Intercom Release Notes

You can now apply SLAs to inbound phone calls — so your team knows exactly what they're aiming for, and whether they're hitting it.

• Set targets in workflows — Add an Apply SLA step to any phone workflow and choose a speed-of-answer target. The timer starts the moment the Apply SLA step runs in your workflow and stops when a teammate answers the call.
• Track status in the inbox — Each phone conversation shows its SLA status, so your team can see immediately which calls are on track and which need attention.
• Measure performance in reporting — Phone SLA data appears in your existing SLA reports alongside chat and ticket SLAs — track met rates, miss rates, and performance over time.

Learn more here

Original source

Supervisors and team leads can now step into live calls — visibly or invisibly — with two new Intercom Phone tools.

Join call (Barge)

When your team needs backup, join the call instantly. Confirm, and you're on — already up to speed because you've been listening the whole time. No scrambling, no back-channel messages.

Coach (Whisper)

Prefer to guide without interrupting? Speak directly to your teammate while they're on a call — your voice reaches only them, the customer hears nothing. Switch in and out as needed, without disrupting the call.

Learn more here

Original source

Learn how Operator can help you understand, manage, and improve your customer experience in a way that has never been possible before.

Today we’re announcing Operator, an Agent that works across both Fin and the Intercom helpdesk to help you manage your customer operations.

Operator manages help content, builds automation, does the ongoing work that determines how well Fin performs, and runs the operational work your human team doesn’t have time for.

Why we built it

Running a customer operation means managing AI and humans simultaneously, and doing this well requires more capacity than most teams realistically have.

On the AI side, Fin’s performance is largely influenced by what surrounds it: the accuracy of your help content, the quality of your Fin configuration, and how well you understand what’s working and why.

Keeping your help center current when product teams ship daily means finding every affected article before customers notice the gaps. When Fin gets a conversation wrong, diagnosing it requires reading through what happened, identifying the root cause at the configuration level, making the fix, and verifying it worked. Analyzing why your resolution rate dropped means pulling conversations, finding patterns, and tracing the cause back to something actionable. And beyond individual fixes, there’s the ongoing question of what to automate next – what your human reps are still handling repetitively, whether it’s worth building a Procedure for it, and how to test it before it goes live.

On the human side, the demands are just as continuous. When an incident hits, someone needs to identify every affected customer, draft the right response, and send it before the problem compounds. Team leads need visibility into rep performance across hundreds of conversations to coach effectively and prep for 1:1s. Reps need to know what to prioritize without spending the first part of their day figuring it out.

In both cases, the work often outpaces what most teams can keep on top of, so it happens reactively, or not at all. Operator was built to change that, giving teams a new way to understand, manage, and improve their customer operations.

How Operator works

Operator can transform every part of your customer operation, and every team using it finds new ways to put it to work. From analyzing data, to managing knowledge and building automation, there are endless ways to use it. Here are just a few.

Ask your data anything

Your support operation generates more useful data than most teams have time to process. Operator gives you direct access to it. You can ask it any question about what’s happening in your operation (why a metric changed, what’s driving escalations, how the team performed last week) and it returns structured answers with charts, breakdowns, and the ability to dig further.

It analyzes samples of real conversations on the fly to surface patterns and identify root causes. If your head of product wants to know what customers are saying about a new release, you can ask Operator rather than spending half a day pulling a report together. It also works across your entire operation, analyzing Fin’s performance, your human reps’ performance, and customer sentiment.

And you don’t have to ask for information like this from scratch every time. Give Operator ongoing work, like analyzing your automation rate every Monday, flagging anything that needs attention, and posting the report in your Fin workspace. It’ll run the analysis, write the report, and deliver it without you having to go looking for it.

Keep your knowledge based current without writing a single article

Your knowledge base is only as useful as it is accurate. When product teams ship fast, keeping pace with content updates is a substantial, ongoing job.

