Your workflows can now watch video. The AI Analyze Video action is available under AI Actions. Give it a video URL and a prompt. Google Gemini watches the video, listens to the audio, and returns a text answer for the actions that follow.

This is a premium action. Each execution has an additional charge.

What's New

• Two Gemini models: Select Gemini 3.8 Flash (default) or Gemini 3.5 Flash Lite.
• YouTube support: Paste a public YouTube link. <a href="http://youtube.com/watch" rel="ugc nofollow noopener noreferrer" target="blank”>youtube.com/watch, <a href="http://youtu.be" rel="ugc nofollow noopener noreferrer" target="blank”>youtu.be, and Shorts links all work.
• Direct video files: Use any public link to an MP4, MOV, WebM, MPEG, FLV, WMV, or 3GP file.
• Dynamic video URLs: Insert the URL from a previous step or a custom value. The video can come from a form, a webhook, or the AI Video Generation action.

• Picture and sound: The model understands what is shown and what is said.
• Flexible prompts: Ask for a summary, a transcript, a list with timestamps, or a yes or no check. The prompt supports custom values.

• Built in Test: Test the action right in the builder with data from your trigger, then read the Response before you publish. Here it summarizes the short film Big Buck Bunny.

Pricing

Video analysis is billed per execution based on the tokens consumed.

Your actual cost per analysis depends on how you configure the action. The main factors are:

• Model: The model you select.
• Video length: A longer video costs more than a short clip.
• Response length: A long, detailed answer costs more than a short one.

How to Use

1. Go to Automation > Workflows.
2. Open a workflow, then add the AI analyze video action from AI Actions.
3. Select the model. The default is Gemini 3.8 Flash.
4. Add the video URL. Type it in, or insert a value from a previous step or a custom value.
5. Write the analysis prompt. Say what the AI should look for and how to answer.
6. Open the Test tab and click Test Action to see the Response. This step is optional.
7. Save the action. Use the Response value in the actions that follow.

Important: The video URL must be public. Page links from Vimeo, TikTok, and similar sites are blocked by those sites, so use a YouTube link or a direct video file link instead.

Why This Matters

A video used to be a dead end in a workflow. You could send a link, but nothing could read it. Now a workflow can watch the video and act on what it sees. No manual review, no note taking, no rewatching.

Save the summary to a custom field, send it in an email or SMS, pass it to a webhook, or feed it to another AI action. Pair it with AI Video Generation to check a generated video before it reaches a customer.

Good to Know

• Each action analyzes one video URL.
• The Response can include Markdown, such as headings and bullets. Ask for plain text in the prompt if you need it.
• A long video takes longer. A 10 minute YouTube video took about 30 seconds in our tests.

AI Builder now tests what it builds. Describe a workflow, let AI Builder build it, then click Test workflow in the same chat. The test runs for real, every step reports back on the canvas, and AI Builder tells you in plain words what worked.

What's New

Test workflow, right in the chat

• Every time AI Builder builds or edits your workflow, its reply ends with a Test workflow button.
• Click it and the test opens inside the chat. Choose Enroll a contact or Test using events, pick the contact, and check the contact data before you start.

Watch the run live

• Click Start test run. The canvas shows each step as Running, then Success, Action skipped or End.
• The chat lists the run step by step, with a check next to every step that ran.

A summary you can read

• When the run ends, AI Builder writes a short test summary: which steps ran, which were skipped, and whether there were errors or missing data.
• Click any step on the canvas to see its Input and Output from the run.

Run another test

• Changed something? Click Run another test to test again with one click.

How to Use

1. Open HighLevel Labs and turn on The New Test Workflow.
2. Go to Automation > Workflows and open a workflow.
3. Open AI Builder and describe the workflow you want, or the change you want.
4. When AI Builder finishes, click Test workflow in its reply.
5. Choose Enroll a contact and pick a contact, or choose Test using events.
6. Click Start test run.
7. Read the test summary. Click any step on the canvas to see its Input and Output.
8. Save and publish your workflow.

Important: A test runs the real steps. Tags are added, notes are written, and messages are sent. Test with your own contact when you do not want to reach a customer.

