# Intercom

Articles and Podcasts on Customer Service, AI and Automation, Product, and more

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Announcing Workforce Management: Forecast, schedule, and plan teammate cover in the Intercom helpdesk

DevFeed: [Announcing Workforce Management: Forecast, schedule, and plan teammate cover in the Intercom helpdesk](<https://devfeed.tech/articles/announcing-workforce-management-forecast-schedule-and-plan-teammate-cover-in-the-intercom-helpdesk-88794.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/announcing-workforce-management>)

Author: Andrea Nagel

Published: 2026-10-16T22:36:29.565778Z

Content type: release

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [Support](<https://devfeed.tech/topics/support.md>)

Tags: [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [capacity-planning](<https://devfeed.tech/tags/capacity-planning.md>), [google-calendar](<https://devfeed.tech/tags/google-calendar.md>), [intercom](<https://devfeed.tech/tags/intercom.md>), [intercom-helpdesk](<https://devfeed.tech/tags/intercom-helpdesk.md>), [news-updates](<https://devfeed.tech/tags/news-updates.md>), [workforce-management](<https://devfeed.tech/tags/workforce-management.md>)

### AI overview

Intercom announced Workforce Management tools for support teams working alongside Fin. Forecasts exclude conversations resolved by Fin to estimate human staffing needs. The tools also provide scheduling with Google Calendar synchronization, hourly coverage comparisons, and performance tracking based on activity in Intercom. Workforce Management is available in the Pro add-on.

### Source excerpt

With Fin resolving a growing share of your support volume, you need a new way to plan for the work that lands with your team. Workforce Management helps you forecast the right capacity, schedule people's time, and ensure you have enough cover.

## Introducing Fin 4: Customer Agent, Operator, and major upgrades to the Intercom helpdesk

DevFeed: [Introducing Fin 4: Customer Agent, Operator, and major upgrades to the Intercom helpdesk](<https://devfeed.tech/articles/introducing-fin-4-customer-agent-operator-and-major-upgrades-to-the-intercom-helpdesk-91172.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/fin-4-customer-agent-operator-and-major-upgrades-to-the-intercom-helpdesk>)

Author: The Fin Team

Published: 2026-10-07T00:00:00Z

Content type: release

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>), [Support](<https://devfeed.tech/topics/support.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [customer-experience](<https://devfeed.tech/tags/customer-experience.md>), [fin](<https://devfeed.tech/tags/fin.md>), [fin-4](<https://devfeed.tech/tags/fin-4.md>), [fin-ai-copilot](<https://devfeed.tech/tags/fin-ai-copilot.md>), [helpdesk](<https://devfeed.tech/tags/helpdesk.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [intercom](<https://devfeed.tech/tags/intercom.md>), [news-updates](<https://devfeed.tech/tags/news-updates.md>), [operator](<https://devfeed.tech/tags/operator.md>), [pioneer](<https://devfeed.tech/tags/pioneer.md>), [upgrades](<https://devfeed.tech/tags/upgrades.md>)

### AI overview

Fin 4 adds capabilities across Intercom's customer support system: Customer Agent uses Skills to solve problems without every step being predefined; Operator uses Routines and Connections for proactive, autonomous operations; and Apex 2.0, Apex Flash 2.0, and Apex for Procedures target resolution performance, speed, accuracy, and complex multi-step queries. The helpdesk updates shift human reps toward supervising Fin: Human in the Loop lets them review, edit, approve, or take over conversations, while the rebuilt Copilot searches connected tools, summarizes issues, drafts replies, and recommends actions when a rep opens a conversation. These features work inside Intercom and are also said to integrate with other helpdesks. The article presents a future in which an Operations Agent manages and optimizes a Customer Agent, with human teams setting strategy; its 90-95% automation figure is a stated vision, not a reported result.

### Source excerpt

At Pioneer 2026, we announced Fin 4, a major step toward a fully agentic customer experience.

## Announcing the 2026 AI Sentiment Report: How end users feel about AI Agents

DevFeed: [Announcing the 2026 AI Sentiment Report: How end users feel about AI Agents](<https://devfeed.tech/articles/announcing-the-2026-ai-sentiment-report-how-end-users-feel-about-ai-agents-9351.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/the-2026-ai-sentiment-report/>)

Author: Maia Bridi

Published: 2026-09-09T16:44:02Z

Content type: article

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai-sentiment](<https://devfeed.tech/tags/ai-sentiment.md>), [customer-service](<https://devfeed.tech/tags/customer-service.md>), [end-user-sentiment](<https://devfeed.tech/tags/end-user-sentiment.md>), [news-updates](<https://devfeed.tech/tags/news-updates.md>)

### AI overview

A research report on end-user sentiment and conditional trust in AI Agents, especially for customer-service queries.

