### 2026

- [January 9 - Chat Sessions in Observability](/content/docs/changelog/chat-sessions-observability/index.html)
- [January 13 - Playground UX Improvements](/content/docs/changelog/playground-ux-improvements-jan-2026/index.html)
- [January 20 - Test Set Versioning and New Test Set UI](/content/docs/changelog/testset-versioning/index.html)
- [January 28 - Navigation Links from Traces to App/Environment/Variant](/content/docs/changelog/trace-navigation-links/index.html)
- [January 29 - Onboarding Widget and Guided Walkthroughs](/content/docs/changelog/onboarding-widget-walkthroughs/index.html)
- [February 4 - Folders for Prompt Organization](/content/docs/changelog/prompt-folders/index.html)
- [February 17 - Enterprise Compliance Features](/content/docs/changelog/enterprise-compliance-features/index.html)
- [February 25 - AI-Powered Prompt Refinement in the Playground](/content/docs/changelog/refine-ai/index.html)
- [February 27 - Tool Integrations in the Playground](/content/docs/changelog/tool-integrations/index.html)
- [March 11 - Webhooks and GitHub Automations for Prompt Deployments](/content/docs/changelog/deployment-webhooks-and-github-automations/index.html)
- [April 14 - Unified Invoke API](/content/docs/changelog/unified-invoke-api/index.html)
- [May 18 - Annotation Queues](/content/docs/changelog/annotation-queues/index.html)
- [June 5 - Dark Mode](/content/docs/changelog/dark-mode/index.html)
- [June 9 - Evaluate While You Iterate in the Playground](/content/docs/changelog/playground-evaluation-workbench/index.html)
- [July 21 - Agenta Is Now a Workspace for Building Agents](/content/docs/changelog/agenta-is-now-a-workspace-for-building-agents/index.html)
- [August 2 - Shared Workspace Files](/content/docs/changelog/file-attachments-in-agent-chat/index.html)
- [August 3 - Run Your Agents on Codex](/content/docs/changelog/codex-harness/index.html)
- [August 4 - API Keys Are Hidden from Agent Sandboxes](/content/docs/changelog/api-keys-hidden-from-agent-sandboxes/index.html)
- [August 12 - Slash Commands](/content/docs/changelog/slash-commands/index.html)
- [August 12 - Automation Runs](/content/docs/changelog/automation-runs/index.html)
- [August 12 - Agent Workspace](/content/docs/changelog/agent-workspace/index.html)
- [August 22 - Agenta on Mobile](/content/docs/changelog/agenta-on-mobile/index.html)

