Multitudes Builds Code Review Quality Feature in 2 Months Using 3 LLMs on Amazon Bedrock
Multitudes · New Zealand
Multitudes, a New Zealand-based engineering analytics startup, used Amazon Bedrock to build a code review quality feature, testing over 10 large language models across roughly 1,000 code reviews before choosing Amazon Nova Pro for bot detection, Anthropic Claude for feedback specificity and prompt-injection detection, and Mistral for sentiment analysis, orchestrated with Amazon Elastic Container Service. The feature increased monthly active users by 44 percent within two months of launch and reduced severe misclassification rates from 20 percent to under 1 percent.
Overview
Multitudes, a New Zealand-based engineering analytics startup, used Amazon Bedrock to build a code review quality feature, testing over 10 large language models across roughly 1,000 code reviews before choosing Amazon Nova Pro for bot detection, Anthropic Claude for feedback specificity and prompt-injection detection, and Mistral for sentiment analysis, orchestrated with Amazon Elastic Container Service. The feature increased monthly active users by 44 percent within two months of launch and reduced severe misclassification rates from 20 percent to under 1 percent.
The challenge
Multitudes had always measured code review activity by the number of reviews or comments, but customers wanted insight into the quality of those reviews. Traditional natural language processing and machine learning models couldn't deliver the level of accuracy needed to build a feature customers could trust.
The solution
Multitudes used Amazon Bedrock to build a code review quality feature, evaluating nearly 1,000 code reviews and manually creating a labeled ground truth dataset across three dimensions: feedback specificity, tone/sentiment, and bot-generated activity. It tested over 10 large language models, then used different models for each dimension -- Amazon Nova Pro for bot detection, Anthropic Claude for feedback specificity and prompt-injection detection, and Mistral for sentiment analysis -- with Amazon Elastic Container Service used to orchestrate the data pipeline.
Reported business value
Within two months of launch, the new code review quality feature drove a 44 percent increase in monthly active users. Model accuracy improved significantly, with severe misclassification rates falling from 20 percent to under 1 percent. The feature quickly became one of the platform's top five most-used capabilities.
Sources
Open any source and check the claim yourself — that is the point of the register.
Other technology & software entries in the register.
Supermetrics: Helping Marketers Redefine Efficiency with AI-Powered Data Analysis
Supermetrics, a Finland-based marketing intelligence platform serving 15,000+ customers across 132 countries, built an AI agent on Google Cloud using Vertex AI Agent Builder and the Agent Development Kit (ADK) that autonomously manages data connections, fixes pipeline errors, and analyzes campaign performance in real time, suggesting new creative options using Imagen. The agent automates the weekly marketing reporting cycle that previously took performance marketers up to four hours, reclaiming over 15 hours per month per marketer for strategy and creative testing. The system uses a central AI agent that interprets natural language requests and delegates tasks to sub-agents, and stores 'core memories' of user preferences for personalized context.
Domyn builds Colosseum 355B, a sovereign AI foundation model, using NVIDIA DGX Cloud
Domyn (formerly iGenius), an Italian AI company serving highly regulated sectors such as financial services and public administration, used NVIDIA DGX Cloud with over 3,000 NVIDIA H100 GPUs to continue-pretrain Colosseum 355B, a 355-billion-parameter foundation LLM. Within one week Domyn had access to the dedicated infrastructure, and within two months completed continued pretraining, achieving 82.04% accuracy on the MMLU benchmark. The model powers Domyn's business intelligence agent, Crystal, a sovereign AI solution deployed on private infrastructure.
Strava's Athlete Intelligence Translates Workout Data into Simple and Personalized Insights
Strava launched Athlete Intelligence, an AI-powered feature available as a public beta to subscribers, which analyzes and interprets workout data across pace, heart rate, elevation, power, and Relative Effort into simple, personalized insights and guidance. The feature spots 30-day performance trends, detects milestones such as fastest pace or longest distance, and offers tailored feedback for each activity, drawing on more than 10 billion activity uploads on Strava.
Fifth Dimension unlocks insights and intelligence with Google Cloud
Fifth Dimension, founded in 2023, provides an AI platform combining machine learning, predictive analytics and natural language processing to uncover hidden patterns in real estate data, processing over 1TB of data per month by 2025. Facing scalability and cost problems with its original infrastructure, the company adopted Google Cloud, building its ML stack on Vertex AI (running Google Cloud Gemini and Anthropic Claude models), plus Cloud SQL, Cloud Run and Pub/Sub. This scaled processing capacity 50x to handle document-processing surges, supported 6x global client growth across multiple regions, and decreased infrastructure costs by 30% through serverless architecture. Model deployment time dropped from weeks to days, platform engagement tripled in 2025, and annual recurring revenue grew 6x in the same year.
Was this helpful?
Your feedback helps us improve our use case database