General fixes and UI improvements

November 19, 2025

Gemini 3 Pro preview now available with advanced reasoning and parallel tool calling

Gemini 3 Pro Preview: Powerful Chain-of-Reasoning Tool Calling Now AvailableYou can now access Google’s latest AI breakthrough with full support for advanced reasoning capabilities!Gemini 3 Pro Preview brings sophisticated chain-of-reasoning tool calling to your agents, enabling parallel tool execution with thought signatures that power each reasoning round. This powerful model delivers enhanced decision-making capabilities while maintaining the flexibility you need during Google’s preview period.➡️ Advanced reasoning capabilities – Leverage thought signatures for more intelligent agent decisions➡️ Parallel tool calling – Execute multiple tools simultaneously for faster, more efficient workflows➡️ Complete integration support – Implement Gemini 3 Pro Preview across all regions with ease➡️ Early access advantage – Gain competitive edge by adopting cutting-edge AI capabilities nowWith Gemini 3 Pro Preview, you can create more sophisticated AI workflows that handle complex reasoning tasks with greater accuracy and efficiency than ever before.To access Gemini 3 Pro Preview, simply select it as your model option when configuring your agent in any region.Start building more powerful AI experiences with Gemini 3 Pro Preview today!‍

Other improvements

General fixes and UI improvements

November 19, 2025

Submit multiple slide changes at once with Bulk Slides Submission

Bulk Slides Submission: Stack, Send, and Queue Your Presentation ChangesYou can now make multiple slide changes at once and submit them in a single batch, saving you valuable time and streamlining your workflow!Bulk Slides Submission transforms how you work with presentations in Relevance AI. Instead of submitting each change individually, you can now stack multiple edits, review them together, and send them all at once. You can even queue changes to be processed while you continue working.➡️ Stack multiple changes – Make edits across several slides before submitting➡️ Submit in bulk – Send all your changes at once with a single click➡️ Queue submissions – Continue working while your changes process in the background➡️ Track progress – Monitor the status of your queued submissions➡️ Reduce wait time – Minimize interruptions and maximize productivityWith Bulk Slides Submission, you can work more efficiently, maintain your creative flow, and produce polished presentations faster than ever before.To use this feature, simply make multiple changes to your slides (via Slider Builder in Chat), then look for the “Submit All Changes” button in your presentation editor.Start batching your slide edits today and experience a smoother, more productive workflow!

Other improvements

➡️ Experience engaging loading states – Stay entertained while your slides update➡️ Enjoy improved mobile view – Access your presentations properly on any device

November 17, 2025

Built-in agents for Workforces: Add preset agents to your workflows

Built-in Agents for Workforces: Add Preset Agents to Your WorkflowsYou can now add Relevance AI’s built-in agents like Slide Builder directly to your workforces without creating them first!Workforces now support both your custom agents and our collection of preset agents, giving you immediate access to specialized capabilities. These ready-to-use agents come pre-configured for optimal performance while still allowing you to customize their inputs to match your specific workflow needs.➡️ Access preset agents instantly – Choose from our library of specialized agents without setup➡️ Combine with custom agents – Mix and match built-in and custom agents in the same workforce➡️ Configure inputs only – Preset agents maintain their optimized settings while accepting your custom inputs➡️ View outputs easily – Get automatic redirects to chat conversations for visual outputs like slides and websites➡️ Accelerate workflow creation – Build complex processes faster with pre-configured agent capabilitiesWith built-in agents in workforces, you can quickly assemble powerful workflows that leverage both your custom solutions and Relevance AI’s specialized tools, saving setup time and ensuring consistent results.To add a built-in agent to your workforce, go to your workforce configuration page, click “Add Agent,” and you’ll now see tabs for “Your Agents” and “Preset Agents.”Start enhancing your workforces with built-in agents today!

Other improvements

Reuse existing tool data to build more reliable agent workflows with ‘Tool Output’ mode

‘Tool Output’ Mode for tool inputs: Reuse Existing Data in Your WorkforceYou can now access and reuse data from any tool that has already run in your workforce!By choosing the “Tool Output” mode for a tool input, you can reuse existing information that your agent has already filled, increasing the reliability of tool calling and creating more efficient and reliable workflows.This feature allows you to use existing values in the workforce, so your agent can reuse information it already has, namely tool inputs and outputs from all tools run by accessible agents in the workforceHow do I use this feature?

