Your customers no longer want to click through software. They want to tell it what to do and have it happen. SaaS is shifting away from menu-driven screens toward AI-powered conversation, and chat is becoming the new front door to every tool you use.

Today that shift arrives for WhatsApp on HighLevel. Ask AI can now run your entire WhatsApp channel for you, end to end, from a single chat window. Templates, sends, bulk campaigns, Flows, analytics, and onboarding. Describe the outcome you want. Get the campaign, the template, or the Flow. Live.

> "Create a WhatsApp marketing template for a bakery — 50% off all items, personalize with first name, add urgency, include a CTA button, and bulk send to all contacts tagged " One sentence. Template created, audience picked, every message sent, read status tracked.

Prompts to try right now:

The most successful businesses of the next decade will not out-click their competitors. They will out-command them.

Every hour your team spends navigating builders, stitching together bulk sends, and pivoting between dashboards is an hour not spent with customers. Ask AI × WhatsApp gives you that hour back at campaign scale, and puts the full power of WhatsApp into the hands of every person on your team.

The AI Agent action now uses significantly fewer tokens per execution with no impact on output quality. Since usage is billed per token, this directly translates to lower costs and more room to scale.

Tested on the same workflow and contact with zero quality loss:

First LLM call: 36% token reduction

Total execution: 20% token reduction

Every workflow execution is now leaner. Same output quality, fewer tokens, lower cost — meaning you can run more automations without increasing spend.

The AI Agent action now supports MCP connections, allowing your agent to connect to external apps and services in real time. Instead of being limited to data inside your CRM, the agent can now reach search engines, browsers, databases, APIs, and any MCP-compatible server, directly within a workflow.

Any MCP-compatible server works out of the box. Popular options include Exa (AI-powered web search), Tavily (real-time web search and page extraction), and Browserbase (full browser automation). Custom MCP servers and open-source options are also supported.

Transport types: HTTP Streamable, SSE

The AI Agent action inside workflows now has full visibility into a contact's entire conversation history across every channel. Before responding, the agent can read every past conversations a contact has had before replying. This makes sure agent is contextually aware of all the messages.

Channels covered: SMS, Email, WhatsApp, Instagram, Facebook Messenger, TikTok & more

The agent automatically uses the tool when mentioned in the system prompt or is required for achieving the goal.

It automatically pulls in contact's conversation threads and recent messages across all channels. It also pulls an AI generated summary for a high level overview if conversations are really long.The agent then responds with full awareness of every prior interaction.

Previously, the agent's context started from the moment it took over a conversation. If a contact had been chatting on WhatsApp for a week, emailed twice, and DM'd on Instagram, none of that history was visible.

Now the agent picks up the way a teammate would — reading the full thread before jumping in. A contact who emails about a quote on Monday and follows up via Instagram on Wednesday will hear from an agent on Friday that already knows about both, references the quote, and picks up exactly where things left off.

We’ve introduced a new Location-Level Breakdown widget in the Reselling tab to give you deeper visibility into how each sub-account contributes to your revenue and profitability.

You can now view a detailed table of sub-accounts (locations) with key financial metrics, including:

This provides a clear, side-by-side comparison of how each location is performing.

The widget is fully interactive, allowing you to:

Beyond visibility, this feature enables action:

Previously, agencies lacked a unified way to analyze performance at the sub-account level, making it difficult to:

This enhancement brings actionable, location-level insights directly into your workflow—helping you manage, optimize, and scale your reselling business with confidence.

AI Studio now supports a larger context window for project history, along with compaction for projects that exceed the history budget. This ensures important context is retained, improving response quality and helping mitigate LLM context window limitations.

Thinking messages are now more intuitive and context-aware. Instead of the earlier long-lasting “Thinking…” indicator, users will see more relevant and timely feedback aligned with their actions.

Issues with context loss across multiple builder sessions have been resolved. Previously, context was limited to a single session, which could cause the AI to lose track once a new session started.

AI Studio now maintains a persistent, per-project context across sessions, resulting in more consistent and accurate outputs.

Resolved an internal infrastructure issue that occasionally caused slow or partial cloning. The cloning process has been optimized for better speed and reliability.

Take control of your newsletter timing and send messages when your audience is most likely to engage.

Until now, newsletters were sent at a fixed default time — the same for every community. With Newsletter Time Configuration, that changes.

Admins can now choose exactly when newsletters go out, based on what works best for their members:

No more generic schedules — your community, your timing.

🚀

We’ve improved the booking experience for Rentals to make selecting dates faster and more intuitive.

Previously, when a customer selected a , the end date picker would still open in the current month, requiring users to manually navigate again. This added unnecessary friction during booking.

With this update, the.

When a customer selects a on the booking page:

You can now drag and move nodes directly inside the workflow canvas. This enhancement makes it easier to reorganize actions and branches without deleting steps or using the right-click move option for each node you want to move.

When you hover over a node, a 6-dot drag handle appears. Click and hold the handle, then move the node to a new position in the workflow. As you drag, the canvas shows a clear “Move here” indicator so you can see where the node can be dropped.

Managing larger workflows can be slow when you have to move steps one by one through right click menus. Drag and drop gives you a faster, more fun and intuitive way to clean up layouts and reorganize branches as your workflow changes.

You can now start a workflow whenever an inbound email is received in your mailbox. This covers cold emails from brand-new senders, warm emails from existing contacts, and, if you allow it, replies inside existing threads - so you can automate lead capture, routing, support intake, and follow-up from the moment an email arrives.

Every inbound email is a potential lead, support request, or deal moving forward - and now your workflows can act on it instantly. The Inbound Email trigger captures emails the moment they land, including first-touch messages from people who aren't in your CRM yet. That means sales teams can route and respond to cold inquiries automatically, support teams can assign incoming requests without manual sorting, and ops teams can kick off processes as soon as a signed document or form hits the inbox.

The trigger fires when an inbound email is received and can be narrowed with filters for mailbox, sender, CC, subject, body, attachments, and whether the message was tied to a workflow. You can also choose to run it only for new email conversations, which helps avoid retriggering on every reply in the same thread.