July 4, 2026

Taskade developer changelog — July 4, 2026: TSK-1 (Taskade System Kernel) launches — an intelligence layer that auto-routes across four capability tiers underneath every AI agent, automation, and Gene

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; for release newsletters see taskade.com/blog/updates.

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.

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 for the full reference.

---

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.

---

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.