Changelog
Follow up on the latest improvements and updates.
RSS
new
Mobile App
Phone System
Transfer calls to Mobile, Web, phone and SIP of a user - no personal phone number required 📞
You can now transfer calls from the mobile app to staff members who don't have a personal phone number.
How to use this?
- Make a regular call from the mobile app (outbound or inbound)
- In the active call, tap the transfer call icon at the top right corner
- Go to the Staff Members tab and choose the staff member you want to transfer the call to. Device types they can receive the transferred call on are shown next to their name

- Tap Call and Hold for a warm transfer, or Transfer and End for a blind transfer
- The staff member receiving the transferred call can see that it's a transferred call, along with who transferred it. On iOS, the incoming call banner shows the contact name followed by "via" and the name of the staff member who transferred it — for example, John Doe via Michael Scott.

On Android, the incoming call screen shows Transferred call from Michael Scott

- They tap Answer
- The warm transfer can be executed as usual



Key points
- Works for both warm and blind transfers
- Works for both outbound and inbound calls
- The mobile app now works as both transfer source and destination
- Re-transferring a call (transferring a call that was already transferred to you) isn't supported yet
- Transfers ring every device the staff member has set under "Forward calls to" at the same time: Web App, Mobile App, Phone, and SIP desk phone
- Staff members with no device configured appear as disabled in the transfer list
new
Conversation AI
Working Hours for Conversation AI Agents
Overview
We're introducing Working Hours for Conversation AI, giving business more control over when their AI agents respond to customers.
You can now set specific working days and hours for each agent, choose which channels should follow those hours, and configure what happens when a customer reaches out after business hours.
This helps business keep their AI aligned with their actual operating hours while still making sure after-hours customers are acknowledged and followed up with.
What's New?
- Set flexible Working Hours for each agent- Choose the days and times when an AI agent should actively respond. You can set different hours for each day and add multiple time slots for breaks or split shifts.
- Choose which channels follow Working Hours- Apply the schedule only to selected channels such as SMS, Email, WhatsApp, Instagram, Facebook, Chat Widget, Live Chat, and TikTok. Channels that are not selected can continue responding 24/7.
- Use Contact or Business Timezone- Run the schedule based on each contact's local timezone or your business timezone.
- Continue ongoing conversations after hours- If a conversation started during working hours, the agent can continue replying after closing time until the conversation becomes inactive.
- Send an Off-Hours Auto-Reply- Automatically acknowledge customers who message outside working hours. You can add your own custom message and personalize it using supported custom values.
- Notify your team about after-hours messages- Send email notifications to admins, users, assigned users, selected team members, or custom email addresses.
- Automatically tag after-hours contacts- Add selected tags to contacts who message outside business hours, making it easier to identify, filter, and follow up with them.
- Follow up when business hours resume- Automatically send a follow-up when the business reopens if the customer has not already received a response from the agent or a team member.
Additional Notes:
- Working Hours is optional. If it is not enabled, the agent continues responding at any time as it does today.
- Working Hours applies only to the channels you select. Other channels continue working normally.
- The Off-Hours Auto-Reply, notifications, and contact tags are triggered once per closed period, so customers will not receive the same acknowledgement for every message they send after hours.
- The business-hours follow-up is skipped if the customer has already received a response from either the AI agent or a team member.
- In Suggestive Mode, suggestions can still be generated after working hours for your team.
- If Followup Hours is also configured for Advanced Follow-Up, the agent's Working Hours takes priority for the channels included in the agent's schedule.
- Agents can still be manually activated outside their Working Hours when needed via conversation panel.
- Working Hours is configured per agent, so different agents can have completely different schedules.




new
Automations
AI Image Generation Action in Workflows
You can now generate an image inside a workflow. The AI Image Generation action is available under AI Actions. Give it a prompt. An AI model creates the image, stores it at a public URL, and returns that URL as text.
This is a premium action. Each execution has an additional charge.

