visualize complex AI agent workflows with ABV's agent graphs. Understand agent behavior, debug multi-step processes, and optimize your agentic applications. - [ABV Prompt Playground](/developer/basic-features/prompt-playground): Test and iterate on your prompts directly in the ABV Prompt Playground. Tweak prompts and model parameters, compare outputs, and experiment with different LLM providers. - [Comments on Objects](/developer/basic-features/comments-on-objects): Collaborate with your team by adding comments to objects in ABV. Flag issues, share insights, and leave feedback on traces, prompts, and more via the UI or API. ## LLM Gateway - [Overview](/developer/llm-gateway/overview): The ABV AI Gateway is a unified interface that lets you call different LLM providers through a single, consistent API. Think of it as a universal adapter for LLMs - you write your code once, and it works across OpenAI, Anthropic, and Google Gemini. - [Quickstart](/developer/llm-gateway/quickstart): This guide will get you making your first AI Gateway request in under five minutes. We'll cover both TypeScript and Python, so jump to whichever language you're using. - [Models Available](/developer/llm-gateway/models-available): The AI Gateway supports a comprehensive range of models from OpenAI, Anthropic, and Google Gemini. Each provider offers models optimized for different use cases, with varying capabilities, performance characteristics, and pricing tiers. - [Typescript Guide](/developer/llm-gateway/typescript-guide): The ABV client library comes as a single npm package that includes everything you need. Install it in your project with npm, yarn, or pnpm: - [Python Guide](/developer/llm-gateway/python-guide): This guide covers implementation specifics for using the AI Gateway with Python. It assumes you've already read the introduction and understand the core concepts. We'll focus on Python-specific patterns, async/await usage, error handling, and practical implementation details. ## Guardrails - [Overview](/developer/guardrails/overview): Guardrails automatically check your LLM's inputs and outputs to keep them safe, compliant, and high-quality. Think of them as safety checks that run before content reaches your users or your language model. - [Quickstart](/developer/guardrails/quickstart): This guide will have you running guardrails in under five minutes. You'll learn how to install the SDK, validate your first piece of content, and understand the result. - [Concepts](/developer/guardrails/concepts): Understanding a few fundamental concepts will help you use guardrails effectively. This guide explains how guardrails work, what their results mean, and how to make decisions based on those results. - [Best Practices](/developer/guardrails/best-practices): This guide covers strategies for using guardrails effectively in production applications. You'll learn how to optimize performance and costs, implement robust error handling, maintain security, and monitor your validation pipeline. - [LLM Security & Guardrails](/developer/guardrails/llm-security-guardrails-overview): Protect your LLM app from risks like prompt injection and PII leakage. Learn to combine run-time security tools with ABV for monitoring, evaluation, and investigation. ### Available Guardrails - [Biased Language](/developer/guardrails/available/biased-language): The biased language guardrail detects discriminatory content, stereotypes, and prejudiced assumptions that could harm your brand or violate compliance requirements. This guardrail uses AI to identify not just explicit bias but also subtle coded language and implicit assumptions that keyword filters would miss.. - [Contains String](/developer/guardrails/available/contains-string): The contains string guardrail validates text against specific strings using pattern matching. Unlike AI-powered guardrails that interpret meaning, this guardrail simply checks whether certain strings appear in your text. - [Valid JSON](/developer/guardrails/available/valid-json): The valid JSON guardrail ensures text is properly formatted JSON with optional **schema validation**. When you're working with AI-generated structured outputs, this guardrail prevents the frustrating errors that happen when your AI returns malformed JSON or when the JSON structure doesn't match what your application expects.. ## Evaluations - [Evaluation Overview](/developer/evaluations/overview): Improve your AI applications with LLM evaluation. Learn about online and offline evaluation methods, and key concepts like scores, datasets, and dataset runs to enhance model accuracy, performance, and user trust. - [Evaluations Quickstart Tutorial](/developer/evaluations/quickstart-tutorial): Learn evaluations with a complete hands-on example. Create a dataset, run evaluations, and analyze results in under 30 minutes. ### Datasets & Runs - [Datasets](/developer/evaluations/datasets): Create robust test cases for your LLM app with ABV Datasets. Learn to build test data from production traces or synthetic examples using our UI and SDKs. - [Dataset Runs Data