Watch: Demos and Prototypes

At Intercom, we’re experimenting with new products and features every day, especially with AI. We’re exploring what the latest AI models can/can’t do.

We are now sharing some of the work in progress to give people a sense of what we’re up to, and maybe start a discussion with us. We’d love that!

August 2025

Content Suggestions – Contradictions and Duplicates

We’ve been working on something new for Fin’s Suggestions – Contradictions and Duplicates.

When you feed Fin a big knowledge base, messy stuff creeps in over time:

– Some content quietly disagrees with other content.

– Some of it is just the same thing again and again.

Both cause problems. Contradictions make Fin second-guess itself. Duplicates clog up its short-term memory, so it can’t pull from as many different sources.

This new feature finds and flags them. Clean them up, and you end up with a tidier knowledge base, less agent confusion, and more varied, reliable answers. Yet another small, satisfying win that makes everything else work better.

Product Engineer Tom Moran has this demo.

July 2025

Voice notes for Fin

Typing isn’t always the best way to ask for help – especially when you’re busy or on the move. With Voice Notes in Intercom Messenger, you can talk to Fin like you would in any messaging app.

Just tap the mic, speak naturally – in any tone or language – and Fin will understand your request and respond with the right help. You can play back your message or read a transcript if listening isn’t convenient.

In this demo, Product Engineer Jason Praful asks Fin about setting up a help desk email using a custom domain and configuring a signature – in both English and Spanish. Fin handles it all. Voice Notes are a small update, but a big shift in how people interact with support.

Smart Routing for Fin

Today we want to share something exciting that we’ve added to Fin Voice: Smart Routing. It lets you say goodbye to old, messy IVR trees and simply talk naturally to our AI agent, Fin, who will understand exactly why you’re calling.

In this quick demo, Product Engineer Brennan Buitendag shows how Fin recognizes a user’s true intent. They ask about a refund, then pivot to a serious concern about service quality (like their dog returning excessively muddy from a sitting?).

Fin listens, understands the shift, and routes them straight to the right team – no frustrating button presses or wasted time. It’s about making AI voice support feel more human and efficient.

Design prototyping with AI

Our design team at Intercom is becoming fully AI-native, using AI to work directly in code and move from idea to execution faster, whether it’s building new components, fixing UI bugs, or exploring new concepts.

Here’s a quick example of how we’re using AI in the Front-End Technologies team to build components as we transition our tech stack to React.

Staff Product Designer Domingo Widen explains that having direct access to code gives him a clear view of how components behave and allows him to hand over working code to engineers. More importantly, AI has helped Domingo grow his front-end skills and learn concepts that make him a more effective partner to his team.

Weekly Topic Trends

Support metrics fluctuate. That’s a fact. What’s harder is understanding why.

Many customers tell us they spend hours manually digging through conversations, trying to piece together what’s driving the changes. It’s inefficient, but it’s what the job requires.

Here’s a little sneak peak at another Insights feature we’re building called Weekly Topic Trends that changes this.

It automatically analyzes your conversation volume, identifies which topics are behind your metric changes and why. Instead of hunting for root causes, you get direct answers about what’s happening in your support operation.

Early stages, still being refined, but the customers testing it are finding it impactful for understanding changes in their support metrics and focusing their investigation efforts.

CX Score updates

The feedback on CX Score has been overwhelming positive since release. Support teams can finally see a complete view of the quality of service being provided across every customer conversation.

But when service levels are not up the standard, everyone wants to know “why”.

In this demo Staff Product Manager Mark O’Donovan shares an early walk through of how you can now understand the real drivers for any negative customer experience, and also get an summary view of the what most pressing issues are across all of your support volume.

Fin on Discord

Dale Cantwell, Senior Manager, Engineering, has been working at Intercom for over a decade building our Messenger channel. Dale’s team’s mission is to build channels that connect Intercom and Fin to anywhere you need to support your customers. In this demo Dale talks about our newest channel, Discord.

If you’re interested in getting onto our Alpha list, let us know!

Multi-brand for Fin

Fin AI Agent used to be one-size-fits-all. One identity, one tone, one knowledge base, even if you supported multiple brands in one Intercom workspace. That didn’t scale so now we’ve built Multi-brand for Fin.

Each brand gets its own Fin identity with its unique voice, escalation rules, and content, all easy to manage in one single workspace. That means you can deliver a fully automated, on-brand support experience for every brand you run.

