# Custom AI Agents: The Intelligence Pillar

> Build a custom AI agent with your projects, tools, slash commands, and a public chat link.

- Source: https://www.taskade.com/learn/agents/custom-agents
- Section: AI Agents
- Updated: 2026-11-09
- Index of all pages: https://www.taskade.com/learn/llms.txt

## Overview

Build a custom AI agent that answers from your projects, uses tools, and publishes as a public chat. This page walks from an empty **AI Agents** list to a tested teammate you can share.

> **TL;DR:** Build a custom AI agent in Taskade with no code. Open AI Agents, write the instructions, add your projects and files as knowledge, and turn on tools. Your knowledge is the agent's persistent memory. Test it in Messages, then share a public link from the Publish tab. Custom agents are the Intelligence layer of [Workspace DNA](https://www.taskade.com/learn/genesis/workspace-dna).

![Taskade Genesis banner that reads One prompt, one app](https://www.taskade.com/static_images/learn/agents/custom-agents-64576d7b.jpg)

Watch how to build a custom AI agent end to end:

[The Complete Guide to Building AI Agents with Taskade](https://www.youtube.com/embed/7-EOl0lW_4c?rel=0)

## Custom AI Agent Basics

A custom AI agent is a reusable AI teammate that you build for one job. It combines **instructions**, **knowledge** that serves as its persistent memory, **tools**, and a **frontier model**. It acts on your workspace and your connected apps, and you can share it with one public link.

![An AI agent's Tools panel, with connected apps switched on so the agent can act and not only answer](https://www.taskade.com/static_images/newsletter-gifs/2026-05-03-agent-workflows-tools.gif)

| | Chatbot | Custom AI agent in Taskade |
| --- | --- | --- |
| **Main job** | Answers questions | Answers, decides, and acts |
| **Knowledge** | General training data | Your projects, files, links, and videos |
| **Context** | One generic thread | Each chat keeps its history. Connected projects stay current |
| **Tools** | None | Web search, project actions, automations, 100+ integrations |
| **Can start work** | No | Yes, it runs automations and creates tasks |
| **Shareable** | Rarely | One public link, or an embed on your site |

An agent runs on **frontier models from top AI labs**. TSK-Auto is the default and picks a model for each request.

## See a Custom Agent in Action

The app below is a published Taskade Genesis app with a custom agent inside it. Open the live version, clone it, and look at how the agent is set up.

[![Content Agent Chatbot, a live custom AI agent published as a Taskade Genesis app](https://www.taskade.com/static_images/community-apps/cibvdbpnmfh8ql8k-content-agent-chatbot.webp)](https://www.taskade.com/app/content-agent-chatbot-cibvdbpnmfh8ql8k)

> 💡 **Clone, then learn.** Clone the app into your workspace and the agent comes with it. Browse more in the [Taskade App Factory](https://www.taskade.com/apps), or describe your own at [taskade.com/create](https://www.taskade.com/create).

## Intelligence in Workspace DNA

Agents are the **Intelligence** (■) pillar between **Memory** (▲) and **Execution** (●). Projects store what your team knows. Agents read that context and decide. Automations do the work, and the results go back into your projects.

```mermaid
graph TD
    M["▲ Memory<br/>Projects · files · data"]:::mem
    I["■ Intelligence<br/>AI agents read and decide"]:::intel
    E["● Execution<br/>Automations run the work"]:::exec
    M -->|agent reads context| I
    I -->|agent starts an action| E
    E -->|results written back| M
    classDef mem fill:#0d1b2a,color:#7dd3fc,stroke:#38bdf8,stroke-width:2px
    classDef intel fill:#2a1225,color:#ff8fa3,stroke:#ff2d60,stroke-width:2px
    classDef exec fill:#0d1a0e,color:#86efac,stroke:#22c55e,stroke-width:2px
```

When an automation writes a result into a project that the agent reads, the agent sees that result in its next reply. See [Workspace DNA](https://www.taskade.com/learn/genesis/workspace-dna) for the full model.