Model](/developer/evaluations/dataset-runs-data-model): Learn about the ABV data model for Datasets and Dataset Runs. Understand how to use collections of inputs and expected outputs to evaluate and test your LLM applications effectively. See the full API reference for details. - [Remote Dataset Runs](/developer/evaluations/remote-dataset-runs): Automate LLM application testing with Remote Dataset Runs. Get full flexibility to run experiments and apply custom scoring logic using the ABV Python & JS/TS SDKs. - [Prompt Experiments](/developer/evaluations/prompt-experiments): Run Prompt Experiments (Native Dataset Runs) in the ABV UI to test and compare different prompt versions or language models side-by-side. Learn how to use LLM-as-a-Judge evaluators for automatic scoring to prevent regressions. ### Scoring - [LLM-as-a-Judge](/developer/evaluations/llm-as-a-judge): Use LLM-as-a-judge for scalable, cost-effective LLM evaluation. Our guide shows how to set up custom or managed evaluators in ABV to automate quality scoring. - [Human Annotation](/developer/evaluations/human-annotation): Discover how to use Human Annotation in ABV for manual LLM evaluation. Learn to collaboratively annotate traces, sessions, and observations, use Annotation Queues for large batches, and set a human baseline for scoring. - [Custom Scores](/developer/evaluations/custom-scores): Implement flexible LLM evaluation with Custom Scores. Learn to ingest user feedback, run custom pipelines, and set guardrails using the ABV Python & JS/TS SDKs. - [Scores Data Model](/developer/evaluations/scores-data-model): Explore the ABV Scores Data Model for LLM evaluation. Learn how to structure scores and use score configs to track numeric, categorical, and boolean metrics consistently. ### Troubleshooting - [Evals Troubleshooting and FAQ](/developer/evaluations/troubleshooting-faq): Find answers to common questions in the ABV FAQ. Learn how to manage Score Configs, troubleshoot missing traces, capture user feedback for evaluation, and explore reasons to use ABV for LLM observability and prompt management. ## Prompt Management - [Prompt Management Overview](/developer/prompt-management/overview): Learn how ABV's prompt management helps you build effective LLM applications. Discover tools for tracking metrics, linking prompts to traces, and improving prompt quality over time. - [Get Started with Prompt Management](/developer/prompt-management/get-started): Learn to manage, version, and track your LLM prompts with ABV. Follow our getting-started guide for the Python SDK, TypeScript SDK, and API integration. ### Configuration & Organization - [Prompt Config](/developer/prompt-management/config): The prompt `config` in ABV is an **optional arbitrary JSON object** attached to each prompt that stores structured data such as model parameters (like model name, temperature), function/tool parameters, or JSON schemas. - [Prompt Folders](/developer/prompt-management/folders): Prompts can be organized into virtual folders to group prompts with similar purposes. To create a folder, add slashes (`/`) to a prompt name. The UI shows every segment ending with a `/` as a folder automatically. - [Prompt Version Control](/developer/prompt-management/version-control): In ABV, version control and deployment of prompts is managed via versions and labels. Learn how to use version IDs and labels to organize prompts across environments, tenants, and experiments. - [ABV Prompts Data Model](/developer/prompt-management/prompts-data-model): Learn about the ABV Prompts data model and how to effectively manage your prompts. This document explains prompt objects, text and chat prompts, versioning, and the use of labels for seamless deployment and management. ### Advanced Features - [Prompt Composability](/developer/prompt-management/composability): As you create more prompts, you will often find yourself using the same snippets of text or instructions in multiple prompts. To avoid duplication, you can compose prompts by referencing other prompts. - [Message Placeholders in Chat Prompts](/developer/prompt-management/message-placeholders): Message Placeholders allow you to insert a list of chat messages at specific positions within a chat prompt. Define multiple placeholders and resolve them with different values at runtime. - [A/B Testing of LLM Prompts](/developer/prompt-management/ab-testing-llm-prompts): [ABV Prompt Management](/developer/prompt-management/get-started) enables A/B testing by allowing you to label different versions of a prompt (e.g., `prod-a` and `prod-b`). Your application can randomly alternate between these versions, while ABV tracks performance metrics like response latency, cost, token usage, and evaluation metrics for each version. ### Integrations - [Link Prompts to Traces](/developer/prompt-management/link-prompts-to-traces): Linking prompts to [traces](/developer/basic-features/observability-tracing) enables tracking of metrics and evaluations per prompt version. It's the foundation of improving prompt quality over time. - [GitHub Integration for ABV Prompts](/developer/prompt-management/github-integration): There