### Source excerpt

We asked over 1,000 end users how they felt about interacting with AI Agents, how capable they think they are, and how much they trust them. Here are our findings.

## Announcing the 2026 AI Sentiment Report: How end users feel about AI Agents

DevFeed: [Announcing the 2026 AI Sentiment Report: How end users feel about AI Agents](<https://devfeed.tech/articles/announcing-the-2026-ai-sentiment-report-how-end-users-feel-about-ai-agents-65060.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/the-2026-ai-sentiment-report>)

Author: Maia Bridi

Published: 2026-09-09T00:00:00Z

Content type: article

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>), [AI interaction best practices](<https://devfeed.tech/topics/ai-interaction-best-practices.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-sentiment](<https://devfeed.tech/tags/ai-sentiment.md>), [end-user-sentiment](<https://devfeed.tech/tags/end-user-sentiment.md>), [news-updates](<https://devfeed.tech/tags/news-updates.md>), [report](<https://devfeed.tech/tags/report.md>), [trust](<https://devfeed.tech/tags/trust.md>), [users](<https://devfeed.tech/tags/users.md>)

### AI overview

Intercom reports survey findings on how end users feel about AI agents, including rising positive sentiment and trust that remains conditional. Respondents are more willing to trust AI with routine support than complex issues, and value human escalation, clear disclosure, and accountability. Trust also varies by interaction channel, while AI shopping raises concerns about whether recommendations serve users or business interests.

### Source excerpt

We asked over 1,000 end users how they felt about interacting with AI Agents, how capable they think they are, and how much they trust them. Here are our findings.

## Announcing Evals and Releases: Evaluate Fin before, during, and after you go live

DevFeed: [Announcing Evals and Releases: Evaluate Fin before, during, and after you go live](<https://devfeed.tech/articles/announcing-evals-and-releases-evaluate-fin-before-during-and-after-you-go-live-9342.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/announcing-evals-and-releases/>)

Author: Brian Donohue

Published: 2026-08-13T17:33:52Z

Content type: article

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [AI Research](<https://devfeed.tech/topics/ai-research.md>), [configuration](<https://devfeed.tech/topics/configuration.md>), [releases](<https://devfeed.tech/topics/releases.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-research](<https://devfeed.tech/tags/ai-research.md>), [evals](<https://devfeed.tech/tags/evals.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [news-updates](<https://devfeed.tech/tags/news-updates.md>), [release](<https://devfeed.tech/tags/release.md>), [releases](<https://devfeed.tech/tags/releases.md>)

### AI overview

Intercom announces Evals and Releases for Fin, paired with Monitors as an eval-driven delivery system. Teams can test Fin with simulated customer conversations, evaluate changes against defined criteria, safely release updates, and monitor live conversations for regressions.

### Source excerpt

Providing a complete evaluation system for Fin, you can now test changes before they go live, roll them out with control, evaluate every live conversation, and have confidence in the experience Fin delivers.

## Announcing Evals and Releases: Evaluate Fin before, during, and after you go live

DevFeed: [Announcing Evals and Releases: Evaluate Fin before, during, and after you go live](<https://devfeed.tech/articles/announcing-evals-and-releases-evaluate-fin-before-during-and-after-you-go-live-65043.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/announcing-evals-and-releases>)

Author: Brian Donohue

Published: 2026-08-13T00:00:00Z

Content type: release

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>), [human feedback](<https://devfeed.tech/topics/human-feedback.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-research](<https://devfeed.tech/tags/ai-research.md>), [cx](<https://devfeed.tech/tags/cx.md>), [data](<https://devfeed.tech/tags/data.md>), [evals](<https://devfeed.tech/tags/evals.md>), [news-updates](<https://devfeed.tech/tags/news-updates.md>), [releases](<https://devfeed.tech/tags/releases.md>)

### AI overview

Intercom announces Evals and Releases for Fin, its AI customer support agent. Evals run simulated conversations against defined criteria to assess behavior and catch regressions; Releases let teams prepare, test, and roll out changes with options such as gradual rollout, A/B testing, and rollback. Monitors assess live conversations and can feed issues into future tests. The announcement describes this as an integrated workflow for managing AI product quality without requiring a developer or ML specialist.

### Source excerpt

Providing a complete evaluation system for Fin, you can now test changes before they go live, roll them out with control, evaluate every live conversation, and have confidence in the experience Fin delivers.

