Docs Menu
Docs Home
/ /

AI 클러스터 어시스턴트

AI 클러스터 어시스턴트는 Atlas UI 에 내장된 AI 기반 헬퍼입니다. 클러스터 생성하거나 클러스터 구성을 편집하는 동안 클러스터 구성에 대한 자연어 질문에 답변하는 데 사용할 수 있습니다. 그러면 AI Cluster 어시스턴트 워크로드 와 요구 사항에 따라 설정을 추천하고 해당 설정을 클러스터 에 직접 적용 수 있습니다.

Atlas 에서 AI Cluster 어시스턴트를 사용하려면 먼저 Organization Settings 페이지에서 생성형 AI 기능을 활성화 해야 합니다.

이 조직 수준 설정을 활성화 하려면 다음 단계를 따르세요.

1
  1. 아직 표시되지 않은 경우 다음 목록에서 원하는 조직 을 선택하세요. 탐색 표시줄의 Organizations 메뉴.

  2. 사이드바에서 Organization Settings를 클릭합니다.

Organization Settings(조직 설정) 페이지가 표시됩니다.

2

Enable Atlas features that use generative AI 토글을 On 으로 설정합니다.

클러스터 생성하거나 클러스터의 구성을 편집하는 동안 Atlas UI 에서 AI Cluster 어시스턴트에 액세스 할 수 있습니다. 클러스터 생성하는 동안 AI Cluster 어시스턴트에 액세스 하려면 다음을 수행합니다.

1
  1. 아직 표시되지 않은 경우 탐색 표시줄의 Organizations 메뉴에서 원하는 프로젝트가 포함된 조직을 선택합니다.

  2. 아직 표시되지 않은 경우 탐색 표시줄의 Projects 메뉴에서 원하는 프로젝트를 선택합니다.

  3. 사이드바에서 Database 제목 아래의 Clusters를 클릭합니다.

Clusters(클러스터) 페이지가 표시됩니다.

2

이미 하나 이상의 클러스터가 있는 경우 Create 을 클릭하여 Deploy your cluster 페이지를 표시합니다.

첫 번째 클러스터 인 경우 Build a Cluster 을 클릭하여 Deploy your cluster 페이지를 표시합니다.

3

페이지 하단으로 이동하여 Go to Advanced Configuration 을 클릭합니다.

페이지 오른쪽에 AI Cluster 어시스턴트 채팅 창 나타납니다.

클러스터 편집하는 동안 AI Cluster 어시스턴트에 액세스 하려면 Upgrade <yourClusterName> 페이지에서 Edit additional configuration 를 클릭하기만 하면 됩니다.

어시스턴트를 닫으려면 채팅 창 오른쪽 상단에 있는 를 클릭합니다. 어시스턴트를 다시 열려면 다음을 클릭합니다. 패널을 닫아도 구성이 변경되거나 해당 세션에서 채팅 기록이 삭제 않습니다. 동일한 세션 중에 언제든지 채팅 창 다시 열 수 있습니다.

1

AI Cluster 어시스턴트에 액세스하기의단계를 따르세요.

2

클러스터 구성에 대한 조언 찾는 프롬프트를 제출합니다. 워크로드, 사용 사례 또는 현재의 애로 사항에 대해 논의하면 AI Cluster 어시스턴트가 요구 사항에 가장 적합한 새로운 구성을 제안하도록 할 수 있습니다.

3

AI Cluster 어시스턴트는 요구 사항을 논의하고 클러스터 구성을 제안하는 응답을 제공합니다. 응답과 제안된 구성을 검토하고 만족스러운지 평가합니다.

4

필요한 경우 AI Cluster 어시스턴트에 후속 메시지를 제출 제안된 구성에 대한 자세한 정보를 얻거나 요구 사항에 더 적합한 새 구성을 요청 수 있습니다.

5

AI Cluster 어시스턴트가 제안한 구성을 수락하려면 Apply these suggestions 를 클릭합니다. 이렇게 해도 구성이 확정되지 않으며 계속 변경할 수 있습니다.

6

채팅 창 AI Cluster 어시스턴트 응답 아래에 있는 또는 버튼을 사용하여 응답에 대한 피드백 과 AI Cluster 어시스턴트 사용 경험에 대한 피드백을 제공할 수 있습니다.

7

만족하면 클러스터 구성을 저장합니다.

클러스터 생성하는 경우 페이지 하단의 Create Cluster 를 클릭하여 제안된 구성으로 클러스터 생성합니다.

클러스터 수정하는 경우 페이지 하단의 Review Changes 를 클릭하면 변경 사항 요약을 볼 수 있습니다. 그런 다음 Accept Changes 을 클릭하여 새 구성을 저장합니다.

이렇게 하면 AI Cluster 도우미가 닫힙니다.

AI Cluster 도우미는 채팅하는 동안 다음 작업 에 따라 다양한 Atlas UI 페이지로 연결되는 링크를 제공합니다. AI Cluster 도우미는 다음 Atlas UI 페이지 중 하나에 연결할 수 있습니다.

다음 시나리오는 Atlas 에서 클러스터 생성하거나 편집하는 동안 AI Cluster 도우미를 사용할 수 있는 몇 가지 방법을 보여줍니다.

