AWS Software / SaaS Global

JetBrains

IT Operations Automation

“It became obvious to us that we needed to support additional LLM providers.” To support new LLMs, JetBrains would need to work with individual LLM providers to understand the way they operate, including the way they handle data and the throughput support that they provide. On a mission to support developers, JetBrains is always looking for ways to streamline how developers work in the age of artificial intelligence (AI).

Read the original story Explore all use cases

The company trains its Mellum model with over 4 billion parameters and appreciates the scalability that AWS provides.

Using DeepSeek in Amazon Bedrock , JetBrains was able to adapt the LLM in just 1 day.

Within 1 month, all testing had been completed, and the integration was complete.

Reported impact

Business outcome

Using Amazon Bedrock, JetBrains not only has flexibility to adapt existing LLMs but can also deliver its own open-source LLMs to Amazon Bedrock. “The fact that we can use Amazon Bedrock to deliver our products so that other folks will be able to use them is extremely important for us,” says Tankov. Key reported metrics include The company trains its Mellum model with over 4 billion parameters and appreciates the scalability that AWS provides.; Within 1 month, all testing had been completed, and the integration was complete.; Using DeepSeek in Amazon Bedrock , JetBrains was able to adapt the LLM in just 1 day..

Solution

Streamlining LLM adaptation using Amazon Bedrock with JetBrains On a mission to support developers, JetBrains is always looking for ways to streamline how developers work in the age of artificial intelligence (AI). The company wanted to adapt new large language models (LLMs) in its AI assistant plugin for its integrated development environments. JetBrains has been using Amazon Web Services (AWS) since 2013, and it had already used AWS services for its JetBrains AI platform, a set of products that includes tools for code completion, context-aware chats, and agent workflows. By adapting LLMs through Amazon Bedrock , a comprehensive, secure, and flexible service for building generative AI applications and agents, JetBrains could reduce the adaptation time for LLMs and experiment with new models simply and quickly—and even within 1 day. Source data enters the JetBrains workflow through its application services, processed with Amazon Bedrock.

Data flow

Source data enters the JetBrains workflow through its application services, processed with Amazon Bedrock.

Solution architecture

1 components · 1 layer

Compute
- Amazon Bedrock Hosts the foundation models and inference APIs that power the generative AI features.

Architecture clues

Additionally, using Amazon Bedrock helps JetBrains maintain compliance across regions, facilitating product deployment in new markets.
And because Amazon Bedrock operates across 17 regions worldwide, JetBrains is able to use cross-region inferencing to distribute workloads, helping to minimize latency even in times of peak demand.
JetBrains has been using Amazon Web Services (AWS) since 2013, and it had already used AWS services for its JetBrains AI platform, a set of products that includes tools for code completion, context-aware chats, and agent
“That’s a really great thing.” Going forward, JetBrains will use AWS to expand its use of agentic workflows.
“Using Amazon Bedrock really helps because we don’t have to recertify the whole solution in different regions,” says Tankov.

Evidence from the source

Because JetBrains has trusted AWS with its infrastructure for more than a decade, its team felt prepared to integrate Amazon Bedrock into its solution.

The company trains its Mellum model with over 4 billion parameters and appreciates the scalability that AWS provides.

Using DeepSeek in Amazon Bedrock , JetBrains was able to adapt the LLM in just 1 day.

Within 1 month, all testing had been completed, and the integration was complete.

“It became obvious to us that we needed to support additional LLM providers.” To support new LLMs, JetBrains would need to work with individual LLM providers to understand the way they operate, including the way they handle data and the thr

“It was simple and straightforward, and that was one of the things that we really liked about Amazon Bedrock,” says Tankov.

Transparency Evidence & methodology 90/100 reference value · 87% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value90/100

Problem clarity20/20
Measures whether the customer's operational problem is specific enough to compare.
Implementation depth20/25
Rewards named components, data flow, integrations, and architecture detail.
Outcome specificity20/20
Measures whether the reported benefit is concrete rather than a generic claim.
Quantified impact25/25
3 metrics describe measurable impact.
Deployment scale5/10
Rewards evidence of a live or scaled deployment and meaningful integration scope.

Evidence confidence87%

Source authority20/25
The main evidence is an official vendor-published customer story.
Claim traceability21/25
10 of 12 key fields link to a named source.
Direct evidence20/20
6 direct source quotes retained.
Date provenance8/10
The publication date comes from publisher-controlled metadata.
Source transparency8/10
1 source reference document publisher, URL, authority, retrieval, and supported fields.
Implementation specificity10/10
Rewards source-backed components, data flow, quantified impact, and a specific outcome.

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

AWS
JetBrains customer story

First-party
https://aws.amazon.com/solutions/case-studies/jetbrains/

Source type
Vendor-published customer story

Published
Apr 12, 2024
Supports
- Customer
- Business problem
- Solution
- Products
- Solution components
- Data flow
- Integrations
- technical area
- use case category
- Business outcome
- outcome category
- Metrics
- Architecture
- evidence quotes
- Publication date

Date evidence

Publisher catalog date Apr 12, 2024 · AWS · First-party
Open date source

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Similar use cases

See all like this

AWS Oct 25, 2024 nnamu Software / SaaS Global Founded in 2022 in Germany, nnamu built a proprietary artificial intelligence (AI) for strategic reasoning based on game theory. The company’s first AI agent is live and can autonomously define negotiation strategies… 30 percent Application RefactoringIT Operations Automation AWS Lambda · Amazon DynamoDB · Amazon Q Business

AWS Sep 18, 2023 CyberGRX Software / SaaS Denver The legacy ML modeling solution for CyberGRX took 8 days to complete predictive modeling for all the companies in its database — 150,000 at the time. Four engineers were required to monitor and manage it, which added… CyberGRX reduced the runtime of its solution from 8 days to 1 hour for its quarterly modeling, improved staff… Application RefactoringIT Operations Automation AWS Lambda · AWS Step Functions · AWS Step Functions Distributed Map

AWS Sep 8, 2023 Katalon Software / SaaS United States Katalon engineers had to set up and manage workflows for a growing number of customers who generated workloads with large fluctuations in volume depending on the time of day. “At first, we didn’t have a messaging… By implementing managed, serverless solutions from AWS, Katalon has automated its ability to scale while… Application RefactoringIT Operations Automation AWS Lambda · AWS Marketplace · Amazon EKS