## The 9 best tools for your early-stage startup tech stack in 2026

DevFeed: [The 9 best tools for your early-stage startup tech stack in 2026](<https://devfeed.tech/articles/the-9-best-tools-for-your-early-stage-startup-tech-stack-in-2026-9345.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/early-stage-startup-tech-stack/>)

Author: Alan McGlinchey

Published: 2026-08-04T08:00:51Z

Content type: article

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [Software](<https://devfeed.tech/topics/software.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [migration](<https://devfeed.tech/topics/migration.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [systems](<https://devfeed.tech/topics/systems.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [aws](<https://devfeed.tech/tags/aws.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [customer-engagement](<https://devfeed.tech/tags/customer-engagement.md>), [fin](<https://devfeed.tech/tags/fin.md>), [growth](<https://devfeed.tech/tags/growth.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [hubspot](<https://devfeed.tech/tags/hubspot.md>), [integrations](<https://devfeed.tech/tags/integrations.md>), [migration](<https://devfeed.tech/tags/migration.md>), [partner](<https://devfeed.tech/tags/partner.md>), [pricing](<https://devfeed.tech/tags/pricing.md>), [startup](<https://devfeed.tech/tags/startup.md>), [startup-advice](<https://devfeed.tech/tags/startup-advice.md>), [startups](<https://devfeed.tech/tags/startups.md>), [stripe](<https://devfeed.tech/tags/stripe.md>), [tech](<https://devfeed.tech/tags/tech.md>), [tech-stack](<https://devfeed.tech/tags/tech-stack.md>), [technology-stack](<https://devfeed.tech/tags/technology-stack.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

A guide to choosing a foundational technology stack for early-stage startups, emphasizing scalable, AI-powered tools, manageable costs, integrations, and problem-focused selection.

### Source excerpt

Learn how to create a foundational tech stack for your high growth and early-stage startup - starting with these top tools.

## The 9 best tools for your early-stage startup tech stack in 2026

DevFeed: [The 9 best tools for your early-stage startup tech stack in 2026](<https://devfeed.tech/articles/the-9-best-tools-for-your-early-stage-startup-tech-stack-in-2026-65046.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/early-stage-startup-tech-stack>)

Author: Alan McGlinchey

Published: 2026-08-04T00:00:00Z

Content type: article

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [issue tracking](<https://devfeed.tech/topics/issue-tracking.md>), [Slack](<https://devfeed.tech/topics/slack.md>)

Tags: [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [aws](<https://devfeed.tech/tags/aws.md>), [customer-engagement](<https://devfeed.tech/tags/customer-engagement.md>), [early-stage](<https://devfeed.tech/tags/early-stage.md>), [growth](<https://devfeed.tech/tags/growth.md>), [hubspot](<https://devfeed.tech/tags/hubspot.md>), [partner](<https://devfeed.tech/tags/partner.md>), [startup](<https://devfeed.tech/tags/startup.md>), [startup-advice](<https://devfeed.tech/tags/startup-advice.md>), [startups](<https://devfeed.tech/tags/startups.md>), [stripe](<https://devfeed.tech/tags/stripe.md>), [tech-stack](<https://devfeed.tech/tags/tech-stack.md>), [technology-stack](<https://devfeed.tech/tags/technology-stack.md>)

### AI overview

A guide to selecting tools for an early-stage startup tech stack, with advice to favor tools that scale, integrate well, and solve a clear problem. It reviews options for payments, team communication, AI meeting notes, customer support, issue tracking, observability, databases, HR and IT, and sales. The article also promotes an early-stage program offering partner credits and discounts.

### Source excerpt

Learn how to create a foundational tech stack for your high growth and early-stage startup - starting with these top tools.

## Doing the right thing when things go wrong

DevFeed: [Doing the right thing when things go wrong](<https://devfeed.tech/articles/doing-the-right-thing-when-things-go-wrong-9344.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/doing-the-right-thing-when-things-go-wrong/>)

Author: Mark Gorman

Published: 2026-07-14T13:41:39Z

Content type: article

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [incident](<https://devfeed.tech/topics/incident.md>), [incident management](<https://devfeed.tech/topics/incident-management.md>), [site-reliability-engineering](<https://devfeed.tech/topics/site-reliability-engineering.md>), [Slack](<https://devfeed.tech/topics/slack.md>)

Tags: [engineering](<https://devfeed.tech/tags/engineering.md>), [incident](<https://devfeed.tech/tags/incident.md>), [incident-management](<https://devfeed.tech/tags/incident-management.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [safety](<https://devfeed.tech/tags/safety.md>), [slack](<https://devfeed.tech/tags/slack.md>), [sre](<https://devfeed.tech/tags/sre.md>), [support](<https://devfeed.tech/tags/support.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

Fin's incident-response process focuses on quickly detecting customer-impacting disruptions, bringing the right people together, reducing impact, communicating clearly, and learning from what happened. The article emphasizes that incident management is a shared discipline supported by tools such as Slack channels, status pages, runbooks, and SRE tooling.