Give Operator a brief about anything, from a new feature or policy change to release notes, and it finds every article in your help center that needs updating, drafts the edits in your tone of voice and style, identifies content gaps, and drafts new articles to fill them. It even handles localized versions. Every change is formatted as a proposal (Operator’s version of a pull request) for you to review, edit, and approve before anything goes live.

Our own knowledge management team has been using it during development. Beth-Ann Sher, our Senior AI Knowledge Manager, says working with Operator is like having five additional knowledge managers working on the team.

Build, test, and ship improvements to Fin

When Fin gets a conversation wrong because of a content gap or misconfigured rule, Operator can debug it by reading through the conversation, identifying what caused the problem, proposing a fix, and running simulation tests to verify it before you approve. You see what changed and why before anything goes live.

Beyond debugging, Operator has deep knowledge of every Fin feature and capability, so you can ask it directly to help you configure whatever you need. If you need a Procedure for a specific query type, describe the outcome you want and Operator builds it, including triggers, multi-step instructions, edge case handling, and a simulation test, all from a single prompt.

The same applies to configuring Guidance rules, data connectors, monitors, and workflows. You don’t need to know which feature solves your problem or how to configure it; you just describe what you want.

For teams looking to increase their overall automation rate, Operator can handle that strategically too. Ask it to analyze where your biggest automation opportunities are and it surfaces them by volume, along with an estimate of the weekly team time each one is consuming. Pick one, and it builds the solution for you to approve.

This is the work our own implementation experts do to help customers get the most out of Fin. Operator makes it available to every team that uses the product.

Effortlessly manage your human support operation

When an incident hits, Operator identifies every affected conversation, drafts targeted responses, and sends them proactively, turning what would normally be hours of reactive triage into minutes of review and approval.

For ongoing team management, a team lead prepping for 1:1s can ask Operator to pull each rep’s metrics, flag outliers, and surface what’s worth digging into. A rep coming back from a meeting can ask what to focus on next and get a prioritized queue based on urgency, customer value, and wait time.

And because Operator sees patterns across everything your human team is handling, it can surface the conversations they’re still resolving manually, flagging your next automation opportunity before you’ve had time to go looking for it.

Hello, Operator

Operator isn’t a general-purpose AI model given access to your data. It’s built on a library of purpose-built tools that encode expertise specific to support operations, like how to pick the right attributes for a given analysis, search a knowledge base semantically, debug Fin’s reasoning in a specific conversation, or write and test a Procedure that will actually work.

The proposal (pull request) system makes this possible. When Operator updates content, adjusts configuration, or modifies how Fin behaves, it creates a proposal – a structured diff of what’s changing and why. You review it, edit if needed, and approve before it takes effect.

Operator does the cognitive work; the human stays in control of what goes live.

More than 200 early users are already trying Operator, and every one of them is finding new use cases. It’s a genuine step change in capability, and we’re confident it will change the way support teams run their operation. We’re working towards a vision of Operator being increasingly agentic, expanding across every new role Fin takes on.

Operator is available in early access now.

Original source

Average Adjusted Handling Time (AAHT)

Average Adjusted Handling Time (AAHT) measures the time a teammate is actively handling a conversation, the clock runs from when they first open it, pauses whenever they switch to other work, and resumes when they come back. Each conversation's handling time now reflects time actually spent on that conversation.

• Pause on conversation switch: the clock stops when a teammate switches to a different conversation and resumes when they return.
• Optional pause on teammate away: Admins can also pause AAHT when a teammate is automatically set to away due to inactivity. This uses an inactivity toggle in Settings.
• Public API for handling events: A new endpoint that returns the underlying pause/resume events for a conversation along with pause reasons.

Learn more

Original source

Fin for Ecommerce guides shoppers from browsing to checkout, delivering a new level of customer experience.

With the launch of Fin for Sales, Fin became a Customer Agent, expanding further across the customer journey. Today, we’re launching Fin’s next role – ecommerce.

