Southwest Airlines
Software development
On-premise systems, dispersed and brittle, bottlenecked every release. AI agents now run routine dev steps — hours cut to minutes.
- 2,700+ developers using Kiro agentic dev tool
Fragmented AI tools across teams excluded nontechnical staff. One shared platform now powers 2,500 employees, coders and non-coders alike.
One of the world's leading tourism companies, providing integrated travel services to 34.7 million customers.
Development teams used disparate AI coding tools with no common way to distribute agents, skills, and configurations, creating fragmentation risk....
“Using AWS, we could influence how Kiro could be shaped so that it fulfills all our agentic software development needs and supported our rollout to over 2,500 employees.”
Integrated tourism group operating airlines, hotels, cruises, and travel agencies.
Cloud computing platform and on-demand infrastructure services.
TUI Group's Software development is part of this use case:
Related implementations across industries and use cases
On-premise systems, dispersed and brittle, bottlenecked every release. AI agents now run routine dev steps — hours cut to minutes.
Building prototypes took months. Engineers now use structured markdown to guide an AI IDE in generating standardized code and test cases.
Manual coding and testing delayed reward campaigns. Now, AI automates repetitive tasks so 240 engineers focus on core architecture.
On-premise systems, dispersed and brittle, bottlenecked every release. AI agents now run routine dev steps — hours cut to minutes.
Building prototypes took months. Engineers now use structured markdown to guide an AI IDE in generating standardized code and test cases.
18 teams, siloed data, cargo checked flight-by-flight. Now one shared workspace turns bookings and campaigns into real-time decisions.
A 15-year-old payroll macro accountants feared would break. Now AI agents book payroll and cut utility compiling from 3 days to 1 hour.
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.
Fragmented AI tools across teams excluded nontechnical staff. One shared platform now powers 2,500 employees, coders and non-coders alike.
One of the world's leading tourism companies, providing integrated travel services to 34.7 million customers.
Development teams used disparate AI coding tools with no common way to distribute agents, skills, and configurations, creating fragmentation risk....
“Using AWS, we could influence how Kiro could be shaped so that it fulfills all our agentic software development needs and supported our rollout to over 2,500 employees.”
Integrated tourism group operating airlines, hotels, cruises, and travel agencies.
Cloud computing platform and on-demand infrastructure services.
TUI Group's Software development is part of this use case:
Related implementations across industries and use cases
On-premise systems, dispersed and brittle, bottlenecked every release. AI agents now run routine dev steps — hours cut to minutes.
Building prototypes took months. Engineers now use structured markdown to guide an AI IDE in generating standardized code and test cases.
Manual coding and testing delayed reward campaigns. Now, AI automates repetitive tasks so 240 engineers focus on core architecture.
On-premise systems, dispersed and brittle, bottlenecked every release. AI agents now run routine dev steps — hours cut to minutes.
Building prototypes took months. Engineers now use structured markdown to guide an AI IDE in generating standardized code and test cases.
18 teams, siloed data, cargo checked flight-by-flight. Now one shared workspace turns bookings and campaigns into real-time decisions.
A 15-year-old payroll macro accountants feared would break. Now AI agents book payroll and cut utility compiling from 3 days to 1 hour.
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.