In this demo, Senior Product Manager Ángela Castillo-Gill used AI to generate two fictional skincare brands: Lunaria (clinical and upscale) and FreshDrop (fun and accessible). Same inbox. Two distinct customer experiences.

Multi-brand for Fin is now in alpha.

Fin Batch Test by AI Topics

Most support teams review past conversations hoping to improve. But what if you could test proactively instead?

The Solution: Matthew Attard, Product Engineer at Intercom, built topic-filtered AI question generation that brings Topics from Insights directly into Fin Batch Testing. Now teams can generate test questions from their actual conversations, filtered by specific topics, so they can see what common issues customers are having and test their Fin against those real scenarios.

Why this matters: It creates a truly connected workflow. See billing conversations trending in Topics Explorer? Generate test questions from those actual billing conversations. Need to improve customer onboarding support? Test with questions that match real customer onboarding issues.

What’s the biggest disconnect you’ve seen between analysing problems and actually testing solutions?

June 2025

Creative Coding with Claude

In our latest demo, Justin Truong shows how Intercom’s brand design team used Claude to execute the visual ideas behind Pioneer, the summit for AI customer service leaders, no engineer needed.

Take a look at the Pioneer site here.

AI-powered Suggestions

For the first time ever, you can now improve AI agent performance – with a single click.

AI-powered Suggestions is a groundbreaking new feature that helps you fix gaps in content, data, or actions to improve Fin’s performance.

No detective work. No guessing. No weeks of analysis. Just clear improvements you can implement instantly.

Check out this demo from Ahmad on our Product Team to see AI-powered Suggestions in action!

Fin on Slack

Slack is where your customers already are, but until now, it’s been a tough place to offer great support.

Today, I’m excited to share our new native Slack channel in Intercom, with full support for Fin, our AI agent.

Now, Fin can instantly help customers in Slack, and your team can jump in seamlessly when needed. No copy-pasting. No context lost.

Check out the demo below to see how it works – and if you’re keen to join our Alpha, let us know in the comments!

May 2025

Optimize Dashboard

To improve AI agent performance, teams can spend days and weeks on content editing, and on 3rd party system integration improvements.

Last week at Built For You we launched the Optimize Dashboard – a powerful new tool that highlights specific opportunities to optimize Fin’s performance, with suggested improvements that you can instantly action.

It shows where Fin is underperforming, pinpoints what’s causing it, and provides AI-powered Suggestions to fix gaps in content, data, or actions—so you can instantly improve Fin’s answers with a single click.

Now, you can make performance improvements for Fin in minutes, not weeks.

It also makes Fin a self-improving system:

• When Fin can’t answer a customer query, it is surfaced as a suggestion.
• You can one click accept.
• Now Fin will excellently answer that query the next time.

Do this again and again, and you can drive up resolution rate very quickly.

In this demo Senior Product Manager for the Optimize Dashboard Ahmad Mu’azzam walks through how it works, and how you can easily improve Fin’s performance.

Topics Explorer

Introducing the Topics Explorer: Spot trends and uncover insights across your customer conversations.

Businesses have hundreds of thousands of customer conversations a year, but no good way to understand all of them.

The Topics Explorer fixes that. It uses AI to organize every single customer conversation into topics and sub-topics, giving you an unprecedented view of what’s driving support volume and impacting quality.

Topics Explorer let’s you drill right down from a topic, into sub topics, into groups of conversations in that sub topic, into individual conversations.

Now, you can easily spot patterns, track trends, and catch emerging issues before they impact your customer experience.

In the demo below, Molly Mahar – Principal AI Designer for the Topics Explorer – breaks down how it all works, and how to identify specific, actionable issues to fix.

CX Score

This week we launched a completely new and better way to measure customer experience: the CX Score.

We think this is a really big deal, and huge step forward.

We worked hard to build this breakthrough, AI-powered metric, because the way we measure customer service is broken.

CSAT has really poor coverage and inaccurate answers, only giving us a view of less than 10% of our customers’ experience. It’s the metric we love to hate. So why do we still use it?

CX Score will become the new standard because it is much better: it gives you a complete view of your support quality across every customer conversation – no surveys required.

How it works:
CX Score uses AI to score every customer conversation from 1 to 5, based on resolution, sentiment, and service quality – all in real time.

Finally we have a way to measure our customers’ experience that is robust, reliable, and gives us full coverage. Take a look at this demo by Intercom Director of Product Management Christine Zdelar, and I’d love to hear your feedback or questions in the comments!