Fin for Ecommerce is a new role purpose-built for Shopify merchants that combines shopping assistance and ecommerce support. Fin is already the best Agent for customer service, resolving over a million queries a week for 8,000+ businesses. Now, it handles the moments before the purchase too, guiding shoppers to the right product, addressing their concerns, and converting browsing into buying.

Here’s what’s new:

• Fin helps shoppers find the right product. It asks the right questions, narrows options from thousands of products, and compares them based on what the shopper actually needs. It’s like a great store assistant, at scale.
• Fin helps increase order value. It recommends relevant products based on the conversation, keeps carts easy to update, and guides shoppers into checkout when they’re ready.
• Fin handles support without losing the sale. Returns, refunds, and order changes can all be resolved in the same conversation. When the issue’s handled, Fin guides the shopper back to browsing.
• Fin is integrated with Shopify. Connect your store and Fin syncs your catalog, order data, and APIs in a matter of minutes. No manual training or complex setup.

Why we built it

When you walk into a retail store, an attentive shopping assistant makes a difference. They ask what you’re looking for, understand your preferences, answer the questions that matter most, and walk you to checkout. When you come back, they even remember you.

But this level of service has never made it online.

In fact, online shopping today looks almost identical to what it did ten years ago. You sort products based on price and color, read a site’s FAQs when you have questions, but quickly realize the experience is self-serve. And it has the same core limitation that self-serve has always had: it requires the customer to already know what they want.

Ecommerce might have scale and 24/7 convenience, but it’s also passive. It can’t understand a customer and help them find a product that fulfills their needs.

Fin for Ecommerce changes that by bringing high-quality shopping assistance to Shopify stores.

How Fin for Ecommerce works

Guide shoppers from discovery to checkout

When a shopper says “I need a gift for my partner” or asks “what running shoes work for trail and road?,” Fin doesn’t return a generic search results page. It starts a conversation. It asks about preferences, incorporates live browsing context, surfaces the most relevant options, and compares them based on what the shopper cares about.

This is powered by Fin Apex 1.0, the best-performing model for customer service, combined with a retrieval engine purpose-built for ecommerce. It handles vague, exploratory shopping questions and large product catalogs, helping shoppers find the right fit, faster.

Based on the conversation, Fin recommends complementary or higher-value options, keeps carts easy-to-update, and guides shoppers into checkout when they’re ready.

Blend support and shopping assistance in a single experience

Fin for Ecommerce is built on the same AI platform that powers Fin for Service. Fin understands whether a conversation requires shopping assistance, support, or both, and moves between them seamlessly without the customer noticing.

This means the same Agent that helps shoppers buy also handles the hard and complex post-purchase work including refunds, exchanges, order changes, tracking, and shipping questions. It can make changes in real time, within the same conversation, using the same context and data.

Integrates with Shopify

Fin for Ecommerce is purpose-built for Shopify merchants. Connect your Shopify store and Fin establishes a live connection to your entire catalog – products, variants, content, and order data – ensuring every response reflects your latest inventory and shoppers only see what’s actually available.

You can add the Messenger to your store and set Fin live in minutes without any manual training or technical expertise. When connected to Shopify’s API, Fin can handle even your most complex customer requests like tracking orders, processing returns, and updating subscriptions via Procedures. Fin automatically drafts Procedures for common ecommerce support queries based on your Shopify account and customized to your company policies.

You review, adjust, and publish, allowing Fin to start handling real queries in minutes.

What’s next

Fin is now a Customer Agent, with multiple roles that work seamlessly across the customer lifecycle.

When a single Agent can guide a shopper from “I need a gift for my partner” to checkout, and handle a return weeks later without losing context, that’s a fundamentally better customer experience. It’s a single Agent that deeply understands your products and your customers, and supports them throughout their entire journey with your business. Leading ecommerce brands, including Avocado, WHOOP, Shutterstock, Flaviar, Carvana, Nuuly, MPB, Pure Electric, and Goodbuy Gear, already trust Fin to create standout experiences for their shoppers.