### Source excerpt

When customers rely on you, minutes matter in an incident. Here's the process Fin's engineers follow to detect, mitigate, and learn from every one.

## How Fin's engineers detect, mitigate, and learn from production incidents

DevFeed: [How Fin's engineers detect, mitigate, and learn from production incidents](<https://devfeed.tech/articles/doing-the-right-thing-when-things-go-wrong-65045.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/doing-the-right-thing-when-things-go-wrong>)

Author: Mark Gorman

Published: 2026-07-14T00:00:00Z

Content type: article

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [Resilience](<https://devfeed.tech/topics/resilience.md>), [alert triage](<https://devfeed.tech/topics/alert-triage.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [Post Mortem](<https://devfeed.tech/topics/post-mortem.md>)

Tags: [communication](<https://devfeed.tech/tags/communication.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [fin](<https://devfeed.tech/tags/fin.md>), [incident](<https://devfeed.tech/tags/incident.md>), [safety](<https://devfeed.tech/tags/safety.md>)

### AI overview

Fin describes its engineering incident response process, from customer reports and product health monitoring through triage, investigation, mitigation, and learning. Clear ownership, coordinated communication, and fast rollbacks help reduce customer impact. Incident reviews and specific follow-up actions aim to prevent recurrence and improve future responses.

### Source excerpt

When customers rely on you, minutes matter in an incident. Here's the process Fin's engineers follow to detect, mitigate, and learn from every one.

## How to measure the customer experience as AI scales

DevFeed: [How to measure the customer experience as AI scales](<https://devfeed.tech/articles/how-to-measure-the-customer-experience-as-ai-scales-9348.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/how-to-measure-customer-experience-as-ai-scales/>)

Author: William Lane

Published: 2026-07-01T16:44:49Z

Content type: article

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [data](<https://devfeed.tech/topics/data.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-blueprint](<https://devfeed.tech/tags/ai-agent-blueprint.md>), [ai-automation](<https://devfeed.tech/tags/ai-automation.md>), [customer](<https://devfeed.tech/tags/customer.md>), [customer-service](<https://devfeed.tech/tags/customer-service.md>), [data](<https://devfeed.tech/tags/data.md>), [metrics](<https://devfeed.tech/tags/metrics.md>)

### AI overview

The article explains why CSAT becomes insufficient as AI handles more customer conversations. It recommends evaluating every interaction with AI-powered scoring to provide broader visibility into service quality, resolution, and customer effort.

### Source excerpt

Traditional support metrics weren't designed for AI handling most of your conversations. As your Agent takes on more, the gaps in what you can see get bigger. Here's how to measure the full customer experience.

## How to measure the customer experience as AI scales

DevFeed: [How to measure the customer experience as AI scales](<https://devfeed.tech/articles/how-to-measure-the-customer-experience-as-ai-scales-65050.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/how-to-measure-customer-experience-as-ai-scales>)

Author: William Lane

Published: 2026-07-01T00:00:00Z

Content type: article

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>), [Factuality scoring in AI](<https://devfeed.tech/topics/factuality-scoring-in-ai.md>), [Business, Industry, Usability, User Experience, User Research, Web Strategy](<https://devfeed.tech/topics/business-industry-usability-user-experience-user-research-web-strategy.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-blueprint](<https://devfeed.tech/tags/ai-agent-blueprint.md>), [ai-automation](<https://devfeed.tech/tags/ai-automation.md>), [customer-experience](<https://devfeed.tech/tags/customer-experience.md>), [customer-service](<https://devfeed.tech/tags/customer-service.md>), [human-review](<https://devfeed.tech/tags/human-review.md>), [metrics](<https://devfeed.tech/tags/metrics.md>)

### AI overview

The article argues that customer satisfaction surveys capture only a small, potentially unrepresentative share of support conversations as AI handles more interactions. It describes scoring every AI and human conversation with Intercom's CX Score, setting targets based on observed performance, and using score patterns to identify and address problems across support, product, and workflows.

### Source excerpt

Traditional support metrics weren't designed for AI handling most of your conversations. As your Agent takes on more, the gaps in what you can see get bigger. Here's how to measure the full customer experience.