## Anatomy of an Agent

Each agent has its own page with four tabs. The **Edit agent** button at the top opens the same settings in one dialog.

```text
┌───────────────────────────────────────────────────────────┐
│ Support Bot                              [ Edit agent ]   │
├───────────────┬──────────────┬────────────┬───────────────┤
│ Messages      │ Knowledge    │ Actions    │ Publish       │
├───────────────┼──────────────┼────────────┼───────────────┤
│ My Chats      │ Instructions │ Commands   │ Publish Agent │
│ Visitor Inbox │ Model        │ Tools      │ Share         │
│               │ Introduction │ Automation │ Embed         │
│               │ Sources      │            │ Customize     │
└───────────────┴──────────────┴────────────┴───────────────┘
```

| Part | What it does | Where to set it |
| --- | --- | --- |
| **Instructions** | The role, the rules, and the response style. You type it in the **Prompt** field | **Knowledge** tab |
| **Model** | **Tone**, **Language**, and **AI Model** | **Knowledge** tab |
| **Introduction** | The first message, the input placeholder, and the conversation starters | **Knowledge** tab |
| **Knowledge sources** | Projects, files, links, videos, and pasted text the agent answers from | **Knowledge** tab |
| **Commands** | `/slash` shortcuts that run a saved prompt | **Actions** → **Commands** |
| **Tools** | What the agent can do: search, project actions, apps, automations | **Actions** → **Tools** |
| **Automation** | Automations that run the agent on a schedule, a form, or a chat | **Actions** → **Automation** |
| **Publish** | The public link, the embed code, and the public look | **Publish** tab |

The **Edit agent** dialog has the tabs **General**, **Knowledge**, **Tools**, **Commands**, and **Share & Embed**. It saves with **Update**. Use the **Publish** tab on the agent page for the full set of publish controls.

```mermaid
graph LR
  Agent[Custom<br/>AI agent]
  Agent --> Persona[Instructions<br/>and tone]
  Agent --> Knowledge[Knowledge<br/>projects · files<br/>links · videos]
  Agent --> Tools[Tools<br/>search · actions<br/>apps · automations]
  Agent --> Model[Model<br/>frontier AI models]
  Agent --> Commands[Slash commands<br/>saved prompts]
  Agent --> Publish[Publish<br/>link · embed · look]
  style Agent fill:#2a1225,color:#ff8fa3,stroke:#ff2d60,stroke-width:2px
  style Persona fill:#1e1e2e,color:#cdd6f4,stroke:#475569
  style Knowledge fill:#0a1420,color:#7dd3fc,stroke:#38bdf8,stroke-width:1.5px
  style Tools fill:#0d1a0e,color:#86efac,stroke:#22c55e,stroke-width:1.5px
  style Model fill:#1a0d24,color:#ce93d8,stroke:#6a1b9a,stroke-width:1.5px
  style Commands fill:#11111b,color:#cdd6f4,stroke:#00d4aa
  style Publish fill:#1a140a,color:#ffb74d,stroke:#e65100,stroke-width:1.5px
```

## Good Jobs for an Agent

Build an agent when a task repeats, takes a lot of focus, or follows a pattern you explain again and again.

| If you often... | Build an agent for... |
| --- | --- |
| Answer the same questions from your docs | Support and knowledge answers |
| Run the same multi-step task | Task routing and follow-up |
| Review the same kind of input | Triage, scoring, and quality checks |
| Prepare or summarize the same meetings | Meeting notes and next steps |
| Draft the same kinds of content | Writing and editing help |

If a job happens one time, ask [Taskade EVE](https://www.taskade.com/learn/agents/eve-assistant). If it repeats, build an agent. For the full journey, see the [AI Agent Playbook](https://www.taskade.com/learn/agents/agent-playbook).

## Build an Agent

Every agent follows the same path: **create it, instruct it, train it, equip it, ship it**.

