Overview
Agent Chat is a revolutionary way of interacting with AI that lets you experience the power of tailored, context-aware responses from your custom AI agents.
๐ก
Powered by Taskade Genesis โ Taskade is now a full-stack AI productivity platform. Build apps, deploy agents, and automate workflows from a single prompt. Learn more about Genesis.
๐ก Note: New to AI agents? Read our Custom AI Agents guide first.
Agent Chat vs. Generic AI Chats?
Every custom AI agent you create comes with a unique knowledge base, tone, and style. This means that the answers and guidance provided by agents are more tailored and specific compared to regular AI chats.
Here are a few more differences:
| ๐ข AI Agent Chat | ๐ต Generic AI Chats | |
|---|---|---|
| Knowledge Base | Fully customizable; agents can learn and adapt from your specific projects and the knowledge you upload to your workspaces. | Based on general, broad knowledge with no customization. |
| Tone and Style | Tailored to your preferences and needs. Interactions match your desired tone and style. | Standard, one-size-fits-all responses that require additional prompts to customize tone and style. |
| Context Awareness | Agents are context-aware, capable of understanding and integrating information from your projects to provide contextually relevant answers. | No context awareness. |
| Response Relevance | Delivers highly relevant and focused responses that are directly aligned with your tasks and projects. | Responses can be vague or off-topic, often requiring additional clarification. |
Start an Agent Chat
You can interact with your custom AI agents in many different ways:
(method 1): Agents Tab
- Navigate to the Agents tab at the top of your workspace.
- Select your custom AI agent.

- Click โ New chat to start a new conversation.

Ask your agent questions or type / to show a list of custom agent commands.
You can also click the Commands button underneath the chat window.
๐ก Note: Once activated, the commands still require prompts for context.

(method 2): Project Chat
- Open a project and click the chat balloon icon ๐ฌ (top-right).

- Use the drop-down menu at the top of the chat to choose an agent.

- Chat with your agent or type / to use custom agent commands.
- Click Copy to save the output, or Add to Project to paste it into the editor.

(method 3): Agent Toolbar
- Create agents following the steps in this article.
- Agents will be added to a sidebar on the right.
- Click avatars in the sidebar to interact with your agents.

Want to share your custom agent with your team? Follow these steps:
- Navigate to the ๐ค Agents tab.
- However the mouse cursor over an agent.
- Click the Share Agent button on the right.

- Enable the Public access toggle.

You can now customize the public agent:
Mode: Choose the level of interactions with the agent.
Copy Knowledge: Decide if you want to allow others to copy agent knowledge.
Hide Branding: Remove Taskade branding in the agent footer.
Theme: Select light, dark, or automatic theme.
Background: Select or upload a custom background.

Finally, you can copy the agent link or embed code:
Click Copy link to share a direct link.
Click Copy code to embed the agent on your website.

Collaborative Agent Chat
You and your team can chat and collaborate with AI agents in the same space, at the same time. This feature brings tailored AI insights into your conversations.
- ๐ค Use a meeting agent to facilitate meetings
- ๐ Employ a data agent to quickly retrieve data
- ๐ Tap a knowledge agent for data and knowledge
- ๐ง Engage a creativity agent to generate new ideas
- ๐ Deploy an analysis agent to support decision-making
1) Chat with a Single Agent
- Open the chat box (see the previous sections).
- Choose an agent from the drop-down at the top.
- (optional) Click the โบ ๐ค button to invite people to the conversation.
- Type a prompt to start a conversation.
๐ก Note: When you start a chat, a tooltip at the bottom of the chat box will let you know if the chat is public or private, so you can see who has access.

2) Chat with an AI Team
- Open the chat box (see the previous sections).
- Choose an AI Team from the drop-down at the top.

- (optional) Click the โบ ๐ค button to invite people to the conversation.
- Choose an agent you want to interact with or set to Auto and let AI decide.
- Type a prompt to start a conversation.

Use Agent Responses
Use quick chat actions to make the most of conversations with your agents:
Click the โจ Plus button to add the output to:
โ An existing project
๐ Agent knowledge

- Click the ๐ Copy button to save the output to the clipboard.

Click the ๐ Create new button use the output:
๐ In a new project
๐ฑ As a seed for AI Project Studio
In an ๐ Automation Flow

Export Conversations
Want to archive or reuse conversations with your agents? Here's to you can do that:
- Click the three dots ยทยทยท next to a conversation thread.
- Choose Export from the drop-down list.

Choose one of the export methods:
- Copy the converstion to the clipboard.
- Download the conversation as a Markdown file.

Shared AI Agent Chats
You can allow others to interact with your agents publicly. The public conversations will be visible inside the agent dashboard under the Inbox tab.
To enable public agent chats:
- Navigate to the ๐ค Agents tab.
- However the mouse cursor over an agent.
- Click the Share Agent button on the right.