Click on an agent, and go to the tools tab (or, select a tool node on workforce)
Go to the tool inputs, and click the input type dropdown, you will see a new option in green -> “Tool output”

How does it work?

You will see a dropdown of all the inputs and outputs of every tool used by every agent in the tree above the agent.

What problem does this solve?

This feature solves the problem of agents hallucinating, forgetting, or dropping values over the course of a long task run
Tool output input mode allows you to deterministically use existing values, rather than relying on the agent to pull these from conversation context.

What happens if I use an tool output or input for a tool that hasn’t run?

In this scenario, the input type falls back to ‘let agent decide’, so your run will not fail

Other improvements

General fixes and UI updates.

April 16, 2025

Save and reuse task filters across agent workflows

Saved Filter Views: Customize and Preserve Your Task Filters‍You can now save your custom filter configurations across sessions, eliminating the need to recreate them every time you navigate away!Saved Filter Views lets you create and maintain personalized task filtering setups that persist in your browser’s local storage. Whether you need to quickly access specific tasks, prioritize certain workflows, or monitor particular agents, your custom views remain just a click away.➡️ Create custom filter views – Press the ”+” button in the views tabs section or click “save view” on default tabs➡️ Manage your views easily – Right-click any view for options to duplicate, rename, or delete➡️ Quick rename functionality – Simply double-click on any view button to rename it➡️ Access your views across pages – Available on both the activity center and agent task full screen pages➡️ Smart space management – If you have more than 5 views, the system shows only default tabs plus your current selectionWith Saved Filter Views, you’ll save valuable time by instantly accessing your most important task views without recreating complex filter combinations.To use this feature, look for the views tabs section at the top of your task lists in the activity center or agent task pages.Start organizing your workflow more efficiently with custom filter views today!

Other improvements

General fixes and UI updates.

April 15, 2025

OpenAI’s GPT-4.1 series now in Relevance AI

New OpenAI Models: Supercharge Your Agents with GPT-4.1 SeriesYou can now access OpenAI’s latest and most powerful models directly in Relevance AI!The newly released GPT-4.1 series brings significant improvements across the board, with enhanced capabilities and performance compared to previous models. These models are available immediately as agents, in the LLM step, and in the vision step.➡️ GPT-4.1 – OpenAI’s flagship model that outperforms GPT-4o “across almost every dimension” and even beats the now-deprecated 4.5 preview on many benchmarks➡️ GPT-4.1 Mini – Impressive performance that surpasses even GPT-4o on several benchmarks while maintaining efficiency➡️ GPT-4.1 Nano – OpenAI’s fastest and most cost-effective model, perfect for tasks requiring quick responses and budget optimization➡️ Seamless integration – Available immediately as agents, in the LLM step, and in the LLM vision stepWith these new models, you can build more capable, responsive, and intelligent agents that deliver better results for your specific use cases while optimizing for performance and cost.To try these new models, simply select them when creating or editing agents or choose them in your LLM and vision steps.Test these powerful new models today and share your feedback on how they perform on your real-world tasks!

Other improvements

General fixes and UI updates.

April 10, 2025

Version Control for your agents

Agent Version Control: Safely Manage and Track Your Agent ChangesYou can now save, track, and restore different versions of your agents with complete confidence!Agent Version Control gives you powerful version management for your AI agents. Create draft versions when you’re not ready to publish, view a complete history of changes, and easily restore previous versions if something doesn’t work as expected.➡️ Save agents as drafts – Make changes without affecting your published agent➡️ Track version history – See all previous versions of your agent in one place➡️ Restore previous versions – Quickly revert to any earlier version when needed➡️ Document your development process – Each save creates a new version automatically➡️ Maintain stability – Only published agents can run, ensuring production reliabilityWith Agent Version Control, you can experiment with confidence, collaborate more effectively with your team, and maintain a complete history of your agent’s evolution.To access version control for an agent, go to Agent Profile, click on the ‘three dots’ icon > ‘Show version history’.Start protecting your agent development process with version control today!