- **What you need**: A Taskade account. Free includes one custom agent.
- **Time**: About 10 minutes.

```mermaid
flowchart TD
    Start([Open AI Agents]):::ws
    How{How do you<br/>want to start?}:::ws
    Gen[Generate<br/>describe it]:::intel
    Tmpl[Templates<br/>pick one]:::intel
    Blank[Create<br/>start blank]:::intel
    Name[1 · Write the instructions]:::tools
    Train[2 · Add knowledge]:::mem
    Tool[3 · Turn on tools and commands]:::exec
    Ship[4 · Test, then publish]:::live
    Start --> How
    How --> Gen --> Name
    How --> Tmpl --> Name
    How --> Blank --> Name
    Name --> Train --> Tool --> Ship
    classDef ws fill:#1e1e2e,color:#cdd6f4,stroke:#475569,stroke-width:1.5px
    classDef mem fill:#0d1b2a,color:#7dd3fc,stroke:#38bdf8,stroke-width:1.5px
    classDef intel fill:#2a1225,color:#ff8fa3,stroke:#ff2d60,stroke-width:2px
    classDef tools fill:#1a140a,color:#ffb74d,stroke:#e65100,stroke-width:1.5px
    classDef exec fill:#0d1a0e,color:#86efac,stroke:#22c55e,stroke-width:1.5px
    classDef live fill:#1a0d24,color:#ce93d8,stroke:#6a1b9a,stroke-width:2px
```

### Step 1: Open the Agents tab

1. In your workspace sidebar, open **AI Agents**.
2. Pick how to start:
   - **Generate**: describe the agent in plain English. See the [AI Agent Generator](https://www.taskade.com/learn/agents/agent-generator).
   - **Templates**: pick a ready-made agent, such as a researcher or a marketer.
   - **Create**: start with a blank agent.

On a narrow window, the three choices sit in the **New agent** menu as **Generate with AI**, **Templates**, and **Blank agent**. You can also ask [Taskade EVE](https://www.taskade.com/learn/agents/eve-assistant) to create the agent for you.

### Step 2: Name the persona

Open the agent's **Knowledge** tab. Type the role into the **Prompt** field under **Instructions**. Write it as a brief for a new teammate.

```text
You are the support agent for a small bakery. Answer questions about
orders, opening hours, and allergens from the attached knowledge.
Keep answers under 80 words. If the answer is not in the knowledge,
say so and offer to take a message. Do not quote prices that are not
in the knowledge.
```

*Why this works:* The last line sets a boundary, so the agent never invents a price.

Then set **Tone**, **Language**, and the **Introduction** that greets each new chat.

### Step 3: Train on your knowledge

On the same **Knowledge** tab, open **Sources** and add what the agent must answer from:

- **Taskade Workspace**: click **Add Project** for a live project, which syncs when it changes. Click **Add Media** for files already in your workspace.
- **Local Upload**: click **Upload from Computer** for PDF, DOCX, TXT, MD, PPTX, XLSX, CSV, or EPUB files.
- **Cloud Import**: files from Google Drive, Dropbox, Box, or OneDrive.
- **Custom Text**: click **Paste Text** or **Write Markdown** for FAQs, guides, or any text.
- **Web Sources**: a website, a YouTube video, an RSS feed, a sitemap, or a blog post.

Some sources need a paid plan. The editor marks them with an upgrade badge. See [Agent Knowledge & Memory](https://www.taskade.com/learn/agents/knowledge).

### Step 4: Turn on tools and commands

1. Open the **Actions** tab.
2. On **Tools**, turn on what the job needs. Start with web search and one app, such as Slack or Gmail.
3. On **Commands**, click **Add command** for each job you repeat.

### Step 5: Test and publish

1. Open the **Messages** tab and send three real examples from the job.
2. If all three answers are correct, open the **Publish** tab.
3. Turn on the **Publish Agent** switch.
4. On the **Share** sub-tab, click **Copy link** next to **Agent Share Link**.

You are done when the link opens your agent in a private browser window.

![Building a custom AI agent's automations and tools inside Taskade](https://www.taskade.com/static_images/newsletter-gifs/2026-05-03-agent-workflows-tools.gif)

### Test Each Step

| Step | Done when | Where to fix it |
| --- | --- | --- |
| **1. Persona** | The agent introduces itself in the right voice | **Knowledge** → **Instructions** |
| **2. Knowledge** | It answers from *your* data, not general facts | **Knowledge** → sources |
| **3. Tools** | It can act, for example create a task or send a message | **Actions** → **Tools** |
| **4. Commands** | Typing `/` shows your command, and the command runs | **Actions** → **Commands** |
| **5. Ship** | The public link opens in a private window | **Publish** → **Share** |

> 💡 **Note:** Need prompt patterns? Read the [Guide to Writing Agent Prompts](https://www.taskade.com/learn/agents/prompts-guide).