Fin AI Agent Escalation

Let us introduce you to a term you’re going to hear a lot more in the near future: probabilistic design.

Here at Intercom, we think it’s the future of design.

In this demo, Intercom Senior AI Designer Burak Urgancioglu takes you deep into our new escalation prompt and shows you how we’re harnessing the potential of probabilistic design by leveraging the synergy between our features to deliver smarter, more adaptive outcomes.

Batch Test with Fin

Fast feedback loops are essential when building with AI – and that’s how we’ve approached Batch Test for Fin at Intercom.

In this demo, Intercom Staff Product Manager Pav Gill shows the redesigned experience for Batch Test, shaped by customer feedback and real world use. It’s now faster, easier to manage, and built for testing at scale!

Simulate Users with Fin Preview

When you’re setting up an AI Agent for Customer Service you need to be super clear that it’s going to behave the way you expect it to. To help with this, Intercom Senior Software Developer Ben Robinson and his team have been working on a feature we’re calling Impersonation.

It lets you see exactly how Fin will respond to any of your actual customers, so you can test with confidence before going live. It’s in closed beta for the moment, but Ben has recorded this demo you can watch.

Fin AI Agent as MCP Client

Earlier today we shared how Intercom is using MCP to give AI systems like Claude access to real-time customer data from Intercom. Great for teams without access to our helpdesk to benefit from a wealth of customer data.

Product Engineer Luis Alvarez Aguilar has been working on the next step in that journey: making Fin act as an MCP client so it can connect with third-party and internal business tools, access data, and take action for customers.

In this demo, Luis shows how Fin connects to a Stripe MCP server to:

✅ Answer customer pricing questions

✅ Pull product plan details

✅ Generate a live payment link—all inside a conversation

We’re still in early stages, but it’s exciting to see Fin connecting with external tools through open standards. More to come soon.

Intercom MCP Server

This week, Senior Product Engineer Davy Malone built an Intercom MCP (Model Context Protocol) server using Cloudflare Workers—and it’s been a game changer.

It allows AI systems like Claude to access real-time data from Intercom: user profiles, conversation history, ticket metadata, and more.

For our engineers, this means less time manually pulling context across systems—and faster, smarter troubleshooting when issues arise.

And we’re just getting started. Soon, our AI agent Fin will also be able to connect to MCP servers to access data and perform actions in external systems.

If you’re curious about where this is going, we’ve shared more on our product vision for MCP here.

April 2025

Setting Fin Voice Live

Last week, we shared an early look at Fin Voice, our AI agent for the phone channel.

In this demo, Artem Ankudovich show’s how to take the next step by moving from a testing environment to going live once you’re confident in Fin’s tone, accuracy, and logic.

It’s exciting to see Fin step in as a frontline agent, handling real queries and handing off to another team when needed.

Fin Voice

Phone support is powerful – but also one of the hardest channels to get right. It’s often slow, tough to scale, and frustrating for customers stuck on hold. That’s why we built Fin Voice – our new Voice AI agent that helps businesses deliver instant, 24/7 phone support, without the wait.

In the demo, you’ll see how Fin responds to common support questions in the Fin Voice testing environment. No matter how large your help center is, Fin can instantly give the right answer and guide your customers – just like a human agent. It’s a glimpse of what support could look like without phone trees, hold music, or long wait times.

We’re still in the early stages, but the potential is big.

AI-Generated Content from Video

We want to share with you an experiment we built at a recent Intercom hackathon around converting videos into great content.

Inside Intercom, we share a lot of product videos internally as we develop and test new features. An idea Senior Group Product Manager Chris Dalley and Staff Product Manager Peter Bar tested was whether we could use AI to convert these product videos into great Help Center articles complete with auto-generated product screenshots – turns out yes we can!

This was a small experiment, but it points to a future where support content could is much easier to create, update, and scale – all from recording a quick video.

It’s still early thinking, and we’re not yet sure where it fits – maybe we should add it into the product? Also curious what approaches you have tested for creating great AI content?

Multilingual Workflows

Scaling support used to mean more tools, more workflows, and more manual effort.

AI is shifting that. And our Multilingual Workflows beta is part of that shift. It lets teams build once and serve every customer, in any language, without duplicating effort!

Check out this working demo, and share what’s helping your team scale.

AI Category Detection for Fin AI Agent

AI is transforming how customers get support. In particular, it’s reshaping the invisible parts, like how conversations are assigned to the appropriate teams.

