> 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

{% 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 routes through function-calling for better schema adherence.
* Auth hardening: PAT bearer verification and OAuth2 JWT-ID validation tightened.
* General stability, performance, and connector reliability improvements.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.taskade.com/changelog/changelog-2026/july-2026/july-4-2026.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.