## Choosing the Right Model

Taskade agents run on **frontier models from top AI labs**. Use the latest frontier models from top AI labs, from OpenAI GPT to open-weight models such as DeepSeek and Qwen. Claude is available in custom agents on Pro and up with your own API key (BYOK).

1. Open the agent's **Knowledge** tab.
2. Under **Model**, open the **AI Model** menu.
3. Hover an option to see its credit cost.
4. Click the option that fits the job.

| Option | Good for | Plan |
| --- | --- | --- |
| **TSK-Auto** *(recommended)* | Most agents. Taskade picks a model for each task | Every plan |
| **TSK-Instant** | Quick answers and high-volume chat | Every plan |
| **TSK-Standard** | Everyday work and drafting | Paid plans |
| **TSK-Thinking** | Bigger jobs that need more care. Uses more credits than TSK-Standard | Paid plans |
| **TSK-Reasoning** | Complex, multi-step problems. Uses more credits | Business and up |
| **All Models** | Pin one specific model. Each row shows its credit cost and any plan badge | Shown for each model |

On a Free workspace, TSK-Auto and TSK-Instant are selectable. The other options show a plan badge.

TSK-Thinking returned in October 2026 with a new model. An agent that saved the older TSK-Thinking option shows **TSK-Auto** and runs on TSK-Auto until you pick TSK-Thinking again.

![Picking the AI model for a custom agent from the model dropdown](https://www.taskade.com/static_images/newsletter-gifs/2026-03-19-pick-your-model-per-agent.gif)

> 💡 **Note:** Deeper options use more credits for each reply. See [AI Usage & Credits](https://www.taskade.com/learn/agents/ai-usage).

## Built-in Tools

Tools let an agent act, not only answer. Turn each one on in **Actions** → **Tools**.

| Category | What the agent can do |
| --- | --- |
| **Web** | Search the web and read a web page |
| **Your workspace** | Find information, create projects, add and update tasks |
| **Connected apps** | Send email, post to Slack, update a CRM, and more from 100+ integrations |
| **Automations** | Run an automation that you allow, with **Manual Approval** or **Automatic Approval** |
| **Custom tools** | Wrap your own automation as a tool the agent can call |

Triggers pull events in, actions push data out.

![The integrations grid: 100+ bidirectional connections an agent can use](https://www.taskade.com/static_images/newsletter-gifs/2026-05-13-integrations-grid.gif)

> 💡 **Note:** See [Tools for AI Agents](https://www.taskade.com/learn/agents/agent-tools) for the setup steps.

## Model Context Protocol (MCP)

**Model Context Protocol (MCP)** is an open standard that connects AI clients to tools and data. Taskade runs a **hosted MCP server** on every paid plan.

- **One address.** Connect an MCP client at `https://www.taskade.com/mcp` and sign in with your Taskade account.
- **Your access, your rules.** The client sees only what your account can see.
- **What it can do.** List your spaces, inspect a workspace, list tasks, and write files.

The other direction works from automations. The [MCP Client connector](https://www.taskade.com/learn/connect/mcp-client-integration) lets an [automation](https://www.taskade.com/learn/automation/automations-execution) call a tool on a remote MCP server, on every plan. An agent cannot reach a remote MCP server by itself. Let the agent run the automation, then read the result.

> 💡 **Note:** Full walkthrough: [MCP Connectors](https://www.taskade.com/learn/genesis/mcp-connectors). For everything else an agent can reach, see the [100+ integration catalog](https://www.taskade.com/integrations).

## Knowledge & Persistent Memory

Knowledge is what the agent reads, and it is the agent's persistent memory. Chat history is the record of one conversation.