We’re continuing to expand Fin’s roles as a Customer Agent, and we’ll share more about that soon. In the meantime, go to fin.ai/ecommerce to learn more.

Original source

Our redesigned Data Connector experience brings together everything you need (setup, security, monitoring, versioning, APIs), so you can successfully configure data connectors.

• New configuration flow — The redesigned configuration experience simplifies API setup, data transformation, Fin configuration, and security controls, so you can reliably deliver the right data to Helpdesk and Fin.

• Security enhancements — Ensure every data connector is built secure by default. Your platform-wide authentication rules are applied by default, and potential security risks are surfaced clearly alongside practical recommendations on how to manage them.

• Reporting — Evaluate the impact and health of each data connector. A dedicated dashboard outlines usage, success rate, latency (Intercom vs. external), error types, and more. Monitor trends over time and dive into detailed execution logs to pinpoint opportunities for improvement.

• Versioning — Iterate on your data connectors without breaking workflows. Every change is captured, giving you visibility into when the change happened, who made the change, and why. If an update has unintended consequences, you can roll back in moments.

• Public APIs — Use the new Configuration API to manage data connectors programmatically, so you can rapidly implement changes. Or use the new Results API to pull detailed execution data, so you can build your own dashboards, integrate with your alerting systems, and more.

Learn more

Original source

Admins can now choose a date range when exporting macro usage data — no more being limited to the last 30 days. Pick a preset like "Past 6 months" or select a custom date range to get exactly the data you need for quarterly reviews, adoption analysis, or historical comparisons.

• Choose from presets: Today, Past week, Past 4 weeks, Past 12 weeks, Past 6 months, and more
• Select a custom date range with the calendar picker — dates beyond 6 months are automatically disabled
• Exported CSV is emailed to you, just like before — now with your chosen date range as column headers

Original source

You can now track every change to your Fin Guidance rules with built-in version history. See who changed what and when, add notes to explain why, and restore a previous version if something goes wrong — all without leaving the Guidance editor.

Guidance version history now includes:

• Full version timeline showing each published version with author, timestamp, and live/paused status
• Version notes to document what changed and why, prompted when saving or enabling
• Rollback with one click restore to load any previous version into the editor for review before saving

Channel and audience snapshots are preserved with each version so you can see the full context of past configurations.

Learn more

Original source

At Pioneer, we shared our vision of a single Customer Agent working across the customer lifecycle. Fin for Sales is a big step towards that vision, and brings Fin to the start of the customer journey.

Today, we’re announcing Fin for Sales, a new role for Fin Customer Agent that runs your inbound sales motion end-to-end.

Six months ago at Pioneer, we shared our belief that a single Customer Agent working across the customer lifecycle with shared context, memory, and business goals will deliver superior customer experience. Fin for Sales is a big step towards that vision, and brings Fin to the start of the customer journey. It can now engage prospects, guide them through your funnel, and ensure the best opportunities reach your sales team.

Here’s what’s new:

• Fin engages every prospect instantly: Fin starts the right conversation the moment intent is highest, re-engages prospects before they go cold, and works on every channel, in every language, 24/7.
• Fin runs discovery like your best rep: Fin explains pricing, guides product discovery, handles objections, and personalizes every interaction based on who the prospect is and what they care about.
• Fin qualifies and routes in real time: Using your playbook, Fin collects and enriches data about your prospects, sends qualified leads to your sales team or down self-serve paths, while syncing full context to your CRM. Your team never works the wrong lead.
• Fin closes deals while you sleep: Fin can book meetings, start trials, and guide buyers to the right next step. Early customers are already seeing impressive results, increasing MQLs, growing pipeline and seeing close/win rates of nearly 50% in the first month.