사용 사례 와 요구 사항을 설명하고 AI Cluster 어시스턴트에게 가장 적합한 클러스터 구성을 제안하도록 요청하세요.

예시 를 들어 애플리케이션 개발하는 경우 AI Cluster 어시스턴트에 애플리케이션 의 목적과 예상 사용자 수를 알릴 수 있습니다.

I’m setting up a development cluster for a restaurant rating app with
100 users in NYC. What’s the best cluster configuration?
For a small development app with ~100 users, cost-effectiveness and
reliability are key. I recommend starting with an M10 cluster on AWS in
US_EAST_1 (N. Virginia). This tier supports your use case with enough
resources for development and light testing, while keeping costs
controlled. Avoid free (M0) since you already have one and FLEX is
unnecessary for your scale.
I'll suggest a configuration based on these requirements. Quick
questions to further optimize:
- Do you expect your dataset to grow beyond 10GB during development?
- Any other environments needed, like staging or test?
- Will more developers or services connect to this cluster soon?
Suggesting the config now.

AI Cluster 어시스턴트가 구성을 제안한 후에는 이를 수락하고 저장하거나 만족스러운 구성에 도달할 때까지 요구 사항을 계속 논의할 수 있습니다.

또한 지원 필요할 것으로 예상되는 데이터의 크기와 프로젝트 의 기반을 AI Cluster 어시스턴트에 알릴 수도 있습니다.

I’m looking to migrate an existing project to Atlas. We currently
have 100GB of data that we need to move over. The project is currently
deployed in Europe and we want to maintain that. How should I configure
my cluster?
For migrating a 100GB project to Atlas in Europe, I recommend the following:
- Use AWS as your cloud provider (most commonly used, but let me know if
you prefer GCP or Azure).
- Select the region EU_WEST_1 (Ireland) to host your data in Europe.
- Choose at least an M40 instance (this tier is recommended for
migrating and running production workloads with 100GB+ data, ensuring
strong performance during data load and normal operations).
- Set storage to 150GB (100GB data + 30% headroom).
- Default disk IOPS for M40 will provide ample performance for both
migration and ongoing workload.
Let’s proceed with this setup.
A few quick clarifications:
- Is this a production environment with performance/uptime requirements?
- Do you expect rapid growth in data or traffic soon?
- Any preference for AWS, GCP, or Azure within Europe, or should we
proceed with AWS?
I’ll configure the cluster now with these optimized settings.

다시 말하지만, 제안된 구성을 수락하고 저장하거나 AI Cluster 도우미를 사용하여 요구 사항을 더 잘 충족하는 구성을 위해 계속 작업할 수 있습니다.

사용 사례 의 변경 사항과 요구 사항을 설명하고 AI Cluster 어시스턴트가 클러스터 구성을 가장 잘 수정하는 방법을 제안하도록 합니다.

예시 를 들어 AI 클러스터 도우미로 예산 제약 조건을 논의할 수 있습니다.

My cluster costs more than expected. Is there a setup that keeps
us under $500/mo?
To keep monthly costs under $500, I recommend switching to an M30 tier.
This provides reliable performance for standard production workloads at
around $394/month on AWS, plus some buffer for backups and storage.
Here’s how I’ll configure it:
- Instance size: M30 (entry-level dedicated, good for most production
apps)
- Region: N. Virginia (US_EAST_1) (stays consistent with your existing
clusters)
- Disk size: 40GB (default for M30, suitable for moderate workloads)
- No additional IOPS or premium storage (keeps costs down)
- No analytics/search node or advanced add-ons
Let’s proceed with this cost-effective configuration.
Before finalizing, can you clarify:
- Is this cluster for production, staging, or development?
- What’s your estimated data volume (just rough amount of GB needed)?
- Any specific performance requirements (high writes, reads, etc.)?
I’ll now suggest the configuration for you.

AI Cluster 어시스턴트가 새로운 구성을 제안합니다.

AI Cluster 어시스턴트로 증가된 워크로드에 대해 논의할 수도 있습니다.

Suggest a cluster setup as I'm expanding to India and expect 20,000
new users and the associated data.
Since you're expanding to India with 20,000 expected users, you’ll need
a production-grade cluster deployed in an appropriate Indian region for
low latency. I recommend AWS as the cloud provider (unless you have a
preference for GCP or Azure), using the AP_SOUTH_1 region (Mumbai).
For your user base and workload size, an M30 dedicated tier is a strong
fit—it’s ideal for mid-sized production apps. This setup will handle
moderate to high traffic and provides headroom as your user base grows.
I'll set:
- Cloud Provider: AWS
- Region: AP_SOUTH_1 (Mumbai, India)
- Instance Size: M30 (production-ready with sufficient resources)
- Disk Size: Default (40GB, upgrade later if data grows quickly)
To refine this setup:
- What type of workload will the cluster handle (e.g., read-heavy,
write-heavy, analytics)?
- Any data volume estimate (GB/TB) for the first year?
- Any specific cost constraints?
Applying this recommendation now.

AI Cluster 도우미는 확장된 요구 사항을 수용할 수 있는 구성을 제안합니다.

  • AI Cluster 어시스턴트의 데이터 사용량

돌아가기

클러스터 생성

이 페이지의 내용