- **Knowledge** is the set of sources on the **Knowledge** tab. The agent reads it in every chat. A connected project syncs when the project changes.
- **Persistent memory** is that knowledge. It stays with the agent in every chat, and you can refresh or update it at any time.
- **Chat history** stays with each chat. Reopen any chat from **Messages** → **My Chats** to continue it.
- **Lasting facts** belong in knowledge. Add a fact to a connected project or to **Paste Text**, and every chat can use it.

> 💡 **Note:** Deep dive: [Agent Knowledge & Memory](https://www.taskade.com/learn/agents/knowledge). To keep knowledge current on a schedule, see [Keep Your Agent's Knowledge Up to Date](https://www.taskade.com/learn/agents/knowledge-updates).

## Slash Commands

Slash commands turn your best prompts into one-keystroke shortcuts. Type `/` in an agent chat or in a project to see them.

1. Open the agent's **Actions** tab, then **Commands**.
2. Click **Add command**, or click **Browse presets** to start from a preset.
3. Set the **Name** that users type after `/`.
4. Write the **Prompt** that the command runs.
5. Pick a mode: **Default** runs the prompt one time. **Plan and execute** sets a goal and works toward it in steps.
6. Save the command.

You can also run a command on many tasks at one time with [bulk commands](https://www.taskade.com/learn/agents/bulk-commands). Call an agent by name with an `@` mention. The GIF below shows [Taskade EVE](https://www.taskade.com/learn/agents/eve-assistant) with commands and mentions.

![Using slash commands and @mentions to call agents anywhere in Taskade](https://www.taskade.com/static_images/newsletter-gifs/2026-05-13-eve-commands-mentions.gif)

## Multi-Agent Collaboration

One agent does one job well. An **AI Team** puts several agents in one chat when the work needs different specialists. AI Teams need Pro or a higher plan.

![A team of agents running an autonomous research-to-review loop](https://www.taskade.com/static_images/newsletter-gifs/2026-05-05-autonomous-agent-loop.gif)

| Mode | Who replies |
| --- | --- |
| **Auto** *(default)* | The single best agent for the message |
| **Everyone** | Every agent on the team, one after another |
| **Manual** | Only the agents you select |
| **Orchestrate** | A lead plans the steps and gives each step to an agent |

```mermaid
sequenceDiagram
  participant User
  participant Lead as Orchestrate lead
  participant Researcher as Research Agent
  participant Writer as Writer Agent
  User->>Lead: Turn this topic into a blog draft
  Lead->>Researcher: Step 1, find sources
  Researcher-->>Lead: Findings and links
  Lead->>Writer: Step 2, draft from the findings
  Writer-->>Lead: Draft
  Lead-->>User: Reviewed draft
```

> 💡 **Note:** See [AI Teams](https://www.taskade.com/learn/agents/ai-teams) and [Multi-Agents](https://www.taskade.com/learn/agents/multi-agents).

## Embedding Agents Publicly

Publish an agent as a public chat page. Visitors need only the link, not a Taskade account.

```text
┌───────────────────────────────────────────────────────┐
│ Publish Agent                         [ On  ● ]       │
│ Share   Embed   Customize   Tool Permissions          │
├───────────────────────────────────────────────────────┤
│ Agent Share Link   taskade.com/a/support-bot-01JK…    │
│ [ Copy link ]   View agent                            │
│ Require password                      [ Off ○ ]       │
│ Link preview   Page title · Short description · Image │
└───────────────────────────────────────────────────────┘
```

1. Open the agent and click the **Publish** tab.
2. Turn on the **Publish Agent** switch.
3. On **Customize**, set the theme, color, header, and background.
4. On **Share**, fill in the **Link preview**: page title, short description, and preview image.
5. Click **Copy link**, or open **Embed** and copy the code for your website.