What's New
- Four models: Select GPT Image 2, Gemini 3 Pro Image (Nano Banana Pro), Gemini 3.1 Flash Image (Nano Banana 2), or Gemini 2.5 Flash Image (Nano Banana).
- 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.
- Quality: Set Auto, High, Medium, or Low. The default is Auto.
- Brand control: Apply your Design Kit and Brand Voice.
- Output control: Set the size, the background, and the file format.
- Automatic storage: Each image goes to Media Storage and returns an Image URL variable for the actions that follow.
Pricing
Image generation is billed per execution. The figures below show what a typical image costs. Most generations land in this range.

Note: Treat these figures as a planning estimate, not a fixed rate.
Your actual cost per image depends on how you configure the action. The main factors are:
- Model: The model you select.
- Quality: The level you set.
- Size: The size you generate at.
- Additional context: A Design Kit or Brand Voice passes extra context to the model, which can shift the cost.
How to Use
- Go to Automation > Workflows.
- Open a workflow, then add the AI Image Generation action.
- Select the model and set the quality. The default is Auto.
- Write the prompt. Type it in, or insert a custom value so the prompt comes from your data at run time.
- Click Enhance Prompt or start from a template. Both steps are optional.
- Open Additional Settings for the size, the background, the output format, the Design Kit, and the Brand Voice. This step is optional.
- Save the action.







Important:
The generated image 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
A workflow can now create a visual, not only move one you uploaded in advance. Use the Image URL in the actions that come after. You can attach it to an email or SMS, publish it to a social post, 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 image for every contact, or fill in an image URL for every row in a Google Sheet.
One change beyond the paste: your pricing copy revealed the quality levels, so I pulled Quality into its own bullet under What's New and named them. That mirrors the Detail level bullet in the Analyze Image doc.
new
Automations
AI Analyze Image: New Workflow Action
You can now analyze an image inside a workflow. The AI Analyze Image action is available under AI Actions. Give it an image URL and a prompt. An AI vision model examines the image and returns the answer as text.

This is a premium action. Each execution has an additional charge.
What's New
- Text extraction:Read the text from receipts, invoices, screenshots, and documents.
- Image descriptions:Receive a written description of the contents of an image.
- Flexible prompts:Tell the model what to look for and how to answer. The prompt field accepts custom values.
- Detail level:Set Auto, High, or Low. High is more accurate for small text. Low is faster.
- Two models:Select GPT-5.6 Luna or GPT-5.6 Tera.
How to Use
- Go to Automation > Workflows.
- Open a workflow, then add the AI Analyze Image action.
- Select the model.
- Enter the image URL. Use the output of an earlier step or a custom value.
- Write the analysis prompt.
- Set the detail level. The default is Auto.
- Save the action.





Important:
The image URL must be public. Anyone must be able to open it without a login. Do not use a link to a page that contains the image. Use the direct link to the image file. Files in Media Storage are already public.Why This Matters
A workflow can now read the contents of an image, not only move the image from step to step. Use the output text in the actions that come after. You can save it to a custom field, send it in an email or SMS, pass it to a webhook, or send it to another AI action.
improved
Automations
Improved: Dynamic Value Chips with Improved error segmentation
What's new?
Dynamic value chips have three states now instead of two. A dynamic value chip used to be valid or invalid, so anything the builder couldn't resolve came back red with "value not recognized". The new middle state is a yellow chip, and it covers values that are real on the platform but have no source in the workflow you have open. Giving a clear distinction between values that could render blank and values that won't render at all.
How it works
Every chip lands in one of three states:
- Blue, value available in this workflow. The workflow can fill it, whether that comes from the contact record, a system value like the current date, or an earlier step.
- Yellow, value not available in this workflow. The value is real on the platform, but nothing in this workflow supplies it, for example {{sheet.10.rowNumber}} in a workflow with no Google Sheets step. It renders blank unless another workflow passes it in through Add to Workflow with pass input trigger parameters.
- Red, value doesn't exist on the platform. Nothing on the platform matches it, for example {{applesheet.10.rowNumber}}, so no workflow will render it.
Spacing inside the handlebars stopped mattering too. The platform stores Attribution Url as {{ attribution.first.url }} with the spaces, so typing {{attribution.first.url}} used to come back red. Both forms match now.
Why we built it
Earlier all fields which wouldn't render would show an error state with a red chip. However you might drop {{invoice.url}} into an Add Notes action on a workflow that no invoice trigger starts, or hand a value from one workflow to another through Add to Workflow.
The red chip earlier called those values unrecognized and pointed you at the picker, so a configuration you built on purpose read like a mistake you had made. Splitting the states puts red back on the cases worth acting on. Red now means the value is wrong. Yellow means check whether something else supplies it.
Additional Notes
- Yellow is a warning, not a block. Save and publish the workflow as usual.
- Red still catches typos, for example {{contact.frist_name}}.
- This changes the UI only. Values resolve at execution time the way they did before, so anything that ran before still runs.
Preview