are two methods to integrate ABV prompts with GitHub: - [Webhooks & Slack Integration](/developer/prompt-management/webhooks-slack-integration): Use webhooks to receive real‑time notifications whenever a prompt version is created, updated, or deleted in ABV. This lets you trigger CI/CD pipelines, sync prompt catalogues, or audit changes without polling the API. ### Performance & Reliability - [Caching of Prompts in Client SDKs](/developer/prompt-management/caching-prompts): ABV prompts are cached client-side in the SDKs, so **there's no latency impact after the first use** and no availability risk. You can also pre-fetch prompts on startup to populate the cache or provide a fallback prompt. - [Guaranteed Availability](/developer/prompt-management/guaranteed-availability): Implementing this is usually not necessary as it adds complexity to your application. The ABV Prompt Management is highly available due to multiple [caching layers](/developer/prompt-management/caching-prompts) and we closely monitor its performance ([status page](https://status.abv.dev)). ### Troubleshooting - [Prompt Troubleshooting and FAQ](/developer/prompt-management/troubleshooting-faq): Common questions about prompt management including configuration, performance measurement, tracing integration, version control, A/B testing, and caching. ## SDKs - [Overview of ABV SDKs](/developer/sdks/overview): Integrate ABV into your application with our powerful and easy-to-use SDKs. Learn how our asynchronous, OpenTelemetry-based SDKs provide accurate latency tracking and a seamless developer experience. ### JavaScript/TypeScript SDK - [TypeScript SDK - Overview](/developer/sdks/js-ts/overview): Integrate ABV with your TypeScript applications using our modular and OpenTelemetry-based SDK. Get started with our powerful tools for tracing, context management, and seamless integration with third-party instrumentations. - [TypeScript SDK - Setup](/developer/sdks/js-ts/setup): Get started with the ABV TypeScript SDK. This guide covers setup for both OpenTelemetry tracing and the general API client in your Node.js application. - [TypeScript SDK - Instrumentation](/developer/sdks/js-ts/instrumentation): Learn how to instrument your TypeScript applications with the ABV SDK. This guide covers custom instrumentation with context managers and wrappers, native instrumentation for LLM libraries, and manual observation control for comprehensive tracing. - [TypeScript SDK - Advanced Configuration](/developer/sdks/js-ts/advanced-configuration): Gain advanced control over your observability data with the ABV TypeScript SDK. Learn to configure data masking, span filtering, sampling, and multi-project setups for enhanced security, cost management, and flexibility in your applications. - [Cookbook: ABV JS/TS SDK](/developer/sdks/js-ts/cookbook): Explore practical examples and code recipes in the ABV JS/TS SDK Cookbook. Learn to trace LLM calls, leverage integrations like OpenAI and LangChain, and master advanced instrumentation techniques for your applications. - [TypeScript SDK - Troubleshooting and FAQ](/developer/sdks/js-ts/troubleshooting-faq): Find solutions to common issues with the ABV TypeScript SDK. This FAQ covers troubleshooting for missing traces, Vercel/otel integration, and serverless environments. ### Python SDK - [Python SDK - Overview](/developer/sdks/python/overview): Get started with the ABV Python SDK for comprehensive LLM application tracing. Built on OpenTelemetry, our SDK offers an intuitive API, decorators, and context managers for easy instrumentation. Monitor and observe your Python applications with ease. - [Python SDK - Setup](/developer/sdks/python/setup): Set up the ABV Python SDK. This guide covers installation, initializing the client with your API key, and key configurations for tracing, sampling, and batching via environment variables or constructor arguments. - [Python SDK - Instrumentation](/developer/sdks/python/instrumentation): Learn how to instrument your Python applications with the ABV SDK. This guide covers using decorators, context managers, and manual instrumentation for comprehensive tracing of your LLM application. - [Python SDK - Advanced Usage](/developer/sdks/python/advanced-usage): Explore advanced usage of the ABV Python SDK for powerful observability and tracing. Learn to use decorators, context managers, and manual observations. - [Python SDK - Evaluations](/developer/sdks/python/evaluations): Evaluate your LLM applications with the ABV Python SDK. Add custom scores, run dataset evaluations, and ensure the quality and reliability of your models in both development and production. - [Python SDK - Troubleshooting](/developer/sdks/python/troubleshooting): Troubleshooting the ABV Python SDK? Find solutions for common issues like authentication errors, missing traces, and incorrect span nesting. Get your integration back on track quickly with our expert guide. ## References - [Python SDK (v3)](/developer/references/python-sdk-v3): Complete API reference for the ABV Python SDK v3. Explore all classes, methods, and functions