**Tool Permissions** appears when the agent has tools. It sets which tools visitors can use. A public chat searches the web or reads a web page only when the agent has that tool turned on and the **Media** row reads **Visitors can use this**. Visitors do not see tool input, tool output, or the reasoning of the agent.

| Control | Plan |
| --- | --- |
| Public link, embed, theme, color, header, chat timeout | Every plan |
| **Require password** | Pro and up |
| **Hide Branding**, **Background**, preview image | Business and up |
| Custom domain for the link | Pro and up |

> 💡 **Note:** Full guides: [Publish Agents Publicly](https://www.taskade.com/learn/agents/public-agents), [Share & Embed AI Agents](https://www.taskade.com/learn/agents/sharing), and [Public Agent Link and Visitor Inbox](https://www.taskade.com/learn/agents/agent-inbox).

## Agent + Automation Pattern

Agents and automations work in two directions:

- **Automation → agent.** An automation step, **Ask an agent** or **Run an agent command**, sends a prompt to your agent. Any trigger can start it: a form, a schedule, or a webhook.
- **Agent → automation.** The agent uses an automation as a tool. It runs the automation in a chat when the request needs that action.
- **Agent → daily job.** Ask the agent in a chat for a daily job, for example "Send me a summary of open tasks every day at 9". The agent makes an automation that asks it your prompt each day at that hour, in your time zone, and emails the reply to you. A job runs on the hour, within about 10 minutes of it. Ask the agent to list your jobs or to remove one.

To give an automation to an agent as a tool:

1. Build the automation. When you generate one with AI, pick the **Agent Tool** mode.
2. Open the agent's **Actions** tab, then **Tools**, and add the automation.
3. Pick **Manual Approval** (the agent asks first) or **Automatic Approval** (the agent runs it).

> 💡 **Note:** See [Automations](https://www.taskade.com/learn/automation/automations-execution) and [Agent Automation](https://www.taskade.com/learn/agents/agent-automation).

## From Agent to Living Software

A custom agent is the brain. **Taskade Genesis** is the app it lives in. Describe an app, and Taskade Genesis builds it with your agent inside. A clinic can put its agent in a client portal, give each client [their own secure login](https://www.taskade.com/learn/genesis/app-users), and use [a branded domain](https://www.taskade.com/learn/genesis/custom-domains). Start with [your first Taskade Genesis app](https://www.taskade.com/learn/genesis/first-app).

| Platform layer | What you get |
| --- | --- |
| **AI Apps** | Describe an app in plain English. Taskade Genesis builds a running app that you can [publish](https://www.taskade.com/learn/agents/sharing) and let others clone |
| **AI Agents** | Custom agents with tools, persistent memory, AI Teams, public sharing, and frontier models, plus [Taskade EVE](https://www.taskade.com/learn/agents/eve-assistant) as the meta-agent |
| **Automation** | Automations with branching, looping, and filtering, plus [100+ bidirectional integrations](https://www.taskade.com/integrations) |
| **Multiple Project Views** | List, Board, Table, and Mind Map, plus Docs, Gantt Chart, Calendar, Actionsheet, and Org Chart under **More views**. Gantt Chart, Actionsheet, and Org Chart need a paid plan |
| **Workspace DNA** | Memory (▲) feeds Intelligence (■), which starts Execution (●), which writes new Memory |
| **Community + App Kits** | Browse live apps in the [Taskade App Factory](https://www.taskade.com/apps), or clone an App Kit as many times as you need |

[![A live Taskade Genesis growth dashboard app powered by custom agents](https://www.taskade.com/static_images/community-apps/h42is85vu180almu-growth-dashboard.webp)](https://www.taskade.com/app/growth-dashboard-h42is85vu180almu)

> 🚀 **Ready to build?** [Start free at taskade.com/create →](https://www.taskade.com/create). Describe your first app and the agent comes with it.

## Pricing & AI Credits

Custom agents are on every Taskade plan, Free included. AI usage is metered in **credits**, not seats.

| Plan | What it adds for agents |
| --- | --- |
| **Free** | One custom agent, and TSK-Auto and TSK-Instant. No starting AI credits: you earn free AI credits as you go |
| **Pro** ★ | No agent limit, AI Teams, more models, Claude with your own Anthropic API key (BYOK), a monthly credit refill, custom domains for public agents, and up to 10 users |
| **Business** | TSK-Reasoning, agents on your own key from more AI hosts, such as xAI, Groq, DeepSeek, or Azure OpenAI (BYOK), Hide Branding, custom backgrounds, and link preview images |
| **Max** | More monthly credits and more capacity |
| **Enterprise** | The highest capacity and org-wide controls |

Deeper models cost more credits for each reply. See the [pricing page](https://www.taskade.com/pricing) and [AI Usage & Credits](https://www.taskade.com/learn/agents/ai-usage).

