HALO makes even complex conversations simple to automate. Ask HALO lets you build and continuously improve your agents, while CM.com's infrastructure connects them to every channel, customer context, and system they need.
Already changing how teams build and improve AI Agents
They need context, an action in a system, or a person who can take over. HALO is the agentic layer of CM.com that brings those parts together.
HALO Agents work across voice and messaging on your existing communication infrastructure.
Uses history, knowledge, context, CXP, and connected systems to understand the customer.
HALO reasons over what's needed, calls tools and APIs, updates systems, and completes interaction.
When judgment or empathy is needed, it continues in Agent Inbox with full context.
Ask HALO lets teams inspect issues, find causes, adjust the agent, and test fixes. all in one place.
HALO Agents work across voice and messaging on your existing communication infrastructure.
Uses history, knowledge, context, CXP, and connected systems to understand the customer.
HALO reasons over what's needed, calls tools and APIs, updates systems, and completes interaction.
When judgment or empathy is needed, it continues in Agent Inbox with full context.
Ask HALO lets teams inspect issues, find causes, adjust the agent, and test fixes. all in one place.
An AI agent that builds AI agents. Describe the problem you want to solve in plain language, and Ask HALO builds the agent, connects it to your tools, tests it, and fixes what it finds along the way. From idea to a working agent in minutes, no heavy lifting required.
Ask HALO is built into the lifecycle of every HALO Agent. Describe what you want to build, test it before launch, learn from real conversations, then use Ask HALO to investigate what happened and improve the agent, tools or knowledge behind it.
Ask HALO reads the current environment, proposes a plan and creates the agent, tools, context variables and handovers it needs. Larger changes remain in draft until you approve and publish them.
Create or update agents
Build tools from text, files or images
Preserve the existing configuration
Connect knowledge, context variables, customer data, APIs and workflows. HALO can work with the context available today, while CXP adds richer connected customer context and predictions.
Reuse existing tools and variables
Create missing tools and connections
Connect handovers and agent networks
Ask HALO runs test cases after creating or changing agents and tools. You can review the inputs, outputs and tool results before deciding whether the draft is ready to publish.
Test agent behaviour
Inspect tool input and output
Keep live agents untouched until publish
Publish HALO Agents across voice and messaging. The channel changes, but the agent can keep using the same knowledge, context, tools and handover logic.
Voice and messaging channels
Consistent brand and behaviour
Human handover in Agent Inbox
Ask HALO traces which agent answered, which tools ran and which knowledge and context were involved. It identifies the likely cause, fixes what it can in draft and tests the result.
Debug live conversations
Find prompt, tool or context causes
Apply and test changes in draft
Use Analytics to spot patterns across every conversation, or ask HALO to investigate performance in plain language. Go from topics and resolution rates to the conversations behind them, understand what caused the outcome, then improve the agent, tools or knowledge that shaped it.
Topic Analysis automatically groups conversations into topics and subtopics, making volume and problem areas visible.
Break outcomes down into Resolved, Undetermined, Unresolved and Handover instead of relying on one overall resolution number.
Put feedback next to topic and resolution, so a technically resolved conversation does not automatically count as a good experience.
Open the underlying conversation, inspect the agents and handovers involved and trace answers back to the knowledge that informed them.
Teams can use the dashboards to drill from topic and resolution into individual conversations. But the faster improvement loop starts in Ask HALO: bring in the conversation you are working on, let it uncover what happened across the agent, tools and knowledge behind it, and improve what needs changing right away.
CM.com does not just connect HALO to communication channels. We operate the CPaaS infrastructure underneath them. That gives HALO a deeper connection to the conversation itself, channel events, metadata, routing and conversational signals can flow directly into the AI experience instead of being stitched together through another integration layer.
Voice
Run HALO directly on CM.com telephony and bring live speech, intent, context, tools and handover together in one voice experience.
WhatsApp + messaging
Use the native capabilities and signals of WhatsApp and other messaging channels while HALO keeps the reasoning, context and business logic consistent.
Live chat
Put HALO directly into your digital experience, with the same knowledge, tools, context and escalation logic used elsewhere.
Understand the message, classify intent, use customer and operational context, complete the work and generate the reply without creating a separate automation stack.
Social + messaging channels
Use HALO across supported social and messaging channels while preserving the channel signals and interaction context behind each conversation.
Teams + Slack
Bring HALO into collaboration channels so teams can access agents, knowledge and operational actions without opening another tool.
Use HALO through APIs for custom experiences while keeping the same agents, knowledge, context, tools and improvement loop behind the interaction.
HALO is not an AI layer floating next to the rest of your customer operation. Inside CM.com it can work directly with the communication, context, service and activation layers around it. The more of that environment you use, the richer the agent becomes, and the less infrastructure you have to assemble yourself.
