What are Monitors?
Use this article to understand how Monitors work and when to use them — whether you're a support manager, QA lead, or anyone responsible for conversation quality. Monitors help you continuously evaluate and improve Fin's conversation quality at scale — for both Fin AI Agent and human teammate conversations. They give you a structured way to define which conversations should be reviewed, whether that's a random sample for baseline quality, or a targeted set based on higher-risk or higher-impact signals. This replaces ad-hoc sampling and spreadsheet-driven quality assurance (QA) with a repeatable system that scales as volume grows. Monitors is available on the Pro add-on — see the note at the end of this article before getting started.
How teams use Monitors
Teams use Monitors to maintain ongoing visibility into quality and focus attention where it matters most.
They're useful for reviewing a random sample of conversations to understand overall quality trends, for focusing on higher-risk interactions flagged by signals like low CX scores, policy breaches, or legal threats, and for tracking conversations tied to a specific initiative — such as a feature launch, pricing change, or product update.
Monitors make it easier to detect patterns, surface issues earlier, and generate insights that can be shared with product, support, or leadership teams. There are pre-built templates across three categories to help you get started:
Fin reviews
Use Fin review monitors to evaluate the quality of conversations handled by Fin. Intercom includes the following templates to get you started:
All Fin conversations — auto-review all Fin conversations.
Weekly Fin review — sample Fin conversations for review.
Low Fin answer quality — conversations with low quality Fin answers.
High Fin answer quality — conversations with high quality Fin answers.
Escalation handling issues — flag conversations where escalation is mishandled.
Repetitive looping issues — flag conversations where Fin is stuck in repetitive responses.
Teammate reviews
Use teammate review monitors to evaluate conversations handled by human teammates.
These are useful for coaching, calibration, and performance tracking. Templates include:
All teammates — auto-review all teammate conversations.
Weekly teammate review — sample teammate conversations for review.
High teammate answer quality — conversations with high quality teammate answers.
Low teammate answer quality — conversations with low quality teammate answers.
Other monitors
General monitors let you track specific customer experience signals and risk factors across all conversations, regardless of whether they were handled by Fin or a teammate.
Templates include:
Negative sentiment — conversations with negative customer sentiment.
Positive sentiment — conversations with positive customer sentiment.
Negative product feedback — track conversations with negative product feedback.
Legal & security issues — flag high risk conversations with legal or security issues.
Vulnerable customers — flag financially vulnerable customer conversations.
Patient safety concern — flag conversations that may indicate a health risk.
Imminent churn risk — flag conversations with customers likely to churn.
At-risk order experience — flag conversations with severe order dissatisfaction.
Using Monitors responsibly
In conversations involving multiple participants (e.g. Fin starts the conversation and a teammate finishes it or multiple teammates are involved), the Monitor score reflects the individual contribution of the participant the Customer specifies during the scorecard setup. Monitors is designed to support conversation quality review, not to assess individual teammate performance for employment purposes. Customers are not permitted to use or rely on Monitor scores to materially influence employment-related decisions about human agents. Such use would be contrary to Fin's AI Product Terms and Acceptable Use Policy. Where Monitors is used in the context of human agent conversations, customers remain solely responsible for ensuring their use complies with all applicable laws.
How Monitors work with Custom Scorecards
In Intercom, Monitors and Custom Scorecards work together as a two-part system for evaluating conversation quality:
Monitors define what gets reviewed
Scorecards define how each conversation is evaluated
Scorecards can include criteria that are reviewed:
Reviewed manually
Evaluated using AI
Or a combination of both
You can associate a scorecard with a Monitor to automatically evaluate every matched conversation against defined criteria. Once selected, the scorecard runs as soon as the conversation is added to the Monitor, and results appear in the Monitor for reporting and review.
This ensures quality is assessed consistently, while still allowing flexibility in how reviews are performed.
Tip: Auto-review is a Monitor setting that automatically marks a conversation as passed when all AI-evaluated scorecard criteria are met. Enable it to skip manual checks entirely when AI scoring meets your quality standards — your team only needs to step in for failures or edge cases.
How to manage Monitors
When you have multiple monitors running, the reviews list can grow quickly. Use the filters at the top of the Monitors page to focus on what's most relevant to you — whether that's a specific type of monitor or conversations waiting for your attention.
Filter by monitor type
On the Monitors page in Intercom, use the monitor type filter to narrow the list to a specific category:
Fin reviews — monitors that evaluate conversations handled by Fin. Use this to focus on AI-driven quality.
Teammate reviews — monitors that evaluate conversations handled by human teammates. Useful for coaching and performance tracking.
Other monitors — any monitors that don't fall into the above two categories.
Filter by review status
Once you're viewing a monitor, use these filters to navigate the review queue based on assignment or who the reviews belong to:
All reviews — shows every conversation in the monitor, regardless of assignment or status. A good starting point when you want the full picture.
Assigned to me — shows only the conversations assigned to you for review. Use this to work through your personal review queue without distraction.
Reviews received — shows conversations where your own work has been reviewed by someone else. Useful for checking feedback on your conversations.
What's coming to Monitors
The following capabilities aren’t available in Monitors yet, but are planned for a future release:
Real-time alerts: Get notified when conversations in a Monitor cross defined thresholds or fail a scorecard.
Evaluation against your knowledge base: Score conversations against your support content and policies, helping ensure responses align with approved sources.
Teammate coaching tips: AI driven coaching tips for teammates who are being reviewed, as well as for managers reviewing those teammates.
Calibration workflows: Calibration helps reviewers align on evaluation standards by assessing shared examples and comparing outcomes, improving consistency and fairness in feedback and quality measurement.
Dispute workflow: Teammates will be able to dispute their reviews.
Sorting and rearranging columns.
How to get started with Monitors
Head over to how to create a Monitor for a step-by-step guide. You'll set up conversation filters to define what gets reviewed, attach a scorecard to define your evaluation criteria, and optionally enable auto-review to automatically pass conversations where all AI-evaluated criteria are met.
Note: Monitors requires the Pro add-on. Make sure your workspace has this before setting up your first Monitor.
Need more help? Get support from our Community Forum
Find answers and get help from Intercom Support and Community Experts