---
title: "From swarms to product: Turning customer signals into scalable features"
description: "Intercom’s Fin teams use cross-functional swarms to identify customer needs while helping customers increase automation and understand the product. In these high-touch engagements, engineers, data scientists, and a product manager analyze conversations, APIs, Procedures, and workflows, using fast feedback to test configuration changes and estimate achievable automation; one manual taxonomy analysis took more than half a day and predicted a 70% rate that the customer achieved. Cockpit then encodes swarm patterns into repeatable workflows, letting customer success managers and Sales assess automation potential, diagnose issues, and suggest next actions across accounts without repeated data-science involvement. It also tests whether ideas generalize before product development. Patterns that prove broadly useful, robust, and scalable can move into product features such as the automation taxonomy in Insights and CX Score, which measures conversation quality; unlike Cockpit, product features must work for every customer without configuration."
---

# From swarms to product: Turning customer signals into scalable features

[Intercom](https://yomu.fyi/company/intercom) · Kevin O'Brien · Apr 13, 2026

**Type:** Explainer

## Summary

Intercom’s Fin teams use cross-functional swarms to identify customer needs while helping customers increase automation and understand the product. In these high-touch engagements, engineers, data scientists, and a product manager analyze conversations, APIs, Procedures, and workflows, using fast feedback to test configuration changes and estimate achievable automation; one manual taxonomy analysis took more than half a day and predicted a 70% rate that the customer achieved. Cockpit then encodes swarm patterns into repeatable workflows, letting customer success managers and Sales assess automation potential, diagnose issues, and suggest next actions across accounts without repeated data-science involvement. It also tests whether ideas generalize before product development. Patterns that prove broadly useful, robust, and scalable can move into product features such as the automation taxonomy in Insights and CX Score, which measures conversation quality; unlike Cockpit, product features must work for every customer without configuration.

## Context

Swarm work provides deep customer insight and rapid feedback but is inherently hands-on and difficult to scale. The stated challenge is turning high-touch learnings into systems, tools, and product changes that benefit more customers.

## Approach / What changed

The model moves validated learnings through three levels: swarms generate customer-grounded signals, Cockpit makes analyses repeatable for CSMs and Sales, and product incorporates patterns that generalize broadly, robustly, and at scale.

## Takeaways

- An automation taxonomy initially required more than half a day of manual preparation and visualization, but accurately predicted one customer’s 70% automation rate.
- Cockpit turns swarm analyses into reusable workflows so CSMs and Sales can assess customer automation potential and recommend next actions without direct data-science involvement each time.
- Moving an analysis from Cockpit into product requires it to work for every customer without configuration, making broad usefulness, robustness, and scalability explicit criteria.

**Tags:** [Automation](https://yomu.fyi/topic/automation), [Customer Experience](https://yomu.fyi/topic/customer-experience)

- Source: [Intercom](https://www.intercom.com/blog/from-swarms-to-product-turning-customer-signals-into-scalable-features)
- Source URL: https://www.intercom.com/blog/from-swarms-to-product-turning-customer-signals-into-scalable-features
- Ingested by Yomu: 2026-09-09T08:22:06.599Z

[Read original post](https://www.intercom.com/blog/from-swarms-to-product-turning-customer-signals-into-scalable-features)