- Enable the Public access toggle.

You can now customize the public agent:
Mode: Choose the level of interactions with the agent.
Copy Knowledge: Decide if you want to allow others to copy agent knowledge.
Hide Branding: Remove Taskade branding in the agent footer.
Theme: Select light, dark, or automatic theme.
Background: Select or upload a custom background.

Finally, you can copy the agent link or embed code:
Click Copy link to share a direct link.
Click Copy code to embed the agent on your website.

When somebody interacts with the public agent, the conversations will be aggregated inside the Inbox tab in the agent dashboard:
- Choose your agent in the Agents tab.
- Navigate to the Chat tab (top-right).
- Go to the Inbox tab in the left sidebar to see threaded conversations.

Use Threaded Conversations
You can engage in multiple conversations with the same agent concurrently.
- Focused conversations: Keep multiple chat threads with the same AI agent neatly organized, each tailored for specific topics or projects.
- Customized interaction: Each chat maintains its unique context, which makes it easier to manage complex tasks without confusion.
Here's how it works:
- Open the agent chat (only applies to methods 1 and 3).
- Click โ New chat to start a conversation.

Use the New chat button in the sidebar on the left to create new threads.
Repeat the step as many times as you need.
Click the time-stamped items in the sidebar to resume conversations.
- Click the three dots ยทยทยท next to a thread to remove or rename it.

- Click the Toggle Sidebar button in the top-right corner to hide chat threads.

Enable Fullscreen Chat
Chat with your agents in full screen to keep conversations in focus:
Choose an agent from the Agent Sidebar.
Click

to open the Agent Modal.
(1) Click

to open the chat in a new window.(2) Click

to enable fullscreen mode.

Quick Add
You can instantly add any agent message into a project with Quick Add.
- Start a new chat with your agent.
- Click the โ icon under the agent's message.

- Choose where you want to add the output.
- Click Add to project to confirm.

Organize the Agent Sidebar
The agent sidebar lists your agents within a workspace. Here's how to customize it:
- Navigate to your workspace or folder.
- Click the โ Manage agents button.

Hover the cursor over any of your agents.
Click the star next to the agent's name to add it to the sidebar.

Click & hold an icon representing an agent to reorder it.
Release the mouse button to drop the agent in its new place.

Format Messages
You can use Markdown syntax to format and structure your prompts:
๐ก Vist: Visit Markdown Support to learn more.
| ๐ ๏ธ Feature | โจ๏ธ Syntax |
|---|---|
| Bold | bold |
| Italic | italic |
| Underline | Double underline test |
| Block quote | > block quote |
| Strikethrough | |
| Inline code | inline code |
| Code block | codeblock |
| Strikethrough | |
| Unordered list | - or * |
| Ordered list | 1., 2., 3., etc. |