## Use Agents on Mobile

The Taskade app for iOS and Android shows the same **AI Agents** and **AI Teams** screens as the web. Chat with an agent, create one, or edit its knowledge from your phone. See [Use Custom AI Agents on Mobile](https://www.taskade.com/learn/agents/agents-on-mobile).

## Agent Skills

Agents support **Skills**: saved playbooks that you call with one slash. A Skill loads only when the task needs it, so the agent's prompt stays short.

- Type `/`, pick the Skill, and the agent runs the playbook.
- Pair Skills with the [Bash Sandbox](https://www.taskade.com/learn/agents/bash-sandbox) for scripted work.

See [Agent Skills](https://www.taskade.com/learn/agents/agent-skills) for the setup.

## Frequently Asked Questions

**What is a custom AI agent?**

A custom AI agent is a reusable AI teammate that you build for one job. It combines instructions, knowledge from your projects and files that serves as its persistent memory, tools, and a frontier AI model. Unlike a chatbot, it can act: it creates tasks, runs automations, and works in connected apps.

**How do I build a custom AI agent?**

Open AI Agents in your workspace and click Generate, Templates, or Create. Write the instructions, add knowledge, and turn on the tools the job needs. Test the agent in Messages, then publish it from the Publish tab. No code is necessary. See [Build an Agent](#build-an-agent) and the [AI Agent Generator](https://www.taskade.com/learn/agents/agent-generator).

**What is the difference between an AI agent and a chatbot?**

A chatbot answers questions from general training data. A Taskade agent answers from your own projects and files, which serve as its persistent memory. It can also act with tools, slash commands, and automations. It is the Intelligence layer of [Workspace DNA](https://www.taskade.com/learn/genesis/workspace-dna).

**Which plans include custom AI agents?**

Every plan can build agents. Free includes one custom agent. You [earn free AI credits](https://www.taskade.com/learn/account/referrals) as you go, and you can upgrade any time. Paid plans raise the agent limit, and Pro and up have no agent limit. AI usage is metered in credits, not seats. See [AI Usage & Credits](https://www.taskade.com/learn/agents/ai-usage).

**How do AI credits work for agents?**

Each reply, tool call, and command uses AI credits. The cost depends on the model that answers. TSK-Auto is the default and picks a model for each request. On Free, you [earn free AI credits](https://www.taskade.com/learn/account/referrals) as you go, and you can upgrade any time. Paid plans add a monthly credit refill.

**What tools and integrations can an agent use?**

An agent can search the web, read a web page, work in your projects, and run your automations. It can also act in connected apps from the [100+ integration catalog](https://www.taskade.com/integrations). You turn each tool on in the agent's Tools tab.

**Do custom AI agents remember previous conversations?**

Each chat keeps its own history, and you can reopen any chat from the Messages tab. Across chats, the agent keeps persistent memory in its knowledge: the files, links, and projects you attach. That memory stays with the agent, and you can refresh or update it at any time. To give the agent a lasting fact, add it to a connected project.

**Which AI models power Taskade agents?**

Taskade provides frontier AI models from top AI labs, including OpenAI GPT and open-weight models such as DeepSeek and Qwen. Users on paid plans can select their preferred model for AI agents and app generation. Claude runs on your own API key (BYOK) in custom agents on Pro and up, and in automations. See [Choosing the Right Model](#choosing-the-right-model).

**Can I build an AI agent without coding?**

Yes. You describe the job in plain English, add knowledge and tools with a few clicks, and save. The [agent generator](https://www.taskade.com/learn/agents/agent-generator) and [Taskade EVE](https://www.taskade.com/learn/agents/eve-assistant) can build a complete agent from one sentence. No frameworks, servers, or API keys are necessary.