Why This Matters

Building with AI is fast. Knowing it works used to be the slow part. You had to leave the chat, find the test, and dig through logs to see what happened.

Now build and test live in one place. Describe it, build it, test it, read the result. No guessing, no digging through Execution Logs, no hoping it works in production.

Good to Know

• Some actions are skipped in a test run. The summary and the canvas tell you which ones.
• Testing is optional. You can save and publish without testing.

Your AI Agent can now search the internet. Turn on Web search in the new Built-in tools section, and the agent looks up the facts it needs in the middle of a run. You can also point it to exact pages: paste their URLs in the Instructions, and the agent reads them when it needs them.

What's New

A Built-in tools section

• Built-in tools sits right below Tools in the AI Agent Action. These are abilities your agent has on its own, on top of the tools you add.
• Hover the (i) on a built-in tool to see what it does. Hover the crown to see what it costs.

Web search

• One toggle: Turn on Web search and the agent can search the internet during any run.
• The agent decides: It searches only when the task needs information it does not have.
• Your own sources: Paste a URL in the Instructions, and the agent refers to that page when the run calls for it.
• Static or live: Give the agent the pages you trust, and let it search the web for everything else.

Coming soon to Built-in tools

AI image generation and AI video generation are already live as separate actions. Both are coming to the AI Agent Action as built-in tools very soon.

Pricing

Web search is a premium tool. It is billed per search, on top of the AI Agent Action.

• OpenAI and Claude models: 1¢ per search.
• Gemini models: 1.4¢ per search.

How to Use

1. Go to Automation > Workflows.
2. Open a workflow, then add or open an AI Agent Action.
3. Scroll down to Built-in tools and expand it.
4. Turn on Web search.
5. To point the agent to specific pages, paste their URLs in the Instructions. This step is optional.
6. Save the action.

Worked Example: Rebate Questions, Answered From the Source

A heating and cooling company follows up on every quote request. Some leads ask about rebates, and rebate programs change often.

The AI Agent Action is set up like this:

1. Instructions: "If the lead asks about rebates, read https://www.energystar.gov/rebate-finder before you reply. For any other facts you need, search the web."
2. Tools: Send email and Send SMS.
3. Built-in tools: Web search on.

A lead asks about heat pump rebates. The agent checks the rebate page you gave it before it replies. Another lead asks a question that page does not cover, so the agent searches the web for the answer. No stale facts, no guesswork, no manual lookups.

Why This Matters

Your agent is no longer limited to what it already knows. Prices, programs, and public details change all the time. Web search lets the agent check them at the moment it needs them.

You stay in control of the sources. Name the pages you trust in the Instructions, and tell the agent when to use them.

You pay only when the agent searches. A run that needs no search costs nothing extra.

Good to Know

• Each search is charged. A run with three searches is billed for three searches.
• Web search finds information. To act on it, the agent still needs the right tools, such as Send email or Send SMS.

Your workflows can now make video. The AI Video Generation action is available under AI Actions. Give it a prompt. Google's Veo 3.1 creates a short video, stores it at a public URL, and returns that URL for the actions that follow.

This is a premium action. Each execution has an additional charge.

What's New

• Two models: Select Veo 3.1 Quality for the most polished output, or Veo 3.1 Fast for quicker generation.
• HD quality: Generate in Standard (720p) or High (1080p).

• Flexible prompts: Type the prompt yourself or insert a custom value. The prompt can come from a contact field, a webhook payload, or an earlier action.
• Enhance Prompt: One click expands a short prompt into a detailed one.
• Templates: Start from Product Mockups, Social Post, Promo Flyer, or Lifestyle. Each template plays a sample video before you use its prompt.

• Reference images: Add up to 3 JPEG or PNG images from your computer, the Media Library, or a URL. The model uses them for subject and style.

• Size and length: Pick Landscape (1920 x 1080) or Portrait (1080 x 1920), and a duration of 4, 6, or 8 seconds.
• Generate Audio: One toggle adds AI generated sound, from ambience to background music.
• Automatic storage: Each video goes to the Media Library and returns its URL for the actions that follow.