## The new product introduction process: How to make sure your Agent is ready every time you ship

DevFeed: [The new product introduction process: How to make sure your Agent is ready every time you ship](<https://devfeed.tech/articles/the-new-product-introduction-process-how-to-make-sure-your-agent-is-ready-every-time-you-ship-9349.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/npi-how-to-ensure-your-agent-is-ready-every-time-you-ship/>)

Author: Sean Reid

Published: 2026-06-26T17:40:52Z

Content type: tutorial

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Support](<https://devfeed.tech/topics/support.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [customer-service](<https://devfeed.tech/tags/customer-service.md>), [features](<https://devfeed.tech/tags/features.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [npi](<https://devfeed.tech/tags/npi.md>), [support](<https://devfeed.tech/tags/support.md>)

### AI overview

The article explains Fin's new product introduction process for keeping an AI Agent's knowledge base current with product releases. It recommends involving support early, preparing and reviewing content, removing outdated information, and testing the Agent before launch.

### Source excerpt

Every time you launch a product, your Agent's knowledge base needs to keep pace. Here's the NPI process Fin uses to make Agent readiness part of every release.

## The new product introduction process: How to make sure your Agent is ready every time you ship

DevFeed: [The new product introduction process: How to make sure your Agent is ready every time you ship](<https://devfeed.tech/articles/the-new-product-introduction-process-how-to-make-sure-your-agent-is-ready-every-time-you-ship-65053.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/npi-how-to-ensure-your-agent-is-ready-every-time-you-ship>)

Author: Sean Reid

Published: 2026-06-26T00:00:00Z

Content type: tutorial

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [Product Management](<https://devfeed.tech/topics/product-management.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [human review](<https://devfeed.tech/topics/human-review.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [customer-service](<https://devfeed.tech/tags/customer-service.md>), [npi](<https://devfeed.tech/tags/npi.md>), [product](<https://devfeed.tech/tags/product.md>)

### AI overview

The article describes Intercom Fin's new product introduction process for keeping an AI support agent's knowledge current with product releases. It recommends involving support early, preparing and reviewing knowledge content, testing likely customer questions before launch, and monitoring resolution and satisfaction metrics afterward.

### Source excerpt

Every time you launch a product, your Agent's knowledge base needs to keep pace. Here's the NPI process Fin uses to make Agent readiness part of every release.

## Conversation design: How to make your AI Agent communicate like your team

DevFeed: [Conversation design: How to make your AI Agent communicate like your team](<https://devfeed.tech/articles/conversation-design-how-to-make-your-ai-agent-communicate-like-your-team-9343.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/conversation-design-for-your-ai-agent/>)

Author: Fred Walton

Published: 2026-06-18T16:55:07Z

Content type: article

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Support](<https://devfeed.tech/topics/support.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-blueprint](<https://devfeed.tech/tags/ai-agent-blueprint.md>), [ai-automation](<https://devfeed.tech/tags/ai-automation.md>), [communication](<https://devfeed.tech/tags/communication.md>), [context](<https://devfeed.tech/tags/context.md>), [customer](<https://devfeed.tech/tags/customer.md>), [customer-experience](<https://devfeed.tech/tags/customer-experience.md>), [customer-service](<https://devfeed.tech/tags/customer-service.md>), [customers](<https://devfeed.tech/tags/customers.md>), [designer](<https://devfeed.tech/tags/designer.md>), [experience](<https://devfeed.tech/tags/experience.md>), [process](<https://devfeed.tech/tags/process.md>), [responses](<https://devfeed.tech/tags/responses.md>), [structure](<https://devfeed.tech/tags/structure.md>), [support](<https://devfeed.tech/tags/support.md>), [teams](<https://devfeed.tech/tags/teams.md>), [trust](<https://devfeed.tech/tags/trust.md>), [voice](<https://devfeed.tech/tags/voice.md>)

### AI overview

This article explains how conversation design helps an AI Agent communicate consistently with a support team. It covers voice, tone, response structure, adapting language to customer context, and designing smooth handoffs to human support representatives. An Intercom example reports that a warmer opening message increased CSAT from 72.8% to 78.4%.

### Source excerpt

If nobody on your team owns how your AI Agent communicates, it defaults to sounding like an LLM. Conversation design is the discipline that fixes that.

