A manager assistance feature that allows you to check contact center operational status in natural language using Amazon Connect Customer has been made available in preview.
This page has been translated by machine translation. View original
Introduction
A preview of an AI-powered manager assistance feature for Amazon Connect Customer has been announced, enabling natural language queries of contact center operations.
In the Amazon Connect Customer management console, this feature is displayed as "Connect Assistant - Preview." In this article, it will be referred to as "Connect Assistant."
According to AWS update information, the feature allows natural language queries of over 150 metrics, including agent schedules, self-service experiences, and performance evaluations, along with their historical data.
It is also described as being able to identify queues at risk of not meeting service level objectives and recommend recovery measures.
As of August 19, 2026, an overview of this feature is also included in the Amazon Connect Customer release notes.
On the other hand, as of August 19, 2026, no dedicated AWS documentation explaining available metrics, required permissions, operating procedures, or limitations for this feature could be found.
Therefore, this article organizes what could be confirmed at this point, based on the overview described in What's New and the release notes, as well as the actual screens and Connect Assistant responses.
Upon checking the Amazon Connect Customer management console, Connect Assistant was displayed, and the following was actually verified.
- What can and cannot be confirmed with Connect Assistant
- Whether operational metrics can be compared by specifying past time periods
- Whether inquiry content can be analyzed on a monthly basis
- Whether Contact Lens contact categories can be referenced
Conclusion
In this verification, Connect Assistant was usable as a feature for aggregating and comparing information available in Amazon Connect Customer dashboards, real-time metrics, historical metrics, and similar sources through natural language.
For example, the following types of information can be confirmed.
- Number of contacts, number of abandonments
- Average handling time
- Performance by queue and channel
- Agent handling status
- Comparison with past periods
- Aggregation by Contact Lens contact category
On the other hand, in this verification, no behavior was confirmed where the body of each contact's transcript was cross-referenced to classify and summarize its content.
Therefore, the following two points need to be distinguished.
| What you want to confirm | Result of this verification |
|---|---|
| What were the number of inquiries and average handling time in July and August? | Could be confirmed as operational metrics |
| What types of inquiries were common in July and August? | Free analysis using transcript content could not be confirmed |
| Which queues or channels increased from July to August? | Could be confirmed as operational metrics |
| What specific inquiry reasons increased from July to August? | Difficult without pre-configured Contact Lens categories |
In other words, Connect Assistant is a conversational assistant for reviewing operational metrics, not a feature for freely analyzing inquiry content across all transcripts.
If you want to check trends in inquiry content, a candidate approach is to pre-configure contact categories in Contact Lens—such as "pricing," "cancellation," "how to use," and "outages"—and then aggregate those classification results using Connect Assistant.
Checking Connect Assistant
"Connect Assistant - Preview" was displayed on the right side of the Amazon Connect Customer management console.
Connect Assistant - Preview displayed in the Amazon Connect Customer management console
The initial screen displayed the following prompts.
- Monitor your contact center
- Check queue performance
- Track agent handling status
For example, "Check queue performance" allows you to see the current number of contacts waiting in queues and the longest wait time.
"Track agent handling status" allows you to see the number of agents by status, such as available, handling, and on duty.
Even from the initial screen prompts, it is clear that the primary use cases are real-time contact center monitoring and checking operational metrics.
What Can Be Confirmed
Connect Assistant was asked what can be confirmed.
Result of asking Connect Assistant what can be confirmed
The response described that the following information can primarily be confirmed.
- Number of handled, abandoned, and transferred contacts
- Average handling time, average hold time, average after-contact work time
- Service level
- Average speed of answer
- Number of contacts entered in queue, longest wait time
- Number of agents by status
- Schedule adherence rate
- Performance evaluation score
- Number of contacts by Contact Lens contact category
- Filtering by period, channel, queue, and agent
- Comparison with previous periods and rankings
- Checking metrics that affect service levels
These overlap with information handled in Amazon Connect Customer dashboards, real-time metrics, historical metrics, and similar sources.
The advantage of Connect Assistant, it seemed, is the ability to ask questions in natural language and compare these pieces of information all at once, rather than checking them individually across multiple screens.
In Amazon Connect Customer dashboards, you can check contact center performance using real-time and historical metrics.
What Cannot Be Confirmed
Connect Assistant was then asked what cannot be confirmed.
Result of asking Connect Assistant what cannot be confirmed
The response described the following as primarily out of scope.
- Viewing the body of call or chat transcripts
- Playback of recordings or screen recordings
- Understanding customer statements or intentions
- Searching for conversations containing specific keywords
- Referencing comments or notes for individual contacts
- Creating, editing, or deleting queues, agents, and similar resources
- Editing or deploying contact flows
- Generating report files such as CSV, Excel, or PDF
- Referencing data outside of Amazon Connect Customer
- Long-term demand forecasting or estimating root causes that cannot be confirmed from data
This response was generated by Connect Assistant itself and is not an official feature specification documented publicly. The scope of responses may vary depending on how questions are phrased, the user's permissions, and the data that has been accumulated.