Why we built it

Right now, most online sales experiences look the same. A prospect visits your site, maybe explores your pricing page, and has specific questions about how your product fits their stack. There’s no one from your team there to answer and they don’t want to fill out a form and wait for a response or talk to a generic chatbot.

Fixing this with headcount alone doesn’t scale. Hiring enough reps to cover every time zone, every channel, every hour of the day isn’t realistic. And even when reps are available, a significant share of their time goes to leads that were never going to convert.

Revenue leaders know this is broken. They see high-intent leads come in and know their teams can’t respond fast or consistently enough to capture them. And the tools they rely on, such as incremental automation, don’t solve the underlying problem. What they need is the ability to handle every inbound interaction immediately, without sacrificing quality, and with the confidence that the right opportunities reach their sales team. Until now, that hasn’t been possible.

How it works

Engages prospects at the right moment

When a prospect is actively exploring your site, that’s the moment they’re most likely to buy. Any delay, a form, a queue, a “we’ll get back to you,” and that intent fades. Fin engages them right there, in real time, through the Spotlight Messenger, a new interface built specifically for sales conversations. When a prospect lands on your site, Fin can proactively start a conversation triggered by context like what page they’re on or how they’re browsing. Smart suggestions also give prospects helpful starting points to encourage engagement.

Now, prospects who would have waited for a response, or never started a conversation at all, can get answers immediately. Fin can also work across channels including messenger and email so buyers can engage however they prefer. Whether someone is browsing your pricing page at 2am or comparing features during a lunch break, Fin is there with an immediate, relevant response so no one waits and no lead is ever left behind.

Moves prospects closer to a decision

Fin guides prospects early in their journey, leading personalized discovery conversations that clarify needs and accelerate decision-making. It draws on four core pillars to deliver accurate answers on pricing and features, address objections, and recommend the right plan or offer to give prospects confidence as they move forward.

Playbook: Just as you brief a new sales rep, you brief Fin. Use the Playbook capability to tell Fin what outcomes to drive towards and how to handle different scenarios. You define the rules, in natural language, and Fin follows them. It handles objections using your approved guidance and keeps conversations on track, capturing all the things you care about.

Knowledge: Fin draws from your product knowledge base to give clear, accurate answers on pricing, features, and plan fit. It can compare options and help buyers understand what’s right for them. And if you’ve already trained Fin for customer service, that knowledge is immediately available, no duplicate setup needed.

Enrichment: Once Fin learns something about a user, like their email or name, it can enrich that data with outside sources, giving it a fuller picture of who it’s talking to. That context drives better decisions; Fin can qualify more accurately, personalize the conversation, and route each lead based on who they actually are.

Memory: If Fin recognizes a returning visitor, it remembers the context. The buyer doesn’t have to start over, the conversation picks up where it left off.

Together, these pillars make sure Fin’s conversations are knowledgeable, natural, and relevant.

Surfaces the opportunities most likely to close

As conversations progress, Fin qualifies the way your best SDR does. It asks about use case, budget, fit, and timing, and applies your existing playbook to identify the strongest opportunities for your team. As Fin captures details conversationally and adds context via enrichment, it builds a complete picture of a prospect. This information is then structured and synced directly into your existing CRM, so your sales team can access it.

Equally important is what happens when a lead isn’t a fit. Fin gracefully disqualifies or redirects prospects based on your preferences, to self-serve resources or to a different path entirely. This saves your team time and ensures only the strongest opportunities reach your pipeline.

Closes like your best sales rep

When a lead is ready to act, Fin closes. It books meetings via tools like Chili Piper or Calendly, guides qualified buyers into trials or subscriptions, and routes opportunities to your sales team with full context.

The handoff is where most systems break down: context gets lost and prospects are forced to repeat themselves. Fin solves this by passing along the full conversation history and an AI-generated summary, so sales reps can pick up exactly where the interaction left off. They know what was discussed, what questions were asked, and why the lead was qualified.

For self-serve motions, Fin can guide prospects all the way through, from discovery to trial signup or even paid conversion, without a human ever needing to step in. The right prospects get the right path, automatically.