available in the Python SDK for LLM observability and tracing. - [JavaScript/TypeScript SDK](/developer/references/js-sdk): Complete API reference for the ABV JavaScript/TypeScript SDK. Explore all classes, methods, and functions available in the JS/TS SDK for LLM observability and tracing. - [Security & Compliance Overview](/developer/references/security-compliance-overview): Learn about ABV's commitment to data privacy and security. Explore our compliance certifications, security measures, and data protection policies. ## Platform ### Administration - [Data Retention](/developer/platform/administration/data-retention): Control your data lifecycle and meet compliance requirements with ABV's Data Retention feature. Set project-level rules to automatically delete old traces, scores, and observations. - [SCIM & Organization-Key Scoped API Routes](/developer/platform/administration/scim-org-key-scoped-api-routes): Automate user provisioning and project management in ABV. This guide covers our management API, SCIM 2.0 endpoints, and a full walkthrough for Okta SSO integration. - [Usage Alerts](/developer/platform/administration/usage-alerts): Set up ABV usage alerts to proactively monitor your event volume. Learn how to configure email notifications when usage exceeds a predefined threshold, helping you control costs and avoid surprise invoices before your next billing cycle. - [LLM Connections](/developer/platform/administration/llm-connections): Learn how to set up LLM connections in ABV to use models in the Playground and for LLM-as-a-Judge evaluations. This guide covers supported providers like OpenAI, Azure, Anthropic, Google, and Amazon Bedrock, and advanced proxy configurations. - [Role-Based Access Controls in ABV](/developer/platform/administration/role-based-access-controls): Learn how Role-Based Access Control (RBAC) works in ABV. This guide explains user roles, permissions, and scopes at the organization and project levels for fine-grained control over your LLM application data and settings. - [Audit Logs](/developer/platform/administration/audit-logs): Enhance enterprise security and compliance with ABV Audit Logs. Get a complete audit trail of user and API actions to monitor activity and investigate incidents. - [Data Deletion](/developer/platform/administration/data-deletion): Learn how to permanently remove data from ABV. This guide provides step-by-step instructions for deleting single traces, batches of traces, entire projects, or organizations via the UI and API to manage your data effectively. ### Metrics - [Metrics overview](/developer/platform/metrics/overview): Gain actionable insights into your LLM app's performance with ABV Metrics. Monitor quality, cost, and latency using customizable dashboards and our powerful Metrics API. - [Custom Dashboards](/developer/platform/metrics/custom-dashboards): Create custom dashboards in ABV to turn LLM data into actionable insights. Track key metrics like latency, cost, and quality with flexible widgets, advanced filtering, and rich visualizations to make data-driven decisions. - [Metrics API](/developer/platform/metrics/metrics-api): Use the ABV Metrics API to build custom reports for your LLM app. Programmatically query trace, observation, and score data with powerful filters and aggregations. ### API & Data Platform - [API & Data Platform overview](/developer/platform/api-data-platform/overview): Extend and customize your LLM workflows with ABV's open data platform. Learn how to export data, use the public API and SDK, and integrate with external tools for custom billing, reporting, and fine-tuning models. - [Export Data from UI](/developer/platform/api-data-platform/export-data-from-ui): Export ABV observability data for fine-tuning, analysis, or model training. Learn to export to CSV/JSON, blob storage, or programmatically via our SDKs and API. - [Export via Blob Storage Integration](/developer/platform/api-data-platform/export-via-blob-storage): Learn how to schedule automated data exports from ABV to your Blob Storage. This guide covers setting up hourly, daily, or weekly exports of traces, observations, and scores to AWS S3, GCS, or Azure Blob Storage. - [Query Data via SDKs](/developer/platform/api-data-platform/query-data-via-sdks): Programmatically access your LLM data for fine-tuning or custom workflows. Learn to use the ABV Python and JS/TS SDKs to query traces, scores, and more. - [Export for Fine-Tuning](/developer/platform/api-data-platform/export-for-fine-tuning): Learn how to export ABV data for fine-tuning. This guide covers exporting generations in OpenAI JSONL format and filtering by quality scores to improve model performance. - [Public API](/developer/platform/api-data-platform/public-api): Access all ABV data and features programmatically via our public REST API and SDKs. This guide provides API endpoints, authentication details, and examples for our Python and JS/TS SDKs to integrate with your workflows. ## Support - [Troubleshooting and FAQ](/developer/troubleshooting-faq): Common questions and solutions for ABV tracing, including serverless