### 2025

- [January 4 - New Onboarding Flow](/content/docs/changelog/new-onboarding-flow/index.html)
- [January 15 - Agenta is SOC 2 Type 1 Certified](/content/docs/changelog/agenta-is-soc-2-type-1-certified/index.html)
- [January 27 - Quality of life improvements](/content/docs/changelog/quality-of-life-improvements/index.html)
- [February 4 - New Playground](/content/docs/changelog/new-playground/index.html)
- [March 11 - OpenTelemetry Compliance and Custom workflows from API](/content/docs/changelog/opentelemetry-compliance-and-custom-workflows-from-api/index.html)
- [March 19 - Improvements to the Playground and Custom Workflows](/content/docs/changelog/improvements-to-the-playground-and-custom-workflows/index.html)
- [April 7 - New Feature: Prompt and Deployment Registry](/content/docs/changelog/new-feature-prompt-and-deployment-registry/index.html)
- [April 15 - Structured Output Support in the Playground](/content/docs/changelog/structured-output-support-in-the-playground/index.html)
- [April 18 - We are SOC 2 Type 2 Certified](/content/docs/changelog/we-are-soc-2-type-2-certified/index.html)
- [May 2 - Documentation Overhaul, New Models, and Platform Improvements](/content/docs/changelog/documentation-overhaul-new-models-and-platform-improvements/index.html)
- [May 10 - Tool Support in the Playground](/content/docs/changelog/tool-support-in-the-playground/index.html)
- [May 15 - Annotate Your LLM Response (preview)](/content/docs/changelog/annotate-your-llm-response-preview/index.html)
- [June 17 - LlamaIndex Integration](/content/docs/changelog/llamaindex-integration/index.html)
- [July 29 - Support for Images in the Playground](/content/docs/changelog/support-for-images-in-playground/index.html)
- [August 7 - Major Playground Improvements and Enhancements](/content/docs/changelog/major-playground-improvements-and-enhancements/index.html)
- [August 12 - Open-sourcing our Product Roadmap](/content/docs/changelog/open-sourcing-product-roadmap/index.html)
- [August 29 - DSPy Integration](/content/docs/changelog/dspy-integration/index.html)
- [September 9 - Multiple Metrics in Human Evaluation](/content/docs/changelog/multiple-metrics-in-human-evaluation/index.html)
- [September 19 - Speed Improvements in the Playground](/content/docs/changelog/speed-improvements-in-the-playground/index.html)
- [September 24 - Deep URL Support for Sharable Links](/content/docs/changelog/deep-url-support-for-sharable-links/index.html)
- [September 26 - New Evaluation Results Dashboard](/content/docs/changelog/new-evaluation-results-dashboard/index.html)
- [October 14 - Filtering Traces by Annotation](/content/docs/changelog/filtering-traces-by-annotation/index.html)
- [October 24 - Vertex AI Provider Support](/content/docs/changelog/vertex-ai-provider-support/index.html)
- [November 3 - Documentation Architecture Overhaul](/content/docs/changelog/documentation-architecture-overhaul/index.html)
- [November 10 - Customize LLM-as-a-Judge Output Schemas](/content/docs/changelog/customize-llm-as-a-judge-output-schemas/index.html)
- [November 11 - Online Evaluation](/content/docs/changelog/online-evaluation/index.html)
- [November 12 - Evaluation SDK](/content/docs/changelog/evaluation-sdk/index.html)
- [November 13 - Agenta Core is Now Open Source](/content/docs/changelog/open-sourcing-agenta/index.html)
- [November 17 - Jinja2 Template Support in the Playground](/content/docs/changelog/jinja2-template-support/index.html)
- [November 18 - Reasoning Effort Support in the Playground](/content/docs/changelog/reasoning-effort-support/index.html)
- [November 20 - Provider Built-in Tools in the Playground](/content/docs/changelog/provider-built-in-tools/index.html)
- [December 4 - Projects within Organizations](/content/docs/changelog/projects-within-organizations/index.html)
- [December 14 - Agenta Documentation MCP Server](/content/docs/changelog/mcp-server/index.html)
- [December 17 - PDF Support in the Playground](/content/docs/changelog/pdf-support-in-playground/index.html)
- [December 31 - JSON Multi-Field Match Evaluator](/content/docs/changelog/json-multi-field-match/index.html)

