Control every interaction: Introducing Tabnine’s new personalization features 

Every engineering team is unique — and has its own distinct and intricate ways of writing, maintaining, and securing the code that powers its applications. This uniqueness means that a one-size-fits-all approach for using AI simply won’t suffice. For AI to drive meaningful impact at enterprises, it must deliver recommendations that are tailored to each team’s specific practices and preferences.

To support these goals, we’re excited to announce the availability of three new features that enable you to personalize Tabnine even more: custom chat behaviors to tailor the behavior of AI chat to your needs; the ability to set the response length for AI chat interactions to get concise or comprehensive suggestions; and shareable custom commands to increase collaboration and consistency across your teams. 

Custom chat behaviors: AI your way

Custom chat behaviors, available now for all Tabnine users, fundamentally change how developers interact with Tabnine AI Chat. Think of it as having a configurable AI partner that automatically adjusts its expertise and communication style to match your team’s needs. 

Here are some common use cases that we’ve seen so far:

Senior developers working on system architecture can configure Tabnine to focus on scalability patterns, performance implications, and architectural tradeoffs. When they ask about implementing a new microservice, they’ll automatically receive responses that address service boundaries, API design, and deployment considerations.

For junior developers, Tabnine can act as a patient mentor. Configure it to provide detailed explanations that include not just the what but the why behind each suggestion. When reviewing a piece of code, it might highlight potential performance concerns while explaining the underlying computer science concepts that cause them.

International teams will particularly appreciate the language customization capabilities. Development teams in Germany, Spain, or any other location can now receive explanations, code comments, and documentation in their preferred language, removing communication barriers and ensuring nothing gets lost in translation.

Process-oriented teams can configure Tabnine to provide structured, step-by-step responses for complex implementations. When developers request guidance, it automatically breaks down tasks into clear implementation steps, includes relevant code examples, and provides a concise summary of changes — perfect for teams that value methodical, documented approaches to development. For example, developers can instruct Tabnine to “Answer in the following structure: Steps to implement, separator line for each step, a one-sentence description of the implementation and code to edit, separator line after each step, one paragraph summary of what was done” and receive consistent, well-organized responses that maintain knowledge sharing and implementation standards across the team.

These customization options are seamlessly integrated into our new interface, making it easier than ever to switch between different behavior modes. Getting started is simple: access custom chat behaviors through the Settings within Tabnine AI Chat using the gear icon next to the test agent beaker. The modernized UI provides clear visual feedback about your current settings, ensuring you always know how Tabnine is configured to assist you.

Customizing response length to meet your needs

We understand that different scenarios call for different levels of detail. Our new response length customization feature lets users fine-tune how Tabnine communicates based on their specific needs and preferences.

The “Concise” mode is perfect for experienced developers who need quick, to-the-point answers. They’ll receive focused responses that cut straight to the solution. This mode optimizes for speed and efficiency, which is ideal when you just need a quick confirmation or a brief code snippet.

The “Comprehensive” mode transforms Tabnine into a detailed technical advisor. It provides in-depth explanations, alternative approaches, and relevant examples. This is particularly valuable for complex architectural decisions, developers who are new to a team or project and need more assistance, or for documenting important technical decisions. Each response becomes a mini-learning opportunity, complete with context, best practices, and potential pitfalls to consider.

Shared custom commands: Standardizing excellence across teams

Tabnine custom commands provide users with the ability to take away the heavy lifting of prompt engineering for tasks or questions they often find themselves asking the AI chat. 

Here are some example commands you might create:

• Security audit workflows that automatically check for common vulnerabilities, analyze dependency risks, and suggest security improvements
• Test-driven development commands that generate comprehensive unit tests before implementation, ensuring quality from the start
• Logging standardization that automatically implements your platform’s logging framework for entry/exit points and key interactions
• Code refactoring patterns that align with your team’s architectural standards and performance requirements
• Documentation generators that create consistent, comprehensive documentation following your team’s templates
• Code review assistants that check for specific patterns, coding standards, and potential issues unique to your codebase
• Sequence diagram generators that visualize code interactions using PlantUML syntax, excluding standard library calls for clarity

For enterprise development teams, consistency and efficiency are paramount. Our new shared custom commands feature (available exclusively for enterprise users) takes team-wide collaboration to the next level. This highly requested feature transforms how teams standardize and share their AI interactions across projects.

At its core is the .tabnine_commands file, which lives in your repository and acts as a central source of truth for your team’s custom AI commands. This approach integrates seamlessly with your existing source control workflows, ensuring that all team members are always working with the latest, approved command set.

Engineering managers can now create standardized commands that encapsulate their team’s best practices. These commands become part of your team’s shared knowledge base, making it easier to maintain consistency across large codebases and distributed teams. New team members can quickly get up to speed with your team’s practices, and experienced developers can work more efficiently with automated, standardized workflows.

The unified command interface ensures that every team member has access to the same capabilities, reducing inconsistencies and making it easier to maintain quality standards across your entire development organization. As your team’s practices evolve, you can update these commands in one place, and the changes are automatically available to everyone.

A modern facelift for modern development

The chat interface has been rebuilt from the ground up to deliver a more modern, intuitive user experience that matches the sophistication of your development workflow. The new design isn’t just about aesthetics — it’s about making every interaction with Tabnine more efficient and enjoyable.

We’ve optimized chat performance with a focus on remote development environments, ensuring smooth operation regardless of your team’s setup. The refreshed interface brings improved readability, more intuitive navigation, and faster access to frequently used features (as well as some new ones). We’ve added new fine-tuning functionality for improved personalization in the redesigned Settings menu, improved the accessibility and layout of our input types for added context, and updated the color scheme to provide a more modern look and feel. This modernization sets the stage for our powerful new personalization capabilities, creating a seamless environment where developers can focus on what matters most: writing great code.

Getting started with personalized AI development

Ready to transform your team’s AI software development? The custom chat behaviors and chat response length features are available now for all Tabnine users across all supported IDEs. Enterprise users can access shared custom commands to start building their team-wide, user-defined custom command repository. The future of AI development isn’t just about having an AI assistant — it’s about having one that truly understands and adapts to your team’s unique needs, presented in a way that enhances rather than hinders your workflow. 

Not yet a customer? If you’d like to learn more about how Tabnine can help you accelerate software development and ship better, more compliant code, we encourage you to reach out to us.

To learn more about the new features, please check out the product documentation or attend an upcoming Tabnine Office Hours session.