The Batch Changes list page now supports searching by title, letting you filter down results by typing keywords that match the batch change’s name. Previously, the list view only showed the 15 most recent batch changes by default, with the option to load 15 more at a time. For customers with long histories of batch changes - sometimes hundreds deep - this made it time-consuming to locate a specific one.

Now you can simply search by title to quickly narrow the list and jump straight to the change you care about, significantly improving the experience for teams managing large volumes of batch changes.

Announced in January, auto-edit goes beyond traditional autocomplete by analyzing recent edits and suggesting context-aware changes that offers a seamless, non-linear coding experience.

Enterprise customers on Google Cloud Platform (GCP) can now use the "extended thinking" variant of Claude 3.7 Sonnet - optimized for extended reasoning and deeper understanding - when using Cody.

This update allows customers that rely on GCP infrastructure access to Anthropic's latest and greatest model, resulting in richer, more thoughtful responses in chat-based interactions within Cody.

Sourcegraph Analytics now has an Overview page that highlights and explains key value metrics including usage, time saved with Sourcegraph, and Percentage of Code Written (PCW) by Cody.

Our guiding philosophy is to provide users access to the latest and greatest models, and we review model availability based off usage and feedback as older models are replaced by newer ones. With the latest update of Sourcegraph and IDE plugins, we are making the following changes to model availability for Cody Free, Cody Pro, Sourcegraph Enterprise Starter and Enterprise customers who use Cody Gateway.

We are deprecating the following models [...]

OpenAI's latest cost-efficient reasoning model o3-mini was announced last month, and in Sourcegraph 6.1 we are making o3-mini-high available to all Enterprise Starter and Enterprise customers.

o3-mini is purported to be OpenAI's "highest performing released model on SWEbench-verified" for software engineering tasks, and we're excited to provide access to this model to customers.

A few weeks ago we added a major upgrade to the Prompt Library, with the ability to add specific files, repositories, and other context in saved prompts. With this update we've streamlined the UI in the editor by moving all of the 'current' context buttons like Current File and Current Selection into the @-mentions menu, creating a more natural-feeling spot for all of your context options to live in one place.

This change does not break existing prompts that use cody:// syntax and they will function as normal.

We recently announced the experimental version of Cody for Visual Studio, starting with chat functionality to help you understand the code you're working with, and today we're excited to add autocomplete to the latest version of the plugin.

Visual Studio users can now leverage the same autocomplete experience as they would in Cody for VS Code and JetBrains, with Cody providing accurate single and multi-line autocomplete suggestions while writing code.

We're making Sourcegraph more accessible to growing teams! Enterprise Starter is a new plan designed for teams of up to 50 developers, giving them access to powerful code search, AI chat, multi-repo context, and more—all for just $19 per user/month.

What's included:

With Sourcegraph 6.0, we're updating the chat experience by introducing a unified interface that combines AI-powered chat and code search into a single, seamless UI. This update helps you search, understand, and create code faster and more efficiently, whether you're in VS Code, JetBrains IDEs, or using Sourcegraph on the web.

What's new:

Sourcegraph is industrializing enterprise software development with the introduction of AI agents, designed to automate repetitive, time-consuming tasks and accelerate how enterprises build software.

The first available agent, the Code Review Agent, is now in Early Access, with additional agents for code migration, testing, documentation, and notifications coming soon. These agents are customizable, enabling enterprises to address bottlenecks and accelerate progress across large, complex codebases. This allows AI to impact and scale beyond individual developers and across the whole company.

Formerly Cody Analytics, Sourcegraph Analytics now provides customers with aggregate and product-specific metrics for Code Search, Batch Changes, and Code Insights, in addition to the Cody metrics that were previously available. The change in name reflects the new metrics that provide insight into how your developers are interacting with features across the entire Sourcegraph platform, and can help you understand ROI.

Sourcegraph Analytics also includes a CSV export with key metrics like number of searches, chats, autocomplete suggestions, completion acceptance rate (CAR %), and more, by user, day, client, and language — perfect for automating retrieval and analyzing data in ways that make the most sense to your organization.

We're introducing agentic chat to Cody users—a transformative upgrade that makes Cody smarter and more autonomous.

With agentic chat, Cody proactively gathers, reviews, and refines context from your codebase, shell, and the web to deliver high-quality, context-rich responses. Whether generating accurate unit tests, answering complex questions, or retrieving the latest API docs, agentic chat eliminates the need for manual context input, saving time and ensuring precision.

The Prompt Library is getting a major update for teams: the ability to embed specific files, repositories, and other context directly into prompts. This feature enables teams to create precise, reusable prompts tailored to their unique workflows, helping ensure collaboration, consistency, and high-quality outputs across their team.

We're excited to introduce auto-edit, an experimental feature now available in Cody for VS Code. Auto-edit goes beyond traditional autocomplete by analyzing recent edits and suggesting context-aware changes, enabling a seamless, non-linear coding experience.

Prompts provide Cody users the ability to create and share actions that can be tailored specifically to their development workflow. In this month's release, Enterprise users can now add tags to prompts, making it easier to group, organize, and filter prompts for easier discovery in the Prompt Library.

Gemini 2.0 Flash Experimental was announced last week, and we're happy to announce support for Google's latest model across all plans for Cody chat. Google indicates Gemini 2.0 Flash outperforms Gemini 1.5 Pro on key benchmarks at twice the speed, with promising improvements across developer-related benchmarks.

Cody users will now see Gemini 2.0 Flash Experimental in the model selection list for them to use when using chat, and the model is available in the latest versions of Cody for VS Code, JetBrains, and Cody Web. For Cody Enterprise customers, the new model is only available via Cody Gateway. These customers will need to upgrade to the latest release (5.11) and use modelConfig to access the model.

We're excited to announce the release of Cody for Eclipse! Eclipse devs can now natively work with Cody in their editor, including users on all Cody plans (Free, Pro, and Enterprise). This release is experimental, and it includes Cody's chat and Prompts functions.

Ask questions about your code, generate code, and fix code all through Cody chat. You can also automate your work with the Prompt Library. Autocomplete and inline editing capabilities will come in a future release.

While Cody primarily lives in your editor, the broadly trained LLMs it uses under the hood let it answer a wide range of questions beyond just coding. We're introducing a new feature for Cody Enterprise that allows teams to give Cody more prescriptive guidance on what kinds of questions it can answer.

Admins on Cody Enterprise instances can now configure prompt pre-instructions. These are text instructions that Cody uses for every chat query, allowing teams to shape how Cody responds to users. For example, if you don't want Cody to answer questions relating to sensitive non-code matters, you can pre-instruct Cody against them.

Cody is built to support the latest and greatest LLMs interchangeably so that developers always have access to the most powerful code AI solution. For Cody Enterprise customers, we're expanding Cody to be even more flexible and allow admins to select multiple models from multiple providers, which end users can then choose from on-demand.

We're excited to announce general availability for enterprise model election. Cody Enterprise users can now select and hot-swap between multiple model options. Cody Enterprise admins can select which models to provide for users, including models from different providers, including Amazon Bedrock, Azure OpenAI, and Google Cloud Vertex AI.