Real results and revenue

Fin is already delivering measurable results for early customers across different company sizes, sales motions, and go-to-market models.

Attio, an AI CRM built for scaling go-to-market intelligently, deployed Fin to replace their traditional form-and-wait inbound flow with real-time conversational engagement. In three months, Fin handled over 1,600 conversations with website visitors, qualified more than 50 leads for sales, and routed over 30 applicants into their startup program. One returning prospect engaged with Fin, had their questions answered in real time, and converted to a paying customer at six times Attio’s average contract value.

Fellow, an AI-powered meeting assistant and management platform, started by deploying Fin overnight, a window where no human was online and prospects waited up to 18 hours for a reply. In January alone, Fin booked 18 meetings the team would never have reached, converting at around 48%. Critically, Fin didn’t cannibalize existing pipeline, the human team kept booking at the same rate, and Fin added net-new meetings on top.

Built on the Customer Agent platform

Fin for Sales is built on the same AI platform that powers the highest-performing Agent in customer service, so the end-user experience is consistent. If a prospect asks a support question mid-sales conversation, Fin can handle it. So you don’t have to hand off to a different vendor, lose context, and create a disjointed experience. Fin shares knowledge and memory across its platform, always knows whether it’s talking to a prospect or a customer, and moves between roles as needed. It acts as a single Customer Agent that creates one seamless experience across the entire journey.

Setup follows the same Fin Flywheel: Train, Test, Deploy, Analyze. Describe your sales playbook, qualification criteria, and routing rules in natural language; test in preview; deploy live; use Analyze to see exactly how Fin performs and where to improve.

What’s next

Fin for Sales is available today, and there’s much more to come. We believe the future is a single Customer Agent, vertically integrated all the way down to the model layer, and we’re building it.

We’ll share more about what that looks like very soon. In the meantime, go to fin.ai/sales and talk to Fin to experience it for yourself.

Original source

Solving your customers’ most challenging problems is what your support team exists for. With Procedures, Fin can do this too.

Complex queries are a small percentage of your queue, but they consume a disproportionate share of your team’s time.

Take a typical queue: password resets outnumber refund disputes ten to one, but a reset takes five minutes and a dispute takes thirty. The “rare” query accounts for over a third of total handling time. The same pattern holds for account investigations, subscription changes, and billing disputes.

How you handle complex queries is also what customers actually remember about their support experience. When someone is dealing with a damaged order or a billing dispute, the stakes are higher, and a fast, good resolution is what separates a forgettable interaction from one that builds lasting trust.

Most AI Agents automate the easy, informational queries well. The question for your automation rate is whether they can handle the hard ones.

We’ve gotten really good at informational queries – the hard part is what comes next

We’ve invested deeply in informational Q&A. We built Apex, a specialized customer service model trained on billions of support interactions, as Fin’s core answering engine. Beneath that sits a custom retrieval model, a purpose-built reranker, and a unified RAG pipeline, all trained specifically for customer service. Fin resolves issues at a higher rate than general-purpose frontier models, with fewer hallucinations and at lower cost.

But informational Q&A only covers queries where text is the answer. Most Agents can handle that. Far fewer let you configure complex, multi-step actions without a forward-deployed engineer setting it up for you, which creates a gap.

Every query your team handles falls into one of three categories:

Informational: “Can you ship transatlantic by priority next day?” Answered with text from your knowledge base.

Personalized: “Where is my order?” Requires data unique to that user.

Action-led: “My order arrived damaged, I need a refund.” Requires doing something: checking a return window, cross-referencing transaction data, making a judgment call – reading from multiple systems and acting across them.

These complex queries, the ones that require multi-step processes across systems, aren’t edge cases; they’re the reason your support team exists. This is the gap we built Fin Procedures to close.

