Announcing major updates to Procedures and Simulations: Enabling Fin to handle complex queries

See the latest updates to Procedures and Simulations, the foundation of how Fin handles complex work.

AI & Automation

Published
Feb 25, 2026

Announcing major updates to Procedures and Simulations: Enabling Fin to handle complex queries

See the latest updates to Procedures and Simulations, the foundation of how Fin handles complex work.

Chris Dalley

8 min

Today, we’re announcing 12 big updates to Fin’s Procedures and Simulations capabilities; the foundation of how Fin handles complex work, and how teams stay in control of the customer experience.

Procedures make it easy to combine three things – natural language instructions, deterministic controls, and fully agentic behavior – to enable Fin to handle the most complex queries. Simulations allow teams to test complex Procedures at scale before they reach customers, so they can deploy with confidence.

Together, they make Fin self-manageable, transparent, and capable of handling genuinely complex work.

Here’s what’s new:

• We’ve made Procedures easier to build and maintain: Draft Procedures with AI by simply outlining your process in natural language, break complex workflows into reusable Sub-procedures, improve instruction authoring, and track when Procedures trigger, resolve, or hand off, all natively within the Procedures UI.

• Improved deterministic controls: Follow explicit rules to switch Procedures under defined conditions, instruct Fin to read specific content in certain scenarios, and include internal notes for smoother human handoffs.

• Improved agentic behaviour: Fin can automatically switch Procedures when intent changes and extract structured data directly from uploaded PDFs and images, so customers don’t have to repeat themselves.

• More powerful Simulations: Generate AI-suggested Simulations from your Procedures, upload images for richer testing, and gain clearer visibility into Fin’s reasoning so you can deploy complex Procedures with confidence.

[See the latest Procedures and Simulations updates. Watch now.]

Why we built this

Teams that see early AI gains in speed, coverage, and cost to serve often hit a ceiling. They restrict AI to simple automation and information retrieval instead of setting it up to handle the kind of complex work that teams reflexively entrust to humans.

They hit that ceiling because they feel they’re not ready to set AI Agents up to tackle greater complexity, and manage them once it is running. We built Procedures and Simulations to make that setup and ongoing management far easier.

We heard from customers that:

• They needed to be easily able to connect data to let Fin reliably and safely check customer status or eligibility and then take action.

• They didn’t want to route through engineering teams to create or amend logic for their AI Agents to make mid-conversation decisions.

Procedures combines natural language instructions and intuitive data connector setups. You tell Fin in your own words how you want it to behave, and you’ll be guided through creating conditional steps so Fin will react consistently, with the option to add in any code snippets for circumstances where absolute precision is required. Once you build one Procedure, we believe you’ll want to build several, so Fin will constantly read the conversation it’s in to ensure it’s following the most relevant Procedure, and jump to a more relevant one if the user intent changes.

We know that the moment you set something like this live for the first time is a leap of faith, so we built in Simulations to allow you to test your Procedures, find edge cases, and be ready for launch with maximum confidence.

Reaching mature deployment takes a deliberate, ongoing commitment to training workflows, validating them before deployment, measuring performance in production, and refining them over time. At Intercom, we call this the Fin Flywheel: train, test, deploy, analyze. Procedures form the foundation of the train stage, and Simulations make the test stage reliable at scale. Together, they enable Fin to handle complex work, and teams to stay in control of it.

[The Fin Flywheel: Train, Test, Deploy, Analyze.]

Procedures: Define exactly how Fin handles complex work

Procedures enable you to set Fin up to resolve your complex, time-consuming queries that require multiple steps or business logic. You can train Fin to follow your standard operating procedures carefully and exercise experience and judgment, just like your human team would, so it can handle even your most complicated queries in a controllable, predictable way.

Procedures does this by combining three powerful things:

1. Natural language instructions

You write a Procedure in plain language, just like documenting a process for a new teammate. You can paste in your existing SOPs, write from scratch, or let AI draft them for you, then iterate yourself.

[Create a Procedure using natural language.]

What’s new 

Draft Procedures with AI

Share an outline of your process and Fin drafts a complete Procedure using your conversation history, knowledge hub content, and relevant data. If additional context is needed, it prompts you with clarifying questions to make sure the Procedure is thorough and tailored to your use case, significantly reducing setup time.

For example: if you’re creating a refund workflow, the system can draft conditional paths for eligibility, approval thresholds, and verification steps based on your historical cases and policies.

Break complex workflows into Sub-procedures

Write a process once and reference it across multiple Procedures by breaking it down into reusable steps, called Sub-procedures. This makes workflows easier to read, faster to build, and simpler to maintain as things change.

2. Deterministic controls

Natural language is flexible, but some steps need to be exact. You can layer in deterministic controls where precision matters, starting with a fully natural language Procedure and introducing structure gradually where it adds value:

• Conditional steps (branching logic) to handle decision points – for example, whether a refund should be approved – so Fin’s behavior is consistent and predictable.

• Data connectors so Fin can pull information from your tools or take actions automatically.

• Code snippets for when absolute accuracy is essential and you need to guarantee that the same inputs always produce the same outputs.

• Checkpoints to pause for approval or hand off to a teammate.

[Layer in deterministic controls where precision matters.]

What’s new 

****Instruct Fin to read specific content from your knowledge hub** **

You can set clear rules for Fin to reference a specific policy or article from your knowledge hub in defined situations so Fin always surfaces the right context in a conversation.

****Explicit Procedure switching under defined conditions****

You can set rules that deterministically trigger a switch to a different Procedure, for example, escalating to a complaints Procedure if specific risk signals are detected mid-conversation.

****Internal notes for human handoffs** **

When Fin hands off to a teammate, it can now include internal notes with relevant context so the person picking up the conversation knows exactly what happened and what needs to happen next.

3. Fully agentic behavior

Because real conversations rarely follow the “happy path,” Procedures are designed to let Fin reason through what’s happening and adapt – jumping to the right step, or switching Procedures entirely if a customer changes their mind or the issue turns out to be about something different.

What’s new 

****Automatic Procedure switching****

If a customer starts in a billing workflow but then asks about cancelling their subscription, Fin transitions to the relevant Procedure without forcing the customer to restart.

[...]

Original source