## Conversation design: How to make your AI Agent communicate like your team

DevFeed: [Conversation design: How to make your AI Agent communicate like your team](<https://devfeed.tech/articles/conversation-design-how-to-make-your-ai-agent-communicate-like-your-team-65044.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/conversation-design-for-your-ai-agent>)

Author: Fred Walton

Published: 2026-06-18T00:00:00Z

Content type: tutorial

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [AI interaction best practices](<https://devfeed.tech/topics/ai-interaction-best-practices.md>), [AI chatbot continuity](<https://devfeed.tech/topics/ai-chatbot-continuity.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [human centric design](<https://devfeed.tech/topics/human-centric-design.md>)

Tags: [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-blueprint](<https://devfeed.tech/tags/ai-agent-blueprint.md>), [ai-automation](<https://devfeed.tech/tags/ai-automation.md>), [customer-experience](<https://devfeed.tech/tags/customer-experience.md>), [customer-service](<https://devfeed.tech/tags/customer-service.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [llm](<https://devfeed.tech/tags/llm.md>)

### AI overview

The article explains conversation design for customer-facing AI agents, including how to set voice and response detail, manage handoffs and follow-ups, handle changes in customer intent, and keep agent instructions focused. It recommends assigning an owner and improving weak conversation types, and reports that a warmer opening message raised Fin's CSAT from 72.8% to 78.4% in an A/B test.

### Source excerpt

If nobody on your team owns how your AI Agent communicates, it defaults to sounding like an LLM. Conversation design is the discipline that fixes that.

## Salesforce signs definitive agreement to acquire Fin

DevFeed: [Salesforce signs definitive agreement to acquire Fin](<https://devfeed.tech/articles/salesforce-signs-definitive-agreement-to-acquire-fin-9350.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/salesforce-signs-definitive-agreement-to-acquire-fin/>)

Author: Eoghan McCabe

Published: 2026-06-15T12:33:30Z

Content type: release

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Software](<https://devfeed.tech/topics/software.md>), [Software as a service](<https://devfeed.tech/topics/saas.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ceo](<https://devfeed.tech/tags/ceo.md>), [company](<https://devfeed.tech/tags/company.md>), [fin](<https://devfeed.tech/tags/fin.md>), [llms](<https://devfeed.tech/tags/llms.md>), [news-updates](<https://devfeed.tech/tags/news-updates.md>), [product-launch](<https://devfeed.tech/tags/product-launch.md>), [salesforce](<https://devfeed.tech/tags/salesforce.md>)

### AI overview

Intercom announces that Salesforce has signed a definitive agreement to acquire Fin for approximately $3.6 billion. The transaction is expected to close in the fourth quarter of Salesforce's fiscal year 2027, subject to closing conditions.

### Source excerpt

We're excited to share that we just signed an agreement for Salesforce to acquire Fin for ~$3.6B.

## Salesforce signs definitive agreement to acquire Fin

DevFeed: [Salesforce signs definitive agreement to acquire Fin](<https://devfeed.tech/articles/salesforce-signs-definitive-agreement-to-acquire-fin-65058.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/salesforce-signs-definitive-agreement-to-acquire-fin>)

Author: Eoghan McCabe

Published: 2026-06-15T00:00:00Z

Content type: news

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [Product Management](<https://devfeed.tech/topics/product-management.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [accelerate](<https://devfeed.tech/tags/accelerate.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ceo](<https://devfeed.tech/tags/ceo.md>), [fin](<https://devfeed.tech/tags/fin.md>), [launch](<https://devfeed.tech/tags/launch.md>), [llms](<https://devfeed.tech/tags/llms.md>), [news-updates](<https://devfeed.tech/tags/news-updates.md>), [operator](<https://devfeed.tech/tags/operator.md>), [product](<https://devfeed.tech/tags/product.md>), [saas](<https://devfeed.tech/tags/saas.md>), [salesforce](<https://devfeed.tech/tags/salesforce.md>), [software](<https://devfeed.tech/tags/software.md>), [team](<https://devfeed.tech/tags/team.md>), [tech](<https://devfeed.tech/tags/tech.md>), [thank-you](<https://devfeed.tech/tags/thank-you.md>), [time](<https://devfeed.tech/tags/time.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

Salesforce signed an agreement to acquire Fin for approximately $3.6 billion, with the deal expected to close in the fourth quarter of Salesforce's fiscal year 2027. Intercom's leadership says the acquisition will help expand Fin, its AI customer agent, while its CEO and R&D leadership continue in their roles.

### Source excerpt

We're excited to share that we just signed an agreement for Salesforce to acquire Fin for ~$3.6B.