It works

Procedures is live, it’s scaling, and the results are clear. Since launching in managed availability, Procedures has handled over 1.5 million conversations, and volume is doubling month over month across hundreds of apps in fintech, e-commerce, gaming, healthcare, and SaaS.

Weekly conversations handled by Procedures

When customers hit complex, multi-step queries, the experience is dramatically better when Fin can do the work end-to-end. We tested this with a randomized 5% holdout – conversations where Procedures would normally run, but didn’t. CSAT was 28.93% higher when Procedures ran, a statistically significant result.

A product, not a services engagement

Plenty of vendors will automate complex processes for you. They’ll send a forward-deployed engineer, run workshops, and in six to eight weeks you’ll have a handful of workflows. Then your refund policy changes, and you’re DM’ing the same engineer, hoping they’re still on your account, waiting to make a change you should be able to make yourself.

Fergal wrote about this recently – the B2B AI industry has a consultingware problem. It’s not databases being forked anymore, it’s prompts. The economics of maintaining bespoke setups per customer don’t work. Either the application falls behind new models, or the vendor changes the model and quality degrades invisibly.

We’ve been opinionated from day one that Fin is a product. Procedures gives your team everything they need: a natural language editor – literally paste your existing SOPs – branching logic, data connectors, and AI-powered simulations for testing. Your CX ops team configures this, iterates on it, owns it. We have a great forward-deployed team too, and they’re there if you need help. But they’re optional, not a dependency. You always have control.

And because it’s a unified product, improvement compounds. When we optimize a prompt, every customer’s Procedures get better. When we upgrade the model, we A/B test across the entire customer base and know it’s better before rolling out. You can’t do that when every customer has a bespoke prompt. The consulting model isn’t just expensive, it’s structurally unable to compound.

Today, Fin Procedures is available to all 8,000+ Fin customers – no waitlist or managed rollout.

What we’ve been shipping

We’re iterating fast based on real customer feedback. Here’s what’s landed since we last shared an update:

• AI-powered Procedure review: Flags broken logic, missing references, and unreachable conditions before you deploy.
• Procedure failure reporting: A new reporting dimension that lets you drill into conversations where Procedures failed, so you can diagnose and fix.
• Version history with rollback: Track every change, compare versions, roll back if needed.
• Data connector health monitoring: See at a glance if your integrations are healthy, degraded, or failing.
• Optional data connector parameters: Fin only asks customers for information when it’s actually needed, instead of prompting for every field.
• Email Simulation support: Test how your Procedures behave across chat and email before going live.

Agent in the Loop (Beta)

Even with Procedures, two things hold teams back from automating their most complex queries: missing integrations and policies that require a human sign-off on sensitive decisions.

“Agent in the Loop” is built for both. Need Fin to check your internal admin tools but haven’t built a data connector yet? Put a human checkpoint at that step. Fin handles the conversation, gathers context, and pauses, surfacing a structured summary for a human agent to verify or act, then resumes. You get automation on the 80% that doesn’t need the integration.

For compliance – identity verification, high-value refunds – Fin does the legwork, a human makes the final call and then hands it back to Fin. This works natively in the Intercom Inbox and via Slack. Some competitors don’t have an inbox-native variant at all, meaning humans need to leave their primary workspace to review AI actions.

Procedures are also built to let you collaborate with all your teammates – both human agents and AI Agents. Fin can work with them directly inside a Procedure, using APIs and webhooks to loop in another teammate mid-flow, hand off context, and pick back up once they’re done.

Making it easier, faster

Procedures is already self-serve, but we’re not stopping there. The next step is making Procedure creation, testing, and maintenance significantly more streamlined and easy to do, with less manual editing and more AI-assisted building and debugging. There’s a lot coming in this space over the next few months that we’re genuinely excited about.

The hardest percentages matter the most

The biggest unlock for your automation rate won’t be answering more FAQs, it will be handling the complex, multi-step queries that consume your team’s time and define what customers remember about their experience with you.

