> 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/ai-features/ai-features.md).

# AI Features Overview

**Think. Learn. Adapt.** Taskade AI features form the living intelligence layer of Workspace DNA, creating systems that understand, evolve, and provide increasingly intelligent value with every interaction.

{% hint style="success" %}
**Living Intelligence Layer** — AI that doesn't just assist, but learns from your business, adapts to your needs, and continuously improves. Powered by EVE, your living AI companion.
{% endhint %}

## What is Living Intelligence?

Living Intelligence is the agent layer in Taskade. It’s how your workspace can **reason**, **draft**, **classify**, and **take action** using context from your projects.

Canonical foundation: [Workspace DNA](/platform/workspace-dna.md).

### What you use it for

* **Customer-facing help**: answer questions, route requests, propose next steps.
* **Ops + admin**: summarize updates, draft emails, generate reports, fill data gaps.
* **Sales + marketing**: qualify leads, personalize outreach, reuse brand voice.
* **Research**: extract key points from docs, compare options, track decisions.

### Core building blocks

#### AI agents

Agents are persistent assistants. You can scope them to a workspace, project, or use case. Learn more about [Taskade AI Agents](https://www.taskade.com/agents).

Start here: [AI Agents Getting Started](/ai-features/ai-features/ai-agents-getting-started.md).

#### Knowledge (what agents learn from)

Most “smartness” comes from the knowledge you give agents. That includes project data and uploaded docs.

Start here:

* [Workspace DNA](/platform/workspace-dna.md)
* [Agent Knowledge & Memory](https://www.taskade.com/learn/agents/knowledge)

#### Tools (what agents can do)

Tools let agents do more than write text. They can create tasks, call integrations, and move work forward.

Start here:

* [Integration Overview](/automations/automation/comprehensive-integration-guide.md)
* [Actions & Triggers](/automations/automation/actions.md)

### Getting started (fast)

1. Create one agent for one job.
2. Give it 2–3 knowledge sources.
3. Run it on real inputs.
4. Tighten prompts and add tools only if needed.

### Where it shows up

* In your workspace as an assistant.
* Inside Genesis apps as an AI layer.
* In automations as a decision-maker.

Next:

* Build apps with agents: [Living Systems That Transform Business](/taskade-genesis/genesis.md)
* Put actions on autopilot: [Living Motion Overview](/automations/automation.md)

{% hint style="info" %}
This page stays overview-level. Model comparisons, tool catalogs, and deep agent training patterns live in the linked guides.
{% endhint %}


---

# 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:

```
GET https://docs.taskade.com/ai-features/ai-features.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.