Agent runtime versions define the capabilities and behavior of your Atlas AI agents. Each version includes a specific system prompt, agent tools and their prompts, and agent-specific features. When you create an agent, Atlas AI automatically pins it to the latest stable runtime version. The agent uses a specific runtime version to provide stability for production deployments. Cognite regularly releases improvements to Atlas AI, but your agent maintains consistent behavior with the assigned runtime version. You control when to upgrade your agent to a newer version.Documentation Index
Fetch the complete documentation index at: https://docs.cognite.com/llms.txt
Use this file to discover all available pages before exploring further.
Lifecycle stages
We use these terms to describe lifecycle stages for runtime versions:-
Stable version: A released runtime version that supports production use. Each stable version includes a retirement date when support ends.
- Latest stable version: The most current stable version. Use this version for new agents, agents in development, or when migrating from older versions.
- Legacy stable version: An older stable version that is supported but has been replaced by a newer stable version. Migrate to the latest version to access new features and improvements.
- Preview version: A pre-release version that provides early access to some features. We recommend that you don’t use these versions in production systems.
- Retired version: A runtime version that is no longer supported and has reached its retirement date. Atlas AI automatically upgrades agents using a retired version to the latest stable version if you don’t migrate them before the retirement date.
Agent runtime version overview
This table lists all available runtime versions with their current status and support timeline.| Version | Status | Release date | Retirement date |
|---|---|---|---|
| 1.2.0 | Latest stable | May 5, 2026 | No earlier than May 5, 2027 |
| 1.1.1 | Legacy | February 24, 2026 | No earlier than February 24, 2027 |
| 1.1.0 | Legacy | February 24, 2026 | No earlier than February 24, 2027 |
| 1.0.2 | Legacy | November 27, 2025 | No earlier than November 27, 2026 |
| 1.0.1 | Legacy | November 27, 2025 | No earlier than November 27, 2026 |
| 1.0.0 | Legacy | November 27, 2025 | No earlier than November 27, 2026 |
| 0.9.9 | Legacy | November 27, 2025 | No earlier than November 27, 2026 |
| 2.0.0-alpha | Preview | November 27, 2025 | - |
Stable version features
This table lists the features available in each stable version.| Feature | 1.2.0 | 1.1.1 | 1.1.0 | 1.0.2 | 1.0.1 | 1.0.0 | 0.9.9 |
|---|---|---|---|---|---|---|---|
| Query memory | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
| Examine data semantically | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
| Query tool (Beta) | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
Preview version features
This table lists the features available in preview versions.| Feature | 2.0.0-alpha |
|---|---|
| Query memory | ✅ |
| Examine data semantically | ✅ |
Feature overview
This section describes the features that vary between runtime versions.Query memory
Query memory is a caching capability that allows agents to store results from Query tools and pass the results as input to other tools in the same conversation. Some tools require Query memory to function, such as the Examine data semantically tool.Examine data semantically
This feature enables you to add the Examine data semantically tool to your Atlas AI agent.Query tool (Beta)
Runtime version 1.2.0 supports a new Query tool that lets agents query Data Modeling directly with explicit operations for view discovery and instance reads. It can list available views, inspect view schemas, and run list, search, aggregate, and retrieve calls on instances with configurable data model and instance-space scoping.Select a runtime version
New agents automatically use the latest stable runtime version. You can select a different version in the agent builder user interface (UI) or through the Cognite API.- Agent builder UI
- Cognite API
The agent builder displays the runtime version in the agent configuration. Change the version from the dropdown.
Upgrade to a new version
Complete these steps before you upgrade your agent to a new runtime version:- Review the feature differences between your current version and the target version.
- Test your agent thoroughly in a non-production environment.
- Verify that any custom tools or integrations work correctly with the new version.
Atlas AI automatically upgrades agents to the latest stable version when their runtime version reaches the retirement date.