improved
Phone System
📞 More Reliable Missed Call Text Back with Smarter Number Selection
📥 Overview
A missed call can be a missed opportunity, and your follow up text should not fail simply because the number your customer called cannot send SMS.
Previously,
Missed Call Text Back
always tried to send the follow up SMS from the same number your customer called. But some numbers are designed primarily to receive calls or may not currently be eligible to send SMS. In those cases, your text back could fail even when another messaging ready number was available in your account.We’ve improved this experience. HighLevel will now automatically choose an eligible sending number, helping more of your missed call follow ups reach your customers while staying aligned with messaging requirements.
The result is simple:
more missed callers receive your follow up message, while your texts stay aligned with messaging requirements.
📊 What’s New?
✅ Your Missed Call Text Back Has a Better Chance of Reaching the Customer
When a customer calls and you miss them, we’ll still try to
text them back from the number they called first
, as long as that number can send SMS.If it can’t, system will automatically look for the next best option:
- A number you’ve successfully messaged this contact from before
- Your default outbound number
- Another eligible messaging numberavailable in the location
This is especially helpful when calls come through
number pools, call tracking numbers, unverified toll free numbers, or other numbers that aren’t eligible to send SMS
. Instead of attempting the text from a number that can’t send, we’ll use an eligible number when one is available.💬 What Will Your Customers Notice?
Most of the time, nothing changes. The missed caller simply receives your follow up as expected.
In some cases, the
SMS may come from a different number than the one they originally called
. That’s intentional. We’re choosing a number that can actually send the message rather than letting an important follow up fail.🔍 Why It Matters
When someone calls your business and you cannot answer, that first follow up can be important for keeping the conversation going.
With smarter number selection, you can:
- 📩 Reach more missed callersinstead of losing the follow up because one number cannot send SMS
- ⚡ Keep follow ups automaticwithout manually managing which number should be used
- 🛡️ Stay aligned with messaging requirementssuch as A2P and toll free verification
- 🤝 Respond to potential leads soonerand keep conversations moving even when you miss the initial call
In short,
if you have an eligible number available, we’ll automatically use it to give your missed call text a better chance of reaching the customer.
💡 Good to Know
- Answered calls will continue to work as before and will not trigger a text back.
- If Missed Call Text Backis disabled in your Phone System settings, no message will be sent.
- Your contacts’ communication preferences and DND settings will continue to be respected.
- If there is no eligible number available, you’ll see the failed attempt in the conversation along with the reason, giving you clear visibility into what happened.
📌 Overview
The User login workflow trigger now fires for logins from the new Client Portal experience — not just legacy membership logins. We've also added a dedicated Client Portal category in the workflow trigger picker, so all Client Portal triggers live in one place.
✨ What's New
🔑 New Client Portal logins now fire the "User login" trigger Successful logins from the new Client Portal experience now emit the same workflow trigger event as legacy membership logins. Any workflow already using the User login trigger will start running on these logins automatically — no reconfiguration required.
🗂️ New "Client Portal" category in the trigger picker
A dedicated Client Portal category now groups all Client Portal triggers together:User login — moved from Courses
Client portal file uploaded — moved from Membership
💬 Clearer helper text