Other improvements

General fixes and UI updates.

April 9, 2025

Choose between cost or performance-optimized models easily

Relevance Recommended Models: Smart Model Selection for Optimal PerformanceYou can now leverage pre-configured AI models optimized for either cost-efficiency or maximum performance!Relevance Recommended Models provide intelligent model selection that balances your needs for performance and budget. We’ve carefully selected and pre-configured two specialized model options that automatically update as better alternatives emerge, eliminating the need for manual model switching or staying current with the latest AI advancements.✅ Cost-optimized model (Default) – Get excellent performance at reduced costs for all users✅ Performance-optimized model – Access the absolute best performance available (Premium plans only)✅ Automatic updates – Benefit from the latest models without manual switching or research✅ Pre-configured settings – Skip complex model selection decisions and configuration✅ Future-proof workflows – Your agents automatically improve as better models emergeWith Relevance Recommended Models, you can focus on building powerful agents while we handle the complex task of selecting and updating the optimal AI models for your specific needs.To select your preferred model, simply choose between “Cost-optimized” (default) or “Performance-optimized” when configuring your agents and LLM tools.Start building with confidence knowing you’re always using the optimal model for your needs!

Other improvements

General fixes and UI updates.

April 8, 2025

Connect your Tools with MCP Server for Claude, Cursor & More

MCP Server Integration: Use Your Relevance AI Tools in External AI ClientsYou can now connect your Relevance AI tools to Claude, Cursor, and other AI clients that support MCP servers!The MCP Server integration creates a bridge between your Relevance AI workspace and external AI clients, allowing you to leverage your custom tools across multiple platforms. This means the powerful tools you’ve built in Relevance AI can now be accessed and utilized by your favorite AI assistants outside our platform.➡️ Extend tool availability – Use your Relevance AI tools in Claude, Cursor, and other MCP-compatible AI clients➡️ Maintain a single source of truth – Update tools in one place and have changes reflect everywhere➡️ Customize your integration – Select exactly which tools to expose to external clients➡️ Simple configuration – Generate MCP server settings with just a few clicks➡️ Seamless workflow integration – Access your specialized tools wherever you work with AIWith MCP Server integration, you can create tools once in Relevance AI and use them across your entire AI ecosystem, maximizing your investment and maintaining consistency across platforms.To set up your MCP Server:

Go to your Relevance AI workspace
Under “Tools”, navigate to “Export Tools” → “MCP Server”
Select the tools you want to share and click “Generate MCP Server Configuration”
Copy your MCP configuration into your preferred client:

GPT-4.5 is now available in model selection
Expect cutting-edge performance—but at a premium
Choose wisely based on your use case

Heads-up: Costs are significantly higher, so keep that in mind when using it in high-volume workflows.To get started, select OpenAI GPT-4.5 in your agent settings and test how it fits into your workflows. If you’re interested in trying out Relevance AI and OpenAI GPT-4.5, you can sign up to get started or book a demo to see it in action.

Other improvements

General fixes and UI updates.

February 26, 2025

Introducing Snippets: Reusable text variables for your tools and agents

Project Snippets: Reusable Text Variables for Your Tools & AgentsManaging shared text across multiple agents and tools just got way easier!Introducing ‘Project Snippets’—a centralized way to store and reference reusable text in your Relevance AI workspace.With snippets, you can:✅ Store common strings (e.g., company names, greetings, standard messages) in one place✅ Use them anywhere a variable is accepted (e.g., agents, tool inputs)✅ Avoid redundant updates—edit once, update everywhere✅ Eliminate ‘prop-drilling’ by making shared text easily accessibleHow it works:Define a snippet and reference it using the snippets. prefix. Example: “This means you can update once and apply everywhere—no more manually changing the same text across multiple tools!You can find Snippets under the left hand side bar. Try it today and simplify your workflow!