## How to make the case for giving your AI Agent system access

DevFeed: [How to make the case for giving your AI Agent system access](<https://devfeed.tech/articles/how-to-make-the-case-for-giving-your-ai-agent-system-access-9347.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/giving-your-ai-agent-system-access/>)

Author: Dawn Perrott

Published: 2026-06-11T12:04:14Z

Content type: tutorial

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Back end](<https://devfeed.tech/topics/backend.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [AI Platform](<https://devfeed.tech/topics/ai-platform.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-blueprint](<https://devfeed.tech/tags/ai-agent-blueprint.md>), [ai-automation](<https://devfeed.tech/tags/ai-automation.md>), [backend](<https://devfeed.tech/tags/backend.md>), [customer-service](<https://devfeed.tech/tags/customer-service.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [integration](<https://devfeed.tech/tags/integration.md>), [knowledge-management](<https://devfeed.tech/tags/knowledge-management.md>), [management-tools](<https://devfeed.tech/tags/management-tools.md>)

### AI overview

The article explains why AI Agents need access to backend systems to move from answering customer questions to completing actions. It argues that connecting support agents to CRM, billing, and order-management systems can enable end-to-end resolution, and describes how Intercom's Procedures with system access handled complex workflows better than fixed, scripted Tasks in some cases.

### Source excerpt

Without access to your backend systems, your AI Agent can answer questions, but it can't take action. A customer asks to change their payment plan, they get a clear explanation, but a support rep still has...

## How to make the case for giving your AI Agent system access

DevFeed: [How to make the case for giving your AI Agent system access](<https://devfeed.tech/articles/how-to-make-the-case-for-giving-your-ai-agent-system-access-65048.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/giving-your-ai-agent-system-access>)

Author: Dawn Perrott

Published: 2026-06-11T00:00:00Z

Content type: article

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [API Governance](<https://devfeed.tech/topics/api-governance.md>)

Tags: [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-blueprint](<https://devfeed.tech/tags/ai-agent-blueprint.md>), [ai-automation](<https://devfeed.tech/tags/ai-automation.md>), [api](<https://devfeed.tech/tags/api.md>), [backend](<https://devfeed.tech/tags/backend.md>), [build](<https://devfeed.tech/tags/build.md>), [customer-service](<https://devfeed.tech/tags/customer-service.md>)

### AI overview

The article explains how support teams can make a focused case for connecting AI agents to backend systems so they can complete customer workflows. It recommends starting with high-volume, repeatable tasks, defining the data and access required, and progressing from no integration to read-only access and then write actions. Examples from Intercom's workflows show that deeper integration helps most when tasks require branching, live data, or judgment; the article also suggests pilots, scoped permissions, mock responses, and clear success metrics to build support from engineering.

### Source excerpt

Without access to your backend systems, your AI Agent can answer questions, but it can't take action. A customer asks to change their payment plan, they get a clear explanation, but a support rep still has to step in and make the change. Someone else needs to update their account, the same thing happens. The Agent knows the answer, it just doesn't have the ability to act. That gap between answering a query and resolving it keeps your team handling requests your Agent could take on.

## Fin extends Service Agent support to HubSpot and Freshworks

DevFeed: [Fin extends Service Agent support to HubSpot and Freshworks](<https://devfeed.tech/articles/extending-fin-as-the-most-open-agent-platform-9346.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/extending-fin-as-the-most-open-agent-platform/>)

Author: Paul Adams

Published: 2026-06-09T16:45:42Z

Content type: release

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [hubspot](<https://devfeed.tech/topics/hubspot.md>), [Support](<https://devfeed.tech/topics/support.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [apis](<https://devfeed.tech/tags/apis.md>), [cli](<https://devfeed.tech/tags/cli.md>), [customer-experience](<https://devfeed.tech/tags/customer-experience.md>), [docs](<https://devfeed.tech/tags/docs.md>), [fin](<https://devfeed.tech/tags/fin.md>), [fin-for-freshdesk](<https://devfeed.tech/tags/fin-for-freshdesk.md>), [fin-for-hubspot](<https://devfeed.tech/tags/fin-for-hubspot.md>), [helpdesk](<https://devfeed.tech/tags/helpdesk.md>), [hubspot](<https://devfeed.tech/tags/hubspot.md>), [integrations](<https://devfeed.tech/tags/integrations.md>), [mcps](<https://devfeed.tech/tags/mcps.md>), [news-updates](<https://devfeed.tech/tags/news-updates.md>), [platform](<https://devfeed.tech/tags/platform.md>)

### AI overview

Intercom announces that Fin can operate as a Service Agent on top of HubSpot and Freshworks, allowing customers to integrate it without migrating from their existing helpdesk. The article also describes Fin's open-platform approach, including APIs, MCPs, CLI access, and public documentation.

### Source excerpt

Fin can be used as a Service Agent on top of HubSpot and Freshworks, meaning you can use the world's best Agent without migrating off your helpdesk.