**Can I share an agent publicly and keep my workspace private?**

Yes. Turn on the Publish Agent switch on the agent's Publish tab and share the Agent Share Link. Visitors chat with the agent without access to your workspace. The agent uses the knowledge you attached and only the tools you allow for visitors. See [Publish Agents Publicly](https://www.taskade.com/learn/agents/public-agents).

**How is a custom agent different from Taskade EVE?**

[Taskade EVE](https://www.taskade.com/learn/agents/eve-assistant) is the built-in meta-agent that builds apps, agents, and automations and operates Taskade for you. A custom agent is a specialist that you build for one job, such as support, research, or sales.

**How do AI agents fit into Taskade Genesis apps?**

A Taskade Genesis app can include custom agents as its intelligence layer. The agent answers visitor questions, reads app data, and triggers automations. This is how a described app becomes software your customers can talk to. See [Build your first Taskade Genesis app](https://www.taskade.com/learn/genesis/first-app).

**Can I use custom AI agents on my phone?**

Yes. The Taskade app for iOS and Android opens your workspace with the same AI Agents and AI Teams screens as the web. You can chat with agents, create them, and edit them from your phone. See [Use Custom AI Agents on Mobile](https://www.taskade.com/learn/agents/agents-on-mobile).

## Related guides

1. [AI Agent Generator](https://www.taskade.com/learn/agents/agent-generator). Create an agent from one prompt.
2. [Agent Knowledge & Memory](https://www.taskade.com/learn/agents/knowledge). Train the agent on your data.
3. [Tools for AI Agents](https://www.taskade.com/learn/agents/agent-tools). Give the agent tools.
4. [AI Agent Chat](https://www.taskade.com/learn/agents/agent-chat). Chat, threads, and commands.
5. [AI Teams](https://www.taskade.com/learn/agents/ai-teams) and [Multi-Agents](https://www.taskade.com/learn/agents/multi-agents). Run specialists together.
6. [Agent Automation](https://www.taskade.com/learn/agents/agent-automation). Trigger agents from automations.
7. [Share & Embed Agents](https://www.taskade.com/learn/agents/sharing). Publish agents to the web.

More guides:

- [Build an AI Agent: The Complete Playbook](https://www.taskade.com/learn/agents/agent-playbook). The full path from idea to working teammate.
- [Guide to Writing Agent Prompts](https://www.taskade.com/learn/agents/prompts-guide). Prompt patterns that work.
- [MCP Connectors](https://www.taskade.com/learn/genesis/mcp-connectors). Model Context Protocol in Taskade.
- [Taskade EVE Assistant](https://www.taskade.com/learn/agents/eve-assistant). The built-in meta-agent.
- [AI Usage & Credits](https://www.taskade.com/learn/agents/ai-usage). How credits and models price out.
- [Automations: The Execution Pillar](https://www.taskade.com/learn/automation/automations-execution). How agents start real work.
- [Workspace DNA](https://www.taskade.com/learn/genesis/workspace-dna). How Memory, Intelligence, and Execution connect.
- [Use Custom AI Agents on Mobile](https://www.taskade.com/learn/agents/agents-on-mobile). Agents on iOS and Android.

### Go deeper

- [What Are AI Agents?](https://www.taskade.com/blog/what-are-ai-agents). The plain-English explainer.
- [AI Agents product page](https://www.taskade.com/agents). The full Taskade AI Agents overview.
- [Build with Taskade Genesis](https://www.taskade.com/create). Describe an app and watch it come to life.
- [Automate your work](https://www.taskade.com/automate). Branching automations across 100+ apps.
- [Taskade Genesis knowledge base](https://www.taskade.com/wiki/genesis). Concepts behind living, cloneable software.
- [Watch: Create an AI Agent](https://www.taskade.com/learn/videos/create-agent). The whole setup as a short video.
- [Keep Your Agent's Knowledge Up to Date](https://www.taskade.com/learn/agents/knowledge-updates). Refresh its knowledge on a schedule.

Build the first one today. Memory ▲, Intelligence ■, Execution ●. Your custom agent is the brain that ties them together. [Start free at taskade.com/create →](https://www.taskade.com/create)