Pricing

Video generation is billed per execution, based on the length of the video and the settings you choose.

Note: Treat any cost figures as a planning estimate, not a fixed rate.

Your actual cost per video depends on how you configure the action. The main factors are:

• Model: The model you select.
• Quality: Standard (720p) or High (1080p).
• Duration: 4, 6, or 8 seconds.
• Audio: Generate Audio increases the per second cost.

How to Use

1. Go to Automation > Workflows.
2. Open a workflow, then add the AI Video Generation action from AI Actions.
3. Select the model and the quality. The defaults are Veo 3.1 Quality and Standard (720p).
4. Write the prompt. Type it in, or insert a custom value so the prompt comes from your data at run time.
5. Click Enhance Prompt or start from a template. Both steps are optional.
6. Add reference images. This step is optional.
7. Open Additional Settings for the size, the duration, and Generate Audio. This step is optional.
8. Save the action.

Important: The generated video is stored at a public URL. Anyone with the link can open it without a login. Keep this in mind when a prompt pulls in customer data.

Why This Matters

Until now, a workflow could send a video you uploaded in advance, but never make one. Now a workflow can shoot the clip itself. No camera, no editor, no studio.

Use the video URL in the actions that come after. Send it in an email or SMS, save it to a custom field, or pass it to a webhook. Because the prompt can come from your data, one workflow can produce a different video for every contact who passes through it.

Good to Know

• Videos are 4, 6, or 8 seconds long.
• Reference images require the 8 second duration. Duration switches to 8 seconds automatically when you add one.
• Generate Audio is off by default.

🧭 Overview

The calendar view now gives you more control over how it looks and what you can do with it. A new Calendar view settings panel brings your display preferences together in one place, export lets you take the exact view you're looking at out of the product, and filters and event colors are easier to work with. These are display and workflow improvements only. Availability, booking rules, and what customers see on your booking page don't change.

🚀 What's New?

✅ Calendar view settings, one click away

Open the more options (3 dots menu ⋮) menu next to Manage view in the calendar toolbar and select Calendar view settings to open a single panel for your display preferences. Your choices are saved for the next time you open the calendar.

✅ Preferences you can tune

• View appointments in: Show times in the timezone you choose throughout your calendar screens. It also applies to your appointment-related emails. Note : This setting is just for you and doesn't affect availability, how others book, or the preferences for other team members or customers.
• Default grid interval: Choose how granular (15,30,60 min) the day and week grids are on the calendar view.
• Grey out hours outside working time: Shade non-working hours for each staff member using their schedules for that date.
• Hide empty rows and columns: Keep the view focused on booked resources and hide the ones without any appointments.
• Show buffer time: See buffer time before and after staff appointments wherever a slot is blocked by buffers.

✅ Timezone now lives with your other view settings

The "View in timezone" setting moved out of Meetings Preferences and the Services/Rentals Global Settings. Any timezone you set before carries over automatically.

✅ Staff colors for admins

Admins get a Staff colours tab to recolor how appointments for the staff members look.

✅ Color events by calendar, service, or staff

Choose whether the event tile is filled with the calendar/service color or the assigned staff color. The other color shows on the tile's left strip.

✅ A wider color strip

The left color strip is wider, so you can tell which staff member or calendar an event belongs to at a glance.

✅ Export what you're looking at

From the same more options (⋮) menu, choose Export to PDF or Export to CSV to export the current view with the same filters and date range.

🧩 How to Use It

• On the unified calendar, open the more options (⋮) menu next to Manage view and select Calendar view settings to adjust your preferences.
• Admins can open the Staff colors tab to recolor staff.
• To export, open the same menu and choose Export to PDF or Export to CSV.

🎯 Why This Matters

• Everyone can shape the calendar to the way they scan it, without digging through calendar configuration.
• Accurate shading means empty time never looks bookable when it isn't.
• Exporting the exact view you're looking at makes it easy to share schedules or work with the data elsewhere.
• Staged filters let you preview a selection before the live calendar changes.