That means working with an Agent that goes beyond answering questions and executes processes. A product your team owns and configures, not a service you buy and hope gets maintained. And a platform where every improvement compounds across every customer.

That’s Procedures. Available now, for everyone.

Get started here.

Get started with the #1 Agent today. Start a free trial.

Original source

The news

Last week, we announced Apex, the world’s first specialized customer service LLM. We’re now going to allow you to access all of this power and all of our core models directly via API.

Today we’re announcing the launch of the Fin API platform.

Our best-in-class vertical customer service models that power Fin are now available for you to mix and match and deploy at insane scale to create the perfect customer agent for you. In this post, I’ll explain exactly what we are announcing, why we’re doing so, and how I think we’re going to see a lot more of this in the industry at large.

Fin is a customer agent platform that at present resolves over 2M customer issues a week, growing at a rapid exponential pace. It’s relied on by the best brands, large and small, in every vertical you can imagine. From Doordash and Riot Games, to smaller hot upstarts like Mercury and Polymarket. It runs on a family of models trained by our AI group. Last week, we announced Apex, which is the world’s first specialized customer service LLM. In production tests over the last 6 months, it beat every single frontier model, including those from Anthropic and OpenAI, on resolution rate, latency, hallucination rate, and cost.

We’re now going to allow you to access all of this power and all of our core models directly via API, with contracts starting at $250k per year, and usage rates that are by far the cheapest in the industry for each of the model’s subcategories.

But why?

It’s simply that our customers want it. We hear from people far and wide who want to build their own agents. So starting today we’re providing three ways to do so.

First, for the vast majority of companies, they will want to run their operations on the Fin Agent Platform. We have ~8k companies on it today. This takes care of the needs of 99% of customers and allows them to configure it easily without the exhausting consulting engagements of our startup competitors. It delivers the very best resolution rates in the industry, but straight out of the box.

Second, we have also had an offering for people who want to present Fin in a unique context. For this they can use the Fin Agent API. In this mode, you get all of the magic of the Fin platform, but you don’t have to use our messenger (or our email or voice or other prebuilt channel) and can display the agent in bespoke ways.

But there are also companies out there who want to build hyper-specific and specialized agents for their business. Perhaps they want to build an agent that does service and is also a product agent that lets users interact with their product. In this world, the best and most obvious decision for them is to use Apex and the collection of models we use in the broader system, because they’re trained for exactly that purpose—unlike the generalized models. This is our third and new offering launching today.

We’re also excited to see new startups build Fin-like businesses that cater to hyper-specific verticals too. Fin for dentists? Why not? Fin for car dealerships? Sure. We’re never going to build for these specific verticals, but we’d love someone else to. In fact, if any of our direct startup competitors would like to substantially improve their offering and give us a little cut of the action, we’ll be more than happy to license our models to them too. Decagon, Sierra, and the rest, you know where to reach me. Let’s be friends! :)

Coming soon to an agent company near you; the defensive reason

Unlike many, I’m not 100% ready to write off all of software. But it’s true to say that the software landscape is certainly about to change dramatically before our eyes. In extremely recent times, differentiation came from software functionality that acted as a moat because it was hard to build. But building software is simply less hard now.

We’ve already managed to more than double our measurable productivity on our engineering team. We’ve also created insanely deep new products that previously existed as separate businesses, built by single Intercom engineers, in literally one week.

Going forward, the differentiation that came from features and interface is, at the very least, going to diminish. Serious software companies must not only move from being a features company to an agents company, because the work they used to assist with that was done by humans will now be done by agents, but they must also be building those agents on differentiated AI. We do believe that more and more value will accrue to the model layer, and so, as we did when we started to disrupt our software business with our agent business, we will now begin the processes of disrupting our agent business with our AI business.

Where this all ends is anyone’s guess, but it’s hard to not imagine we’ll see this with many other companies too. For now, we’re excited to be out there first and best with this new platform and business and we can’t wait to see what people build.

Original source