Programming · News · 🇧🇷 Brazil
Livelo engineers report up to 50% higher productivity with AI agents
The Brazilian loyalty program brought Kiro and Amazon Q Developer to its team of about 240 engineers, with metrics and governance from day one.
- Profession
- Developer, Technology Manager
- Tools
- Kiro, Amazon Q Developer
- Source
- letsmoney.com.br ↗
- Country
- 🇧🇷 Brazil
- Report date
- October 28, 2026
- Verified on
- October 29, 2026
See more: AI for developers
What they did
In a three-month project designed by AI/R with AWS, Livelo brought the AI agents in Kiro, the AWS development environment, and Amazon Q Developer into the workflow of its engineering team, which handles digital products, new features and platform maintenance. According to CPTO Felipe Avila, AI took over repetitive tasks and the teams gained time for architecture and problem solving.
How it went
77% of engineers reported about 30% higher productivity, reaching 50% on some tasks. Active use of the tools is above 90% of the team, and the defect rate per feature fell by more than 55% over the months. Estimated savings in the first year are about US$ 700,000.
Good to know
The figures come from AI/R, which ran the project, and the productivity gains are as perceived by the engineers themselves. If you measure something similar, pair a team survey with objective data such as defects and delivery time.
The prompt
I lead a team of [number] developers working with [languages and systems]. I want to pilot an AI coding agent for [number] weeks. Build a pilot plan with: which repetitive tasks to give the agent, code review rules, the metrics to measure before and after (e.g. delivery time, defects per feature, adoption) and a short survey for the team. Also list the risks to watch.
Replace what is in [brackets]. Prompt written by us from the account, not a literal copy of the source. Do not paste other people’s personal data (privacy laws such as LGPD and GDPR apply).
Summary in our own words. Results as stated in the original account; we have not tested or audited them. Read the source ↗ Found a mistake?
Similar cases
01A leaner MCP server finds wasted AWS spend in fewer calls
A cloud architect rebuilt a 15-tool MCP server with just 4 tools, and the agent now answers where an AWS account is wasting money in 2 calls instead of 7.
02Letting the agent deploy and read production errors on its own
The founder of a deployment platform explains how they designed an MCP server to take the human out of "copy and paste the log".
03Launching a habit app solo and doing the marketing with AI
A dev created Kada, a habit app with no account and no ads, and used AI for marketing.
04Building an "internet TV" in 6 days with a team of agents
A dev created Crom TV, with 24-hour channels of YouTube videos, coordinating several AI agents.
05Asking AI for a specific algorithm for a research project
A developer skeptical of LLMs used Gemini to generate random quantum circuits in the QCOP project.
06Teaching an agent to use your bank's API
A developer created an open source skill so Codex and Claude Code can integrate with the Banco Inter API.
07Set up a 100% local AI coding environment
A junior developer integrated local models into VS Code with Ollama and Cline, with no paid APIs.
08Build a World Cup tracking website with AI help
An engineer built Central da Copa 2026 and explains why it wasn't "just asking the AI to do it."