Other improvements

General fixes and UI updates.‍

February 25, 2025

Anthropic's Claude 3.7 Sonnet now in Relevance AI

You can now use Anthropic’s Claude 3.7 Sonnet as an agent model in Relevance AI, giving you more flexibility in selecting the right model for your use case. To get started, select Claude 3.7 Sonnet in your agent settings and test how it fits into your workflows. Alongside this release, Anthropic also launched Claude Code—its first agentic coding tool. Our lead AI engineer, Aman Arora, put it to the test with the Relevance AI SDK, and the results were impressive:➡️ Generated a 1,300+ LOC pull request with unit tests for the Relevance AI SDK—all without Aman writing a single line of code➡️ Understood our public repo in minutes, following existing code patterns without explicit instructions➡️ Ran tests, fixed errors, and created a PR—iterating on feedback and automatically resolving issues➡️ Installed pytest-asyncio on its own to test async functions, demonstrating strong contextual reasoning➡️ PR cost: $3.30 USD—a glimpse into the efficiency of agentic codingIf you’re interested in trying out Relevance AI and Claude, you can sign up to get started or book a demo to see it in action.

Other improvements

General fixes and UI updates.

February 19, 2025

Annual plans now available

Annual Plans Now Available: Save 10% with Yearly BillingRelevance AI now offers annual subscription plans, giving you more flexibility and better value. With annual billing, you get:✅ 10% discount compared to monthly plans ✅ 12 months’ worth of credits upfront✅ Longer validity for purchased top-ups ✅ Flexible upgrade & downgrade optionsHow it works:

If you upgrade your plan, the change takes effect immediately
If you downgrade or switch to a monthly plan, changes happen at the end of your billing cycle
If you upgrade your plan, any unused credits from an annual plan will be refunded when switching from yearly to monthly
On an annual plan, you can still buy top-up credits - what’s good is they’ll take longer to expire because of the yearly reset

Click on ‘Manage Plan’ to switch to annual billing today!

Other improvements

General fixes and UI updates.

February 18, 2025

Edit and reschedule scheduled messages

Edit & Reschedule Scheduled Messages with EaseWe’ve introduced an update to Schedule Messages, making it easier to edit and reschedule scheduled messages directly in Task View.When managing scheduled messages, you often need to make quick changes—whether it’s adjusting the content or rescheduling the send time. Previously, this meant canceling and recreating messages from scratch, but not anymore.Now, you can:➡️ Edit the content of a scheduled message before it sends➡️ Reschedule a message without needing to cancel and recreate itThis means more flexibility and a smoother workflow experience.To edit a scheduled message, simply navigate to Task View, make your changes, and save—no need to cancel and restart.Next time you need to adjust a scheduled message, try it out directly in Task View!

Other improvements

General fixes and UI updates.

February 14, 2025

OpenAI o3-mini now in Relevance AI

You can now use OpenAI o3 Mini as an agent model in Relevance AI, giving you more flexibility in selecting the right model for your use case.When working with AI-driven workflows, you often need an efficient, cost-effective model for tasks like:➡️ Running lightweight AI processes➡️ Generating responses at a lower cost➡️ Balancing model performance with budget optimizationWith OpenAI o3 Mini, your AI agents now have a new model option that improves efficiency while keeping costs under control.To get started, select OpenAI o3 Mini in your agent settings and test how it fits into your workflows.If you’re interested in trying out Relevance AI and OpenAI o3 Mini, you can sign up to get started or book a demo to see it in action.

Other improvements

General fixes and UI updates.

February 13, 2025

Custom Tool Outputs

Custom Tool Outputs: More Control Over How Data is RenderedWe now have the ability to customize tool outputs, allowing you to manually define how data is displayed instead of relying on automatic formatting. When building AI workflows, flexibility in data presentation is key. This update brings 8 Rendering Options:✅ Auto✅ Raw✅ JSON✅ Table✅ Image✅ HTML✅ Markdown✅ Hide These changes can be seen in three different areas:

Agents

New agent task action view UI displays the selected output format.

Option to view the tool output in the agent timeline through the dropdown.
Tool builder: Users can manually configure output formatting in tool configuration settings.