setup, cost tracking, environments, API keys, and troubleshooting missing traces. # Security & Compliance ## Overview - [Security & Compliance Overview](/security/overview): Learn about ABV's commitment to enterprise-grade data privacy, security, and compliance. We are ISO 27001 certified and GDPR/HIPAA compliant, offering robust encryption, data masking, and secure deployment options to protect your data. ## Security - [Authentication & Authorization](/security/security/authentication-authorization): Secure your ABV organization with robust authentication and authorization. Learn about sign-in options like SSO via Okta/OIDC and managing user access with RBAC. - [Encryption](/security/security/encryption): Learn about ABV's robust data encryption methods. We protect your data with TLS for encryption in transit and the AES-256 standard for encryption at rest across all services, including Postgres, S3, and Clickhouse. - [Data Regions & Availability](/security/security/data-regions-availability): Meet your data residency and compliance needs with ABV's cloud regions. Learn how to choose and connect to our US or EU regions for optimal performance and GDPR compliance. - [Penetration Testing](/security/security/penetration-testing): Validate ABV's security posture with our annual third-party penetration test reports. Learn about our testing process and how to request the summary for your compliance needs. - [Vulnerability Management](/security/security/vulnerability-management): Discover ABV's comprehensive vulnerability management program. Learn how we identify, assess, and remediate security vulnerabilities through automated scanning, penetration testing, and a responsible disclosure program to protect customer data. - [Incident & Breach](/security/security/incident-breach): Review ABV's incident response policy and breach notification commitment. See how we handle security incidents and provide transparent updates on our official status page to ensure customer awareness and data protection. - [Responsible Disclosure](/security/security/responsible-disclosure): View ABV's responsible disclosure policy for security vulnerabilities. This page details how to submit a report and clarifies our stance on bug bounty rewards. - [Whistleblowing](/security/security/whistleblowing): Learn about the ABV Whistleblowing Policy. This page provides information on how to confidentially or anonymously report potential breaches of laws, regulations, or company policies via secure channels. - [Security FAQ](/security/security/faq): Find answers to frequently asked security questions about ABV. This FAQ covers encryption, compliance (ISO 27001, GDPR, HIPAA), SSO, RBAC, and data privacy. ## Compliance - [Policies](/security/compliance/policies): Review ABV's comprehensive set of internal policies that form our compliance framework. This page lists our documented policies for AI Governance, Data Protection, Secure SDLC, Business Continuity, and more to ensure robust security. - [HIPAA Compliance](/security/compliance/hipaa-compliance): Learn how ABV aligns with HIPAA for healthcare organizations. We offer a Business Associate Agreement (BAA) to help you safeguard Protected Health Information (PHI). - [ISO 27001 Compliance](/security/compliance/iso-27001-compliance): Learn about ABV Cloud's ISO 27001 certification for information security. Pro and Enterprise customers can request our official certificate for their compliance needs. - [ISO 42001 Compliance](/security/compliance/iso-42001-compliance): Learn about ABV Cloud's ISO 42001 certification, the international standard for information security management systems (ISMS). This demonstrates our commitment to maintaining robust security. Certificate available on request. - [NIS 2 Compliance](/security/compliance/nis2-compliance): Learn about ABV's compliance with the EU NIS2 Directive for cybersecurity. Discover how our ISO 27001-certified Information Security Management System (ISMS) meets NIS2 requirements for risk management and incident reporting. ## Privacy - [Managing Personal Data](/security/privacy/managing-personal-data): Take control of personal data processing in ABV. Learn how to use powerful features like data masking to hide PII, targeted data deletion, and custom data retention policies to ensure privacy and compliance. - [GDPR Compliance](/security/privacy/gdpr-compliance): Discover ABV's commitment to GDPR compliance. This page outlines how we lawfully and transparently process personal data, and provides information on our DPA, privacy policy, and how to submit a Data Subject Access Request (DSAR). - [Data Processing Agreement (DPA)](/security/privacy/data-processing-agreement): Learn how to execute a Data Processing Agreement (DPA) with ABV. Review our standard DPA template, available for Pro and Enterprise customers to ensure GDPR compliance. - [Privacy FAQ](/security/privacy/faq): Find answers to frequently asked questions about data privacy at ABV. Learn how we handle customer data, our policy on training AI models, DPA availability, and your options for data retention and deletion.