# From firefighting to building: How AI agents restored our team’s core productivity

[Grab](https://yomu.fyi/company/grab) · Sneh Agrawal · Mar 19, 2026

## Summary

Grab's Analytics Data Warehouse team spent roughly 40% of their engineering bandwidth answering repetitive questions, tracing data lineage, and handling basic pipeline enhancement requests across more than 15,000 tables. To eliminate these manual investigative bottlenecks, the team implemented a multi-agent AI architecture using FastAPI, LangGraph, Redis, and PostgreSQL. Incoming requests route through two dedicated pathways: an enhancement pipeline for generating code changes and an investigation pipeline for diagnosing data anomalies. Specialized agents interact with underlying engines like Trino, GitLab, and observability platforms to query data, trace transformations, and check ongoing incidents before synthesizing findings. This system automates the context-gathering process within minutes while maintaining human-in-the-loop review for merge requests and production changes.

## Takeaways

- Grab selected a modular multi-agent architecture orchestrated with LangGraph over a monolithic model to achieve higher domain accuracy and easier debugging despite added coordination latency.
- The semi-automated enhancement pathway reads Jira requirements, validates schemas against source tables, generates DDL scripts, and creates merge requests for engineer review.
- The investigation pathway uses a Classifier to sequence queries across a Data Agent, Code Search Agent, and On-call Agent before a Summarizer resolves conflicting data into a single report.

**Tags:** [Architecture](https://yomu.fyi/topic/architecture), [Data Pipelines](https://yomu.fyi/topic/data-pipelines), [Developer Experience](https://yomu.fyi/topic/developer-experience), [LLMs](https://yomu.fyi/topic/llm)

[Read original post](https://engineering.grab.com/from-firefighting-to-building)