The intelligence across the operation.
HALO reasons over the conversation, uses the context available, chooses the right tool or workflow and performs the work.
Handle more
Automate repeat work and let AI Agents process many conversations at the same time.
Resolve faster
Connect the conversation directly to the context, tool or person needed to move forward.
Protect quality
Test changes before launch and investigate real conversations when something goes wrong.
Improve continuously
Use Ask HALO to shorten the path from an issue in production to a tested change in draft.
We handle thousands of unique personalized orders every day, and yet 70% of all customer questions via chat are now resolved automatically. That gives our team the space to be truly personal when it actually matters.
79% of our customer chats are now fully handled by Lucie, our AI colleague. That's not just a number, it means our team finally has the space to focus on conversations that truly require a human touch.
We now handle 44% more customer contacts with the same team. Not by working harder, but because AI takes care of the repetitive questions so our people can focus on what actually matters.
Checking an order status used to take a minute and six manual steps. Now the AI responds in 5 seconds, and that's already happened over 22,000 times. That's the time our team gets back for the conversations that actually require expertise.
AI is not about replacing our expertise, it’s about making it more accessible. The more we work with it, the more we see how it can strengthen the guidance we provide.
Agentic AI is a type of AI that can act autonomously to accomplish tasks. This means that AI agents can make decisions and take actions on their own, and they can even learn from themselves to improve over time.
Agentic AI can think, learn and adapt without needing constant interference or redirection. 'Agentic' means 'agent-like behavior, such as expressing agency or control on one's own behalf'.
An important component of Agentic AI are AI agents. These AI agents act as virtual employees with a certain degree of autonomy within the Agentic AI framework, designed to perform tasks on behalf of the business.
There are many types of AI agents, from agents that can help with order management to streamline services, give shopping advice to help convert and boost sales, and much more. And there is no real limit to how many AI agents a business can create..
So, how does one control AI agents? First, with a platform that has governance or quality assurance options, by setting clear objectives, and implementing role-based access. This makes sure that there is no unauthorized use possible with the AI tooling. And secondly, by actively monitoring the performance of the AI agents. Use dashboards to keep track on behavior and results, and tweak the AI agents accordingly to make sure everything works seamlessly and results keep improving.
See how HALO connects customer conversations to context, actions and human agents, and how Ask HALO helps your team build and improve the entire operation.
HALO, our Agentic AI solution, just got a powerful new upgrade: Voice. With Voice as a channel, you can fully automate phone conversations and serve customers more efficiently.
Artificial Intelligence (AI) has been in development for decades, but the way we use it today has changed dramatically. With the advent of ChatGPT and other applications, AI has suddenly become tangible for the general public. While it was previously used primarily for specific, often invisible applications (think fraud detection in banking or predictive maintenance in industry), it now actively assists in content creation, enhancing customer experiences, and streamlining processes. Within customer experience, three forms of AI are particularly relevant: generative, agentic, and predictive AI. In this article, we’ll break them down and explain how to leverage them effectively.
Imagine customer inquiries being answered 24/7 without wait times, automatic updates on delayed orders, or fully digital shopping assistants guiding customers from browsing to purchase. These are just a few examples of what Agentic AI can achieve. In this article, CM.com’s Marketing Lead AI & SaaS, Sander Harryvan, and Product Marketer, Tom Faas, share their insights on where businesses currently stand in adopting Agentic AI, what the next phase looks like, and why Agentic AI will have a profound impact on the way we do business in the coming years.
Customer service teams are used to precise analytics. Average handle time, first contact resolution, CSAT scores, numbers that are clean, comparable, and easy to report on. AI agents change that dynamic in a fundamental way.
More and more companies are rolling out AI agents that go far beyond generating content or answering simple questions. They handle customer requests, update systems, trigger workflows, and even complete transactions. This brings speed, efficiency, and relief from manual, repetitive work. But once AI starts doing instead of merely assisting, something fundamental shifts. You need more than clever technology. You need a clear way to stay in control of what it does, why it does it, and the limits within which it can operate. This is where AI governance comes in. Not as a tick-box compliance layer, but as a practical foundation that keeps AI predictable, explainable, and safe as it becomes more autonomous.
' Tis the season for conversational commerce - and CM.com can deliver the whole customer journey in one package! From getting your promotional material seen to facilitating payments within the conversation, and some post-purchase customer care to turn holiday shoppers into loyal fans of your brand.
Customers are increasingly communicating through apps rather than traditional phone calls. That is why we are introducing an important expansion of HALO today: Voice Agents can now automatically handle incoming calls made through WhatsApp. We are also looking back at improvements we have added to HALO over the past months. Developments that bring voice and chat closer together and help organizations automate faster and more consistently.
Select a region to show relevant information. This may change the language.
HALO
HALO
HALO
HALO
HALO
HALO