Publish Agents Publicly

Overview

Publish any Taskade AI agent to a public URL so customers, prospects, or community members can chat with it directly. You decide which tools the agent can call when used by anonymous visitors and which projects feed its context. Everything else stays private inside your workspace.

TL;DR: Publish a custom AI agent at taskade.com/a/{agent-name}-{id}. Choose its appearance, password, starter prompts, and the tools visitors can use. Visitors can chat without entering your workspace. Their conversations appear in the Visitor Inbox. You can also embed the agent on a website.

Publish an agent

Open the agent in the Agents tab, then turn on the Publish Agent switch.

1. Open AI Agents in your workspace sidebar.
2. Click the agent you want to publish.
3. Click the Publish tab.
4. Turn on the Publish Agent switch.
5. 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.

The agent is reachable immediately. The link carries the agent's name followed by its id, so an agent called Support Bot gets something like taskade.com/a/support-bot-01JK82XFM2. Rename the agent and the readable part changes, but the old link keeps working because the id at the end is what Taskade looks up. Send the link, drop it into a Notion page, or post it in your community.

The publish panel keeps every control in one place, split across Share, Embed, Customize, and, when the agent has tools, Tool Permissions. A live preview on the right shows the agent exactly as visitors will see it while you set things up.

┌───────────────────────────────────────────────────────┐
│ 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 │
└───────────────────────────────────────────────────────┘

Publish controls at a glance

Use this table to decide which controls to turn on before you share the link.

Customize the public surface once

The Publish Agent panel splits into Share, Embed, and Customize, plus Tool Permissions when the agent has tools. Set the look on Customize and every place the chat appears picks it up. You are describing the agent, not decorating one particular page.

• Mode: Chat Only, or Chat & Template so visitors can clone the agent.
• Theme: Light theme, Dark theme, or Auto.
• Color: pick a hex code for the launcher and accents. Taskade works out whether light or dark text reads better on it, so your label stays legible.
• Header: keep Default, which uses the agent's name, or switch to Custom and write your own title.
• Agent avatar: the picture shown beside the agent's replies.
• Chat button icon: an emoji or an uploaded square image on the floating chat button. Leave it unset and the agent's avatar is used.
• Message Style: Default for a transcript-style thread, or Bubble for rounded chat bubbles.
• Show Suggestions: turn the starter-prompt chips on or off. The prompts themselves come from the agent's conversation starters.
• Notice: one short dismissable line above the chat, for a privacy notice or opening hours. Up to 200 characters, and a visitor's dismissal lasts for that browser session.
• Footer: one short plain-text line under the composer, for a disclaimer or a legal note. Up to 200 characters.
• Background: an image behind the chat.
• Hide Branding: removes the Taskade mark from the public chat.
• Chat Timeout: ends a chat after a time with no activity. The When an agent chat ends automation trigger needs it.

A live preview sits beside the panel, and you can flip it between the full page and the Chat Widget form factor. Changes save instantly, and the public surface picks them up on the visitor's next load.

Know where those settings show up

Three surfaces read the same appearance settings, so there is nothing to configure twice.

The website widget is the public page in a floating panel, which is why the two always match. A Taskade Genesis app's chat block reads the same profile. The assistant inside your app shows your agent's name, starter prompts, placeholder text, and accent color, not a generic "Assistant".

The widget snippet carries the agent's saved theme and accent color. Per-site settings cover the launcher corner, size, label, welcome bubble, and auto-open delay. The same agent can look different on two websites, and its public page does not change.

Check which appearance settings need a plan

Most of the appearance controls work on every plan. These do not.

Hide Branding and Background carry a Business badge on Customize. On a Free workspace, Require password carries a Pro badge on Share, and any paid plan can turn it on. Taskade also checks the plan when you save a preview image. Turning a setting back off, or removing an image you already uploaded, is never blocked. A workspace that changes plan can always undo a setting. Current plan details are on the pricing page.

Scope public agent knowledge

Public agents only see the knowledge sources you have explicitly attached to the agent. The Knowledge panel is the source of truth: anything connected there is fair game for public answers. Anything outside the agent stays private. Connect a public FAQ project, leave your internal customer database (CRM) out, and the agent answers from the right material every time.

For sensitive content, build a separate public-facing agent with its own knowledge connections instead of toggling sources on and off in real time. That keeps the security model simple. See Agent Knowledge & Memory for the full setup.

Switch Between Search and Ask AI

The public agent page offers two ways to use the same approved knowledge.

• Search finds matching passages in the agent's public knowledge.
• Ask AI opens a chat with follow-up questions and the tools that you allowed for visitors.

Visitors can switch between the two without leaving the public agent page.

Public agents in Workspace DNA

A public agent is the public-facing tip of your Workspace DNA. It draws Memory from the Projects you connect, runs Intelligence with the agent's prompt and tools, and triggers Execution through whichever automations it can call.

Anything you do not connect to the agent stays internal. That is the security model in one picture.

Visitor Inbox

Every public conversation lands in the agent's Visitor Inbox. Read it like a support log.

1. Open the agent.
2. Click the Messages tab.
3. Click Visitor Inbox in the left sidebar.

You see every public thread, with each visitor message and the agent's reply. The inbox is read only, so you cannot reply inside a visitor's chat. To follow up, build an automation with the When an agent chat ends trigger that sends each chat to Slack, email, or a CRM. Read Public Agent Link and Visitor Inbox for the full setup.

Rate limits and abuse controls

Public agents come with safeguards by default.

• Request limit. Each visitor can send only a limited number of requests in a short time, so one visitor cannot drain your AI credits.
• Workspace credits. Visitor chats use your workspace's AI credits, within your plan's limits.
• One-click pause. Turn off the Publish Agent switch and the public page stops working at once. Turn it back on at any time.

Visitor chats stay private to your workspace. On every plan, you can export one from the Visitor Inbox when you need a copy.

Lock or take down an agent

Turn on Require password on the Share sub-tab when you want a published agent reachable by link but limited to the right people. It needs a paid plan. Visitors enter the password before they can chat. A client-only or internal-only agent stays private and still lives at a clean URL.

Turn off the Publish Agent switch on the agent's Publish tab and the public page stops working at once. Knowledge connections, tool configurations, and conversation history all stay intact, so you can flip the agent back on later without losing setup.

This is useful for:

• Limited-time campaigns. Publish for a launch week, then take it down.
• Iterating in private. Pause, retrain, re-enable.
• Compliance reviews. Take an agent offline, audit, and restore.

Frequently Asked Questions

Related guides

• Embed AI Agents as Website Widgets: Drop a public agent onto your site as a chat launcher.
• Public Agent Link and Visitor Inbox: Read every public conversation, and automate follow-ups.
• Tools for AI Agents: Pick which capabilities a public agent can call.
• Custom AI Agents: Build the agent before you publish it.
• Agent Knowledge & Memory: Train an agent on the docs you want it to share.