However, in the verification described later, operational metrics by channel and queue were analyzed rather than transcript content.
Analyzing Inquiries from July and August
The following query was submitted.
Please analyze inquiry types for July and August.
The result is as follows.
Result of requesting an inquiry type analysis for July and August 2026
In this verification, the following periods were compared.
- July 1, 2026 to July 31, 2026
- August 1, 2026 to August 19, 2026, 13:46
The response compared the number of handled contacts, number of abandoned contacts, and average handling time by channel and queue.
It also identified days with concentrated contacts and performed a daily average comparison that accounted for the difference in aggregation periods.
The ability to retrieve multiple operational metrics together and explain them while accounting for period differences is convenient.
On the other hand, the requested "inquiry types" were analyzed as channels such as VOICE and CHAT, and queues, rather than as inquiry content.
Analysis of Inquiry Content Using Transcripts Could Not Be Confirmed
What the author wanted to confirm under "inquiry types" was inquiry content such as the following.
- Pricing
- Cancellation
- How to use
- Outages and defects
- Contract changes
- Complaints and dissatisfaction
However, what Connect Assistant analyzed was primarily the following information.
- Channels such as VOICE and CHAT
- Queues that handled contacts
- Number of handled and abandoned contacts
- Average handling time
- Daily contact counts
In other words, the response was not an analysis of inquiry content, but a dimensional analysis of contact performance.
In this verification, no behavior was confirmed where transcript content was cross-referenced to perform the following types of analysis.
- What types of inquiries were most common
- What inquiry reasons increased compared to the previous month
- Whether new inquiry themes emerged
- The main reasons customers felt dissatisfied
- The cause of increased inquiries
For example, the following questions can be answered by referencing operational metrics.
Please compare the number of inquiries and average handling time for July and August.
Please tell me which queue had the most contacts in August.
On the other hand, answering the following questions requires reviewing the transcript content of each contact and classifying the conversation content across all contacts.
Please tell me what types of inquiries were most common in July and August.
Please tell me what new inquiry reasons increased from July to August.
In this verification, this kind of highly flexible analysis could not be confirmed.
Therefore, it is most straightforward to think of Connect Assistant as a feature that aggregates and compares information available in dashboards, real-time metrics, and historical metrics through natural language.
Inquiry Content Can Be Aggregated Using Contact Lens Categories
While direct analysis of transcript content was not possible, contact categories pre-assigned by Contact Lens could be referenced.
The following query was submitted.
What types of inquiries were most common this month?
The result is as follows.
Result of checking contact categories for August 2026
In this verification, the following contact categories were displayed for August 1 to August 19, 2026.
| Contact Category | Number of Handled Contacts | Average Handling Time |
|---|---|---|
AutoEvaluationRule-PostCall |
7 | 40 seconds |
From this result, it was confirmed that Connect Assistant can reference categories assigned to contacts by Contact Lens and aggregate the number of handled contacts and average handling time by category.
However, the AutoEvaluationRule-PostCall displayed in this verification appears, based on its name, to be a category related to an auto-evaluation rule, and is not a category representing inquiry content.
If you want to aggregate inquiry content on a monthly basis, a good approach would be to pre-configure contact categories in Contact Lens such as the following.
| Contact Category | Examples of Classification Targets |
|---|---|
| Pricing/Billing | Pricing, billing amount, payment methods |
| Cancellation | Cancellation, withdrawal, contract termination |
| How to Use | How to use a product or service |
| Outages/Defects | Connection errors, issues not working properly |
In Contact Lens, contacts can be classified based on specific words or phrases, or conditions described in natural language.
If categories have been assigned to contacts, it may be possible to ask Connect Assistant the following.
Please compare inquiries from July and August by Contact Lens contact category.
Contact Lens handles the classification of conversation content, and Connect Assistant aggregates and compares the pre-classified categories.
Therefore, this approach is suited for continuously checking the number and trends of pre-defined inquiry reasons, such as pricing or cancellations.
On the other hand, even with Contact Lens categories configured, Connect Assistant does not freely read across all transcripts to discover new inquiry themes on the fly.
A different analysis method is needed for discovering inquiry themes that were not anticipated in advance, or for free-form root cause analysis based on customer statements.
Note that newly created category rules are applied to contacts that occur after they are created. They cannot be retroactively applied to previously saved conversations, so if you plan to perform monthly comparisons, it is necessary to configure categories early and accumulate data.
Summary
A preview of an AI-powered manager assistance feature has been made available in Amazon Connect Customer.
In this verification, information from dashboards, real-time metrics, historical metrics, and similar sources could be aggregated and compared using natural language. On the other hand, no behavior was confirmed where transcript content was cross-referenced to freely classify and summarize inquiry content.
For checking monthly trends in inquiry content, a good approach is to pre-configure inquiry categories in Contact Lens and aggregate those classification results using Connect Assistant.
However, what can be analyzed with this approach is limited to pre-defined inquiry reasons. It is important to note that this approach is not suited for discovering new unexpected inquiry themes or for free-form analysis based on customer statements.