To get started, head to the final tool output settings → configure → select manual output → add variable(s) → choose edit.Before applying these settings, you’ll have the opportunity to preview how each rendering option affects the final output. This update provides greater flexibility in presenting data, ensuring tool outputs are displayed in the most relevant format for your workflow. If you’re interested in trying out Relevance AI and Custom Tool Outputs, you can sign up to get started or book a demo to see it in action.

Other improvements

General fixes and UI updates.

February 12, 2025

Send emails with attachments in Gmail and Outlook

Now in Relevance AI: Attachments in Agent-Generated EmailsYou can now add attachments to emails sent by AI agents in Relevance AI, allowing for more complete and professional communication.When automating emails, you often need a way to send essential documents, reports, and media files, such as:✅ Sending invoices and contracts as PDFs✅ Sharing reports in CSV format✅ Including images for marketing campaigns✅ Attaching videos for client communications✅ And much more!With this update, your AI agents can now handle attachments seamlessly, eliminating manual steps and ensuring critical files are sent along with automated emails.This applies to the following tool steps: ‘Send Email,’ ‘Send Gmail email,’ or ‘Send Outlook email’.Here’s how it works:1️⃣ Upload your file using the “File to URL” input, or generate a temporary link with the Python tool step2️⃣ In the top right of your send email tool step, click the cog icon to open “Advanced Settings”3️⃣ In the ‘File Attachments’ section, enter each “file name” and “download link” pair inside a JSON object (e.g., “file1.txt”: “https://example.com/file1.txt”)Before sending, you’ll have the opportunity to review all attachment details, ensuring your files are correctly included.This feature enhances AI-driven email automation by making it more complete, efficient, and professional—perfect for automated reporting, customer communications, and more.If you’re interested in trying out the new email attachment functionality, you can sign up to get started or book a demo to see it in action.

Other improvements

General fixes and UI updates.

February 6, 2025

Power up your AI Agents: New triggers for ZoomInfo, Telegram, Google Calendar & more!

Big updates just dropped! Your AI agents can now connect and react to more platforms, making automation even more powerful.When automating workflows, you often need seamless integration across multiple tools.These new updates enable:✅ Automating actions based on ZoomInfo Intent Topics. Agents can now be triggered by ZoomInfo, perfect for customers leveraging ZoomInfo Intent Topics to stay ahead of key signals.✅ Triggering AI workflows directly from Telegram messages. Your agents can now integrate seamlessly with Telegram!

Trigger agents from Telegram messages
Search through your message history
Send messages
…and more!

✅ Running AI workflows before, after, or exactly at a Google Calendar event. Set your AI agent in motion before, after, or exactly at the time of a Google Calendar event—perfect for automating workflows around meetings and key events.✅ Backfilling Salesforce data with a One-Off Sync. Need to backfill Salesforce tasks or pull data you missed? Now you can! Just go to Advanced Settings > Execute Once Off Sync to run a single-time sync (excluding LIMIT queries).

Fetches historical Salesforce data
Ideal for backfilling missed records

✅ Generating and publishing LinkedIn posts from AI agents. Agents can now generate and publish LinkedIn posts directly.✅ Using the Google Sheets API to send, retrieve, and update data. Easily send, retrieve, and update data within Sheets.✨ To get started, explore the new integrations in your agent settings.Before enabling new triggers, you’ll have the opportunity to review automation details to ensure they align with your workflow needs.These enhancements make automation more connected, responsive, and intelligent—allowing your AI agents to work seamlessly across different tools.If you’re interested in trying out Relevance AI and OpenAI o3 Mini, you can sign up to get started or book a demo to see it in action.

Other improvements

**🛠 More Control with Custom Tool Outputs**Choose how tool outputs are formatted:

Raw
Markdown
Table
JSON
HTML
Code snippet

**🔍 Smarter Search for Tool Templates**Finding the right tool just got easier. Semantic search now powers tool template searches, meaning you don’t need to type an exact match—just search by meaning. This makes it much easier to connect placeholder tools when inventing new agents!‍✨ Ready to try these updates? Log in now and start automating!

January 22, 2025

Simulate the entire agent creation process—in real time!