## Extending Fin as the most open Agent platform

DevFeed: [Extending Fin as the most open Agent platform](<https://devfeed.tech/articles/extending-fin-as-the-most-open-agent-platform-65047.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/extending-fin-as-the-most-open-agent-platform>)

Author: Paul Adams

Published: 2026-06-09T00:00:00Z

Content type: release

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [hubspot](<https://devfeed.tech/topics/hubspot.md>), [self-service](<https://devfeed.tech/topics/self-service.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [developer](<https://devfeed.tech/tags/developer.md>), [fin](<https://devfeed.tech/tags/fin.md>), [fin-for-freshdesk](<https://devfeed.tech/tags/fin-for-freshdesk.md>), [fin-for-hubspot](<https://devfeed.tech/tags/fin-for-hubspot.md>), [helpdesk](<https://devfeed.tech/tags/helpdesk.md>), [integrations](<https://devfeed.tech/tags/integrations.md>), [news-updates](<https://devfeed.tech/tags/news-updates.md>), [platform](<https://devfeed.tech/tags/platform.md>)

### AI overview

Intercom announces that its Fin service agent can run on HubSpot and Freshworks without requiring customers to migrate helpdesks. The post emphasizes APIs, MCPs, CLI access, public documentation, configuration, and self-service setup, and argues that open platforms give businesses flexibility to switch vendors.

### Source excerpt

Fin can be used as a Service Agent on top of HubSpot and Freshworks, meaning you can use the world's best Agent without migrating off your helpdesk.

## Playing a different game

DevFeed: [Playing a different game](<https://devfeed.tech/articles/playing-a-different-game-65055.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/playing-a-different-game>)

Author: Eoghan McCabe

Published: 2026-06-04T00:00:00Z

Content type: release

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [speech-to-speech](<https://devfeed.tech/topics/speech-to-speech.md>), [Media Queries](<https://devfeed.tech/topics/media-queries.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [customer-experience](<https://devfeed.tech/tags/customer-experience.md>), [customer-service](<https://devfeed.tech/tags/customer-service.md>), [features](<https://devfeed.tech/tags/features.md>), [fin](<https://devfeed.tech/tags/fin.md>), [fin-voice](<https://devfeed.tech/tags/fin-voice.md>), [fin-voice-2](<https://devfeed.tech/tags/fin-voice-2.md>), [low-latency](<https://devfeed.tech/tags/low-latency.md>), [news-updates](<https://devfeed.tech/tags/news-updates.md>), [product](<https://devfeed.tech/tags/product.md>), [upgrade](<https://devfeed.tech/tags/upgrade.md>)

### AI overview

Intercom announces Fin Voice 2, a voice agent for customer service built on Apex Flash. The release describes its low latency design, ability to handle complex requests and take actions, transfer context to human teams, and tools for configuring and reviewing call behavior.

### Source excerpt

Announcing Fin Voice 2, a major upgrade to Fin Voice with over 20 new features, and our first product built on Apex Flash.

## Building and maintaining a knowledge base for AI customer service agents

DevFeed: [Building and maintaining a knowledge base for AI customer service agents](<https://devfeed.tech/articles/the-ultimate-guide-to-knowledge-management-for-your-service-agent-65049.md>)

Original publisher: [Read original article](<https://www.intercom.com/blog/guide-customer-service-knowledge-management-ai>)

Author: Beth-Ann Sher

Published: 2026-05-27T00:00:00Z

Content type: tutorial

Language: en

Sources: [Intercom](<https://devfeed.tech/sources/the-intercom-blog.md>)

Topics: [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [customer-service](<https://devfeed.tech/tags/customer-service.md>), [fin](<https://devfeed.tech/tags/fin.md>), [knowledge-management](<https://devfeed.tech/tags/knowledge-management.md>), [service](<https://devfeed.tech/tags/service.md>)

### AI overview

The guide explains how to build and maintain a knowledge base for AI customer service agents. It covers auditing and prioritizing support content, writing clear and structured material, testing an agent's answers, tracking performance, and keeping knowledge current as products and policies change.

### Source excerpt

Everything you need to know about building and maintaining a knowledge base that powers your Service Agent, in one comprehensive guide.

[Next page](<https://devfeed.tech/sources/the-intercom-blog.md?cursor=WyIyMDI2LTA1LTI3VDAwOjAwOjAwKzAwOjAwIiwgIjNiZmU0OGNkLWY1YTMtNGIzMS05N2IyLWQ1MjU0ZjU3Y2Y0YiJd>)