The User login trigger now spells out that it covers both legacy membership logins and logins from the new Client Portal experience — removing the confusion caused by its old placement under Courses.
🛠️ How to Use
Automate on Client Portal member login
- Open the Workflow Builder.
- Click Add trigger and search for User login.
- Select it under the new Client Portal category (previously found under Courses).
- Save your workflow — it will now fire on both legacy membership logins and logins from the new Client Portal experience.
Already using this trigger?
No action needed. Existing workflows continue to run as-is and will automatically pick up login events from the new Client Portal experience.💡 Why This Matters
Agencies on the new Client Portal experience previously had no way to automate off a member login, because the trigger only covered legacy memberships. Trigger placement was inconsistent too — login sat under Courses while file upload sat under Membership — making it unclear what each trigger actually covered. This update closes the gap and puts both triggers where you'd expect to find them.
new
Phone System
📢 Carrier Fee Pricing Update - Effective October 1, 2026
🗓️
Effective Date
- October 1, 2026 → Verizon and 'Other' Category Carrier Fee Updates
Overview
To keep our pricing aligned with current carrier costs and maintain optimal deliverability across global telecom networks, we are updating carrier fees for messaging traffic sent to U.S. numbers via Verizon and select providers in the 'Other' category.
Verizon Carrier Fee Updates
Key changes for outbound messaging via the Verizon network
:- Outbound SMS (Long Code, Short Code, Toll-Free, Authy & Verify): $0.0045 → $0.0050 per message
- Outbound RCS Rich: $0.0045 → $0.0050 per message
Other Carrier Fee Updates
Key changes for outbound messaging via 'Other' Category Carrier network:
- Outbound SMS (Long Code, Short Code Group B, Toll-Free, Authy & Verify): $0.0040 → $0.0042 per message
- Short Code Group A SMS: $0.0025 per message (No change)
🔍 Why It’s Happening
These updates stem directly from our downstream carriers in response to changing delivery and infrastructure costs across telecom networks.
Updating our rates ensures:
• Continued high-quality service and performance
• Reliable and optimised message delivery
• Direct alignment with global carrier pricing structures
🙏
Thank You
We understand how important clear and transparent communication is regarding billing updates. We are committed to keeping you informed well in advance to ensure these adjustments are as seamless as possible. No action is required on your end. The updated rates will apply automatically from the effective date.
new
Phone System
Privacy Policy + T&C URLs on Toll-Free Verification
Overview:
Toll-free verification now asks for your Privacy Policy URL and your Terms & Conditions URL. Carriers will begin rejecting any new toll-free verification without both links on September 15, 2026, so both fields are live now and required before you submit.

What's new:
- Two new fields on Step 3 (Messaging use case), directly below your opt-in workflow images. Both are required before you can send the submission.
- Steps 1 and 2 are unchanged. Existing verified numbers are out of scope and need no update or re-verification.
Previously:
- The form didn't ask for policy links, so a missing o policy page only surfaced when Carriers rejected the submission.
Why it matters:
- From September 15, 2026, a toll-free submission without both links is rejected outright. Providing them now keeps your new numbers moving.
improved
SaaS Mode
Delete Saved Payment Methods on SaaS v2 Sub-Accounts
What's New
You can now delete a saved payment method from your sub-account. If a card is outdated, expired, or just no longer needed, you can remove it directly instead of leaving it on file indefinitely.
Why It Matters
This gives you full control over the cards saved to your account and keeps your billing dashboard clean and easy to manage — no more sorting through payment methods you no longer use.
Notes
Available for sub-accounts on SaaS v2 system.

Load More
→