Your Agent Generator ‘Gen’ has leveled up, now allowing you to simulate the entire agent creation process in real time. When building AI agents, you often need a way to preview how they function before deploying them. With this new update, you can: ✅ Run an End-to-End Simulation – Watch your AI agent operate before launch✅ Gain Real-Time Insights – See how your AI agent performs at every step ✅ Preview Tools & Capabilities – Review every aspect of your agent’s abilities in actionTo get started, type your needs into the “I want an agent that…” field, such as: 📌 “Generates employee satisfaction surveys”Sit back and watch as your AI agent runs through every step of its workflow in real time.This update makes agent building more transparent and intuitive, ensuring your AI works exactly as expected before going live. If you’re interested in trying out the new Agent Inventor, you can sign up to get started or book a demo to see it in action.

Other improvements

General fixes and UI updates.

January 21, 2025

AI Tools just got a massive glow-up!

We’ve improved our tools library—the skills your AI agents rely on—to help you build smarter, more capable agents. When creating AI workflows, having well-optimized tools is critical. This update brings: 1��⃣ Smarter tools – All tools now follow our Tool Style Guide for better clarity, names, and discoverability. 2️⃣ Enhanced performance – Default LLMs have been upgraded, delivering faster, better results at reduced costs. 3️⃣ Expanded tool library – 31 brand-new tools added, including 5 tailored for Google Calendar. 4️⃣ More customization – 19 new tool steps provide even greater flexibility to build and innovate. To get started, explore the updated tool library inside Relevance AI. This update makes AI tool-building more intuitive, powerful, and customizable than ever. 📖 Learn more in our Tool Style Guide.)

Other improvements

General fixes and UI updates.

January 15, 2025

Introducing AI Agent Generator

The wait is over. Building AI agents doesn’t have to be complicated. With Agent Generator, anyone can get started. This is for you if:

You’ve thought, “AI agent building isn’t for me.” 🤷
You’re unsure where to start 🤔
You learn by doing and want an easy, hands-on approach 🙌

Agent Generator solves this by allowing you to describe what you need in plain English, instantly generating a blueprint to set up your AI agent. To get started, simply type your needs into the “I want an agent that…” field and watch as your personalized agent blueprint is created. Keen to power your agent building with Gen? 👇For now, Agent Generator provides a fully personalized framework for your AI agent, including placeholders like “Get Instagram Account Analytics” for where your AI tools go. While it doesn’t automatically create or insert the AI tools yet, you can either build them yourself or browse through available tool templates (for now). More features coming soon!If you’re interested in trying out the new Agent Inventor, you can sign up to get started or book a demo to see it in action.

Other improvements

General fixes and UI updates.

January 14, 2025

ModernBert, more DSPy support and Qwen 2.5

New models and features have landed in Relevance AI, expanding support for advanced AI capabilities. When working with AI-driven applications, having optimized models and training tools is key. These new updates include: ✅ ModernBERT for Advanced RAG – Now leveraging ModernBERT Embed (released by the answer.ai team), a model trained from ModernBERT-base, bringing new embedding advancements to AI workflows. More details on the model are available here: https://huggingface.co/nomic-ai/modernbert-embed-base✅ Expanded DSPy Support – We’ve added DSPy get training data, DSPy train, and DSPy run steps to train DSPy systems for response generation based on gold set answers. ✅ Qwen 2.5 for AI Agents – Our tool-calling model suite now includes Qwen 2.5, known for exceptional coding & tool execution performance, achieving benchmarks comparable to GPT-4o. To get started, explore these new models and capabilities inside Relevance AI. Before using these updates, you’ll have the opportunity to review model specifications and tool integrations to ensure they align with your workflows. These enhancements bring more power, flexibility, and precision to AI agents, making your automation workflows even stronger. If you’re interested in learning more, you can sign up to get started or book a demo to see it in action.

Other improvements

A small one but a good one! —> The entry point for viewing agent queues has been restyled!At a glance you can now see how many active queues your agent has and how many upcoming items are going to be processed in those active queues. For better user experience, the button is now also hidden if the agent has no queues (active or paused). The scheduled triggers queue is now only created when the agent enables that ability instead of by default on agent creation.

Earlier changes

2026

26 updates

2024

17 updates

2023

8 updates

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

​Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements

Other improvements