When a customer reaches out, they expect to be understood and quickly directed to the right place. Intercom’s AI Category Detection feature helps Fin do exactly that. It analyzes each conversation to identify things like the request category or sentiment, and then saves this information as conversation data that can be used for routing, reporting, and more.

In this demo, we show how it can be used to automatically assign conversations to the right support team. No long menus for customers, no manual triage for teammates.

The feature is in closed beta, and we’re still learning more. Stay tuned!

OTP for Fin Tasks

As AI Agents take on more complex and sensitive workflows, security can’t be an afterthought. It has to be built in from day one.

At Intercom, we’ve designed Fin with security as a first principle, enabling customers to configure multiple layers of protection, real-time verification flows, and safeguards that help maintain trust between agents and their customers.

In this demo, Fin supports a customer through a policy amendment, verifying their identity and then guiding them through the process step by step.

Take a look and let us know what you think.

AI Generated Fin Task Instructions

Last week, we shared a demo of Fin showing how we’re blending rules based (deterministic) and natural language based (generative) logic in Fin so that our customers can configure the exact customer journeys they need.

This is a very important thing to learn about and understand if you are using or building AI Agents.

But this whole area is new, it has never existed before the AI era, and so people need to learn how to do it. To help them, we’ve built a feature that uses AI to suggest instructions. Today we’ve a nice follow up demo showing how you can write structured Task instructions using natural language in Fin.

March 2025

Fin Tasks

The future of AI Agents is generative and deterministic workflows blended together, and Agents that complete full Tasks for customers.

Most businesses have complexity, and in exploring different ways Fin can work for our customers, it’s really clear that they need both generative and deterministic steps in single workflows. Here is a demo of our work in progress.

Fin in the Help Center

Knowledge bases are a critical line of defence for support teams but they can also become a bottleneck, leaving customers to sift through hundreds of articles to find what they need.

So we ran an experiment: using Fin to deliver faster, more direct answers inside the Help Center.

We’re still early in the test but already learning a lot about how AI can reshape self-serve support.

Fin Messenger experiments

Over the past month we have been very busy running a series of experiments on the design of Fin in our Messenger. We decided to challenge numerous design decisions that were meant to address problems from a different era.

Every new experiment lead to theories, every theory lead to new ideas and ideas with the best rationales made it to their respective A/B tests. The results were as interesting as the process itself. This demo shows the results, and how we think about our AI products and using data to refine our design decisions.

Fin Testing

As more customers use Fin, we’re learning how important it is to test how Fin answers different types of questions.

So we’ve been building new powerful testing tools. Here is a working beta of one of them.

What makes it so powerful is the ability to bulk test how Fin answers a set of questions. Plus, right below the answers, you’ll find details on the inputs used to generate each response, making it easy to troubleshoot and refine.

We’re already seeing how this is helping customers feel more confident in how Fin responds – and giving them the tools to make those responses even better.

Fin Guidance Assistant

We mortal humans are still trying to learn how to use AI systems. The more we talk to them, the more weird and wonderful things we learn about how they ‘think’. LLMs are a generative technology which makes them unpredictable at times.

But using AI for business, we need to be able to control parts of what they do. We built Fin Guidance to do this, so you can guide Fin. But guidance is like advice, you can give good or bad advice, and so you can give good or bad guidance!

And we’ve seen customers doing this, trying to give good guidance but learning through trial and error that it doesn’t quite work as intended. So we’re now building tools to help our customers write good guidance. This is cutting edge stuff, we’re using Anthropic’s Claude 3.7 Sonnet with Extended Thinking.

February 2025

Real time Inbox Translations

Customer Service teams need to support their customers in many languages, and so end up hiring multilingual speakers, using different translation tools, and ultimately adding a lot of complexity to their support operations.

But AI is excellent at real time translations. So we’ve been building that into the Intercom Inbox. Now any customer and any agent can seamlessly converse, no matter their language.

Fin over API

So far, Chat has been the dominant interface for us to communicate with AI. Makes sense, it is familiar. But that is going to change, and soon. We’re seeing customers who want to build their own interface to Fin (our AI Agent) so we’re building Fin over API. Now, any interface is possible.

Giving Fin Guidance

When Support teams hire new people, they train them, they give them guidance on what to say and how to react in different scenarios.

They need to do the same for AI Agents, so we’ve been building that into Fin.