Code Block Support
Agents can generate code snippets in the agent chat. This feature is useful for quick prototyping, debugging, and even learning new programming concepts.
Start a conversation with your agent.
Ask the agent to generate code.
e.g. "generate a Python function to sort a listโ
3. **Hover** the **mouse cursor** over the **code block**.
4. Click **Copy** to save the code block to the clipboard.
<iframe src="https://www.youtube.com/embed/IniIdZ-6i6A?rel=0" title="AI Agent Chat advanced features video" width="100%" height="400" allow="autoplay; fullscreen" allowfullscreen style="border: none"></iframe>
---
### Tables
Agents can render data in table format to make it easier to read and analyze. This is useful for organizing information in reports, comparisons, and schedules.
1. **Start a conversation** with your agent.
2. **Ask** the agent to **generate in a table format.**
- ```
e.g. โgenerate a table that summarizes global sales of EVs"
- Hover the mouse cursor over the table.
- Click Copy to save the table to the clipboard.

Use Agent Responses
Use quick chat actions to make the most of conversations with your agents:
Click the โจ Plus button to add the output to:
โ An existing project
๐ Agent knowledge

- Click the ๐ Copy button to save the output to the clipboard.

Click the ๐ Create new button use the output:
๐ In a new project
๐ฑ As a seed for AI Project Studio
In an ๐ Automation Flow

Agent Chat supports the latest AI models including GPT-5.2, Claude Opus 4.5, Claude Sonnet 4.5, Gemini 3.1 Pro, o3, o4-mini. Select your preferred model when configuring the agent or switch during a conversation.
โน๏ธ
Workspace DNA โ Every Taskade workspace is powered by three interconnected pillars: Memory (Projects & Databases), Intelligence (Custom AI Agents), and Execution (Automations). Together they form a continuous feedback loop that makes your workspace smarter over time.
๐ Start Building
๐
Ready to get started? Create your first project and experience the power of AI-driven productivity.
๐ Explore the Community
๐
Browse templates, agents, and apps built by the Taskade community at taskade.com/community.
Command Modes
Overview
Command modes dictate how your custom AI agents approach tasks, whether by following specific instructions or by autonomously setting goals and iteratively working towards them. Currently, there are two primary modes:
| ๐ข Default | ๐ต Plan & Execute |
|---|---|
| The agent operates directly based on your prompt without setting any additional goals. It focuses on generating content or completing tasks following the instructions provided in a prompt. | The agent sets an overarching goal based on your opening prompt and then iteratively works towards achieving that goal. This mode is more autonomous and is designed to handle complex tasks. |

Change Command Modes
Follow these steps to change modes for your agent's commands:
- Open the Agents tab in your workspace.
- Click ยทยทยท next to an agent โก Edit agent.

- Choose the Commands tab on the left.
- Select an existing command or click โ New command.

- Scroll down and click the Mode drop-down to change modes.

Plan & Execute Examples
Example 1: (specific goal) "I need strategies to increase sales revenue."
The agent identifies the goal as "strategies to increase sales revenue."
Runs related self-generated prompts to try and meet the goal, e.g.
- "best sales techniques for increasing revenue," "effective marketing strategies," "ways to improve customer retention," "how to optimize pricing strategies," etc.
Runs various prompts for 4-5 steps and then produces a summary.
Example 2: (no specific goal) "Our sales are declining."
- The agent tries to identify the goal and guess what the user expects.
- Runs related self-generated prompts to try and meet the goal.
- Runs various prompts for 4-5 steps and then produces a summary.
Example 3: (specific goal) "I need advice on employee productivity improvement."
The agent identifies the goal as "advice on employee productivity improvement."
Runs related self-generated prompts to try and meet the goal, e.g.
- "how to enhance employee productivity"
- "tools for better time management"
- "techniques to boost workplace motivation"
- "ways to create a productive work environment"
Runs various prompts for 4-5 steps and then produces a summary.
Advanced Prompting
Command modes are part of advanced techniques you can use to make your custom AI agents even more powerful. Explore these guides to learn more:
- AI Agent Fine-Tuning: Use Retrieval Augmented Generation (RAG) in training.
- Advanced Prompting: Craft precise and detailed prompts to guide AI responses.
- Automated Agentic Workflows: Design automations with agents in the center.
- Specialized AI Teams: Group agents into specialized teams.
Command Modes
Overview
Command modes dictate how your custom AI agents approach tasks, whether by following specific instructions or by autonomously setting goals and iteratively working towards them. Currently, there are two primary modes:
| ๐ข Default | ๐ต Plan & Execute |
|---|---|
| The agent operates directly based on your prompt without setting any additional goals. It focuses on generating content or completing tasks following the instructions provided in a prompt. | The agent sets an overarching goal based on your opening prompt and then iteratively works towards achieving that goal. This mode is more autonomous and is designed to handle complex tasks. |

Change Command Modes
Follow these steps to change modes for your agent's commands:
- Open the Agents tab in your workspace.
- Click ยทยทยท next to an agent โก Edit agent.

- Choose the Commands tab on the left.
- Select an existing command or click โ New command.

- Scroll down and click the Mode drop-down to change modes.

Plan & Execute Examples
Example 1: (specific goal) "I need strategies to increase sales revenue."
The agent identifies the goal as "strategies to increase sales revenue."
Runs related self-generated prompts to try and meet the goal, e.g.
- "best sales techniques for increasing revenue," "effective marketing strategies," "ways to improve customer retention," "how to optimize pricing strategies," etc.
Runs various prompts for 4-5 steps and then produces a summary.
Example 2: (no specific goal) "Our sales are declining."
- The agent tries to identify the goal and guess what the user expects.
- Runs related self-generated prompts to try and meet the goal.
- Runs various prompts for 4-5 steps and then produces a summary.
Example 3: (specific goal) "I need advice on employee productivity improvement."
The agent identifies the goal as "advice on employee productivity improvement."
Runs related self-generated prompts to try and meet the goal, e.g.
- "how to enhance employee productivity"
- "tools for better time management"
- "techniques to boost workplace motivation"
- "ways to create a productive work environment"
Runs various prompts for 4-5 steps and then produces a summary.
Advanced Prompting
Command modes are part of advanced techniques you can use to make your custom AI agents even more powerful. Explore these guides to learn more:
- AI Agent Fine-Tuning: Use Retrieval Augmented Generation (RAG) in training.
- Advanced Prompting: Craft precise and detailed prompts to guide AI responses.
- Automated Agentic Workflows: Design automations with agents in the center.
- Specialized AI Teams: Group agents into specialized teams.
