> For the complete documentation index, see [llms.txt](https://docs.taskade.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.taskade.com/changelog/changelog-2026/july-2026/july-4-2026.md).

# July 4, 2026

TSK-1 (Taskade System Kernel) launches — an intelligence layer that auto-routes AI work across four capability tiers for agents, automations, and Genesis apps.

{% hint style="info" %}
**Developer highlights.** This section tracks API, MCP, SDK, automation, and Taskade Genesis platform changes for developers. For the full product changelog see [taskade.com/changelog](https://www.taskade.com/changelog); for release newsletters see [taskade.com/blog/updates](https://www.taskade.com/blog/updates).
{% endhint %}

## What's New:

### TSK-1: The Taskade System Kernel

**TSK-1** is the intelligence layer that coordinates models, memory, agents, and workflows across your workspace. It is not a single model — it is an orchestration layer that dynamically routes each request to the right capability tier underneath. As underlying models improve, TSK-1's tier definitions stay stable; what changes is which model serves each tier.

The model picker now shows a **TSK-1** header with four capability tiers:

| Tier          | Best for                                                 |
| ------------- | -------------------------------------------------------- |
| **Instant**   | Fast edits, simple completions, quick lookups            |
| **Standard**  | Everyday work — balanced speed and reasoning             |
| **Thinking**  | Planning, creation, multi-step reasoning                 |
| **Reasoning** | Complex systems, deep analysis, multi-agent coordination |

Plus **Auto** — the recommended default — which picks the right tier per request. Agents or automations pinned to a specific model are unchanged; new agents default to Auto.

{% hint style="info" %}
**Vendor-agnostic.** TSK-1 runs on the latest frontier models. The tier describes what the system is good at, not which provider powers it — providers may change as the landscape evolves. See [TSK-1 Model Tiers](/ai-features/ai-features/tsk-1-model-tiers.md) for the full reference.
{% endhint %}

***

### Workspace DNA Framework

The **Workspace DNA** framework is now the unified architecture underneath every Taskade workspace:

1. **Projects remember** — your data and context stay connected.
2. **Agents reason** — multi-agent teams understand goals and take action.
3. **Workflows run** — automations continue after chat ends.
4. **Apps launch** — one prompt, one live app.

TSK-1 sits between the EVE persona and Workspace DNA, coordinating how intelligence flows through all four pillars. See [How Taskade Genesis Works](/taskade-genesis/genesis/how-genesis-works.md).

***

## Improvements & Fixes:

* Agent Teams create/edit/delete dialogs now match the editor chat experience.
* Public agent knowledge respects per-user row-scoped data — rows hidden from a user are never surfaced in agent answers.
* Automation AI structured output now follows your defined schema more reliably.
* Authentication hardening for personal access tokens and OAuth 2.0.
* General stability, performance, and connector reliability improvements.