Updates under 30 lines sat for 65 hours. Gemini now auto-approves safe changes, saving 70k developer hours monthly.
A leading Latin American delivery platform processes over 160 million monthly orders across food, grocery, and fintech services with a team of 1,400 engineers.
Code reviews created a significant bottleneck, with developers waiting an average of 65 hours for approval even on small updates under 30 lines. This...
“A escolha pelo Google Cloud, especificamente pelo Vertex AI neste projeto, foi crucial por oferecer um modelo de IA generativa como o Gemini 2.5 Flash, que era, de longe, o mais eficiente em custo-benefício.”
Online food delivery and grocery marketplace platform in Brazil.
Cloud computing services, AI infrastructure, and data analytics platforms for enterprises.
iFood's Automated code review is part of this use case:
Related implementations across industries and use cases
Manual code reviews missed bugs and slowed delivery. AI now drafts pull request summaries and flags missing tests across 15,000 repos.
Reviewers struggled to predict how code ripples through the system. AI now flags cross-service risks that cause outages.
Classifying 100 comments took an hour, forcing sampling. Llama 3.3 now sorts every review by issue type to prioritize fixes.
Manual code reviews missed bugs and slowed delivery. AI now drafts pull request summaries and flags missing tests across 15,000 repos.
Reviewers struggled to predict how code ripples through the system. AI now flags cross-service risks that cause outages.
Recruiters juggled disconnected systems while managers fielded candidate calls from the back office. An AI now screens and engages 24/7.
16.5 hours to a first reply—on 9,500 inquiries a week. Launched the day before Black Friday, AI agents now close 42% without a human.
Tournaments running simultaneously meant an hour of manual checks each. AI agents now run them in minutes, freeing the team to be proactive.
Large AI training jobs meant fighting for preemptible slots or leaving campus. Marlowe gave any lab guaranteed multi-node access on demand.
Updates under 30 lines sat for 65 hours. Gemini now auto-approves safe changes, saving 70k developer hours monthly.
A leading Latin American delivery platform processes over 160 million monthly orders across food, grocery, and fintech services with a team of 1,400 engineers.
Code reviews created a significant bottleneck, with developers waiting an average of 65 hours for approval even on small updates under 30 lines. This...
“A escolha pelo Google Cloud, especificamente pelo Vertex AI neste projeto, foi crucial por oferecer um modelo de IA generativa como o Gemini 2.5 Flash, que era, de longe, o mais eficiente em custo-benefício.”
Online food delivery and grocery marketplace platform in Brazil.
Cloud computing services, AI infrastructure, and data analytics platforms for enterprises.
iFood's Automated code review is part of this use case:
Related implementations across industries and use cases
Manual code reviews missed bugs and slowed delivery. AI now drafts pull request summaries and flags missing tests across 15,000 repos.
Reviewers struggled to predict how code ripples through the system. AI now flags cross-service risks that cause outages.
Classifying 100 comments took an hour, forcing sampling. Llama 3.3 now sorts every review by issue type to prioritize fixes.
Manual code reviews missed bugs and slowed delivery. AI now drafts pull request summaries and flags missing tests across 15,000 repos.
Reviewers struggled to predict how code ripples through the system. AI now flags cross-service risks that cause outages.
Recruiters juggled disconnected systems while managers fielded candidate calls from the back office. An AI now screens and engages 24/7.
16.5 hours to a first reply—on 9,500 inquiries a week. Launched the day before Black Friday, AI agents now close 42% without a human.
Tournaments running simultaneously meant an hour of manual checks each. AI agents now run them in minutes, freeing the team to be proactive.
Large AI training jobs meant fighting for preemptible slots or leaving campus. Marlowe gave any lab guaranteed multi-node access on demand.