### 2024

- [January 12 - Adding Cost and Token Usage to the Playground](/content/docs/changelog/adding-cost-and-token-usage-to-the-playground/index.html)
- [January 22 - Revamping evaluation](/content/docs/changelog/revamping-evaluation/index.html)
- [January 24 - Improved human evaluation workflow](/content/docs/changelog/improved-human-evaluation-workflow/index.html)
- [January 25 - Bring your own API key](/content/docs/changelog/bring-your-own-api-key/index.html)
- [January 29 - Improved error handling in evaluation](/content/docs/changelog/improved-error-handling-in-evaluation/index.html)
- [January 30 - New JSON Evaluator](/content/docs/changelog/new-json-evaluator/index.html)
- [January 31 - Prompt Versioning](/content/docs/changelog/prompt-versioning/index.html)
- [February 4 - Minor fixes](/content/docs/changelog/minor-fixes/index.html)
- [February 14 - Deployment Versioning and RBAC](/content/docs/changelog/deployment-versioning-and-rbac/index.html)
- [March 4 - Highlight output difference when comparing evaluations](/content/docs/changelog/highlight-ouput-difference-when-comparing-evaluations/index.html)
- [March 11 - Minor improvements](/content/docs/changelog/minor-improvements-2/index.html)
- [March 25 - New evaluators](/content/docs/changelog/new-evaluators/index.html)
- [March 31 - Minor improvements](/content/docs/changelog/minor-improvements/index.html)
- [April 1 - Compare latency and costs](/content/docs/changelog/compare-latency-and-costs/index.html)
- [April 14 - Observability (beta)](/content/docs/changelog/observability-beta/index.html)
- [April 23 - Evaluation Speed Increase and Numerous Quality of Life Improvements](/content/docs/changelog/evaluation-speed-increase-and-numerous-quality-of-life-improvements/index.html)
- [April 28 - Miscellaneous Improvements](/content/docs/changelog/miscellaneous-improvements/index.html)
- [May 1 - Prompt and Configuration Registry](/content/docs/changelog/prompt-and-configuration-registry/index.html)
- [May 24 - Playground Improvements](/content/docs/changelog/playground-improvements/index.html)
- [May 25 - New LLM Provider: Welcome Gemini!](/content/docs/changelog/new-llm-provider-welcome-gemini/index.html)
- [June 4 - Evaluators can access all columns](/content/docs/changelog/evaluators-can-access-all-columns/index.html)
- [July 5 - More Reliable Evaluations](/content/docs/changelog/more-reliable-evaluations/index.html)
- [July 9 - Migration from MongoDB to Postgres](/content/docs/changelog/migration-from-mongodb-to-postgres/index.html)
- [August 12 - RAGAS Evaluators and Traces in the Playground](/content/docs/changelog/ragas-evaluators-and-traces-in-the-playground/index.html)
- [August 20 - New Alpha Version of the SDK for Creating Custom Applications](/content/docs/changelog/new-alpha-version-of-the-sdk-for-creating-custom-applications/index.html)
- [August 22 - UI Redesign and Configuration Management and Overview View](/content/docs/changelog/ui-redesign-and-configuration-management-and-overview-view/index.html)
- [September 22 - Evaluator Testing Playground and a New Evaluation View](/content/docs/changelog/evaluator-testing-playground-and-a-new-evaluation-view/index.html)
- [October 22 - New Application Management View and Various Improvements](/content/docs/changelog/new-application-management-view-and-various-improvements/index.html)
- [November 6 - Observability and Prompt Management](/content/docs/changelog/observability-and-prompt-management/index.html)
- [November 29 - Viewing Traces in the Playground and Authentication for Deployed Applications](/content/docs/changelog/viewing-traces-in-the-playground-and-authentication-for-deployed-applications/index.html)
- [December 11 - Add Spans to Test Sets](/content/docs/changelog/add-spans-to-test-sets/index.html)

### 2023

- [January 1 - Changes to the SDK](/content/docs/changelog/changes-to-the-sdk/index.html)
- [October 23 - Launch of SDK Version 2 and Cloud-hosted Version](/content/docs/changelog/launch-of-sdk-version-2-and-cloud-hosted-version/index.html)
- [November 2 - Cypress Tests and UI Improvements](/content/docs/changelog/cypress-tests-and-ui-improvements/index.html)
- [November 12 - Sentry Integration and User Communication Improvements](/content/docs/changelog/sentry-integration-and-user-communication-improvements/index.html)
- [November 17 - Enhanced Self-hosting and Mistral Model Tutorial](/content/docs/changelog/enhanced-self-hosting-and-mistral-model-tutorial/index.html)
- [December 1 - Multiple UI and CSV Reader Fixes](/content/docs/changelog/multiple-ui-and-csv-reader-fixes/index.html)
- [December 1 - Introduction of Chat-based Applications](/content/docs/changelog/introduction-of-chat-based-applications/index.html)
- [December 7 - Minor Adjustments for Better Performance](/content/docs/changelog/minor-adjustments-for-better-performance/index.html)
- [December 7 - Bug Fix for Application Saving](/content/docs/changelog/bug-fix-for-application-saving/index.html)
- [December 12 - Integrated File Input and UI Enhancements](/content/docs/changelog/integrated-file-input-and-ui-enhancements/index.html)
- [December 12 - Comprehensive Updates and Bug Fixes](/content/docs/changelog/comprehensive-updates-and-bug-fixes/index.html)
- [December 18 - Resolved Batch Logic Issue in Evaluation](/content/docs/changelog/resolved-batch-logic-issue-in-evaluation/index.html)
- [December 19 - Improving Side-by-side Comparison in the Playground](/content/docs/changelog/improving-side-by-side-comparison-in-the-playground/index.html)