Why property bookings changed, answered by an AI agent on AWS

Executive summary

Trueestate needed faster insight into property and booking performance. Understanding why activity changed meant manual SQL across several data points, so insights arrived late and depended on technical expertise. DevOps TechLab deployed QueryDash, its agentic investigation platform built on Amazon Bedrock, so the team can ask questions such as why bookings declined, and receive a step-by-step, evidence-backed explanation.

Client

Trueestate · Real estate

Business problem

Explaining changes in property and booking activity needed manual SQL across several data points.

What we delivered

An AI investigation agent (QueryDash) on Amazon Bedrock with Amazon Nova Pro, connected read-only to Trueestate’s business data.

Engagement

Discovery, build and onboarding, then managed operations and continuous optimisation by DevOps TechLab.

Outcome

The team investigates property and booking performance in plain language, with evidence for every finding.

The business challenge

Understanding why property and booking activity changed meant writing SQL across several data points and combining the results. Insights arrived late and depended on people with technical expertise.

Why it mattered

• Insights arrived late

  Explaining a change in booking activity took a manual investigation, which slowed the response.

• Data points connected by hand

  Changes in property and booking activity had to be traced across several data points manually.

• Dependence on technical staff

  Only people who could write SQL could investigate, so business questions waited.

• Every follow-up started again

  Each new question about the same drop needed another round of queries.

What Trueestate set out to achieve

1. Let the team ask property and booking questions in plain language.
2. Explain why performance changed, not just show that it did.
3. Keep investigation context for follow-up questions.
4. Protect production data from AI-generated queries.
5. Use one platform for new questions as the business grows.

The solution: an AI agent that investigates property performance

The team asks a question such as “Investigate why property bookings declined.” The agent plans the investigation, explores the relevant data, generates and validates each query, analyses the results and shows the evidence behind its explanation, recovering on its own when a query fails.

Key design choices

• Managed generative AI

  Amazon Bedrock with Amazon Nova Pro handles reasoning and tool use. There are no models to host and no GPU infrastructure to run.

• No servers to manage

  The application runs on Amazon ECS on AWS Fargate behind an Application Load Balancer, so it scales with demand.

• Works on the data where it lives

  The agent queries the existing operational databases directly, read-only, instead of copying data into a new warehouse.

• Investigations that remember

  Amazon DynamoDB keeps the conversation and investigation history, so follow-up questions build on what the agent already found.

Security and governance

For leadership, the first question about AI on production data is risk. The platform is built so that AI-generated queries never touch the database directly.

• Read-only by design

  Only read statements (SELECT, WITH, SHOW, DESCRIBE, EXPLAIN) are allowed. Any write or schema change is rejected before it runs.

• Validated before execution

  Every query the AI writes passes through a server-side validation layer. The model never has a direct line to production data.

• Protected performance

  Results are capped, so a broad question cannot turn into a runaway query on a production database.

• Managed credentials

  Database credentials sit in AWS Secrets Manager, and access is governed by AWS IAM roles, not stored in code.

Architecture on AWS

Click to enlarge

How we delivered

1. 01Discover

   Mapped the questions Trueestate’s users need answered, the data behind them and how it relates, and defined secure, read-only access to production.

2. 02Build & onboard

   Connected Trueestate’s data, configured Amazon Bedrock and Nova Pro, set up read-only validation, conversation memory and real-time streaming, and tested against representative investigation scenarios.

3. 03Run

   DevOps TechLab operates the service: monitoring the application, the AWS environment and the agent, supporting queries and resolving production issues.

4. 04Improve

   Ongoing tuning of agent planning, query generation and recovery, plus reviews of performance, cost and security as new questions are added.

Business outcomes

Trueestate’s team now moves from a drop in bookings to an evidence-backed explanation in one conversation, instead of waiting for manual analysis.

• ✓
  Faster insight into performance

  The team investigates property and booking changes themselves, in plain language.

• ✓
  Explanations, not just numbers

  The agent explores the data and shows the evidence behind each finding.

• ✓
  Context kept across questions

  Follow-up questions build on the same investigation.

• ✓
  Zero write access to production

  AI-generated queries are validated and read-only.

• ✓
  Less dependence on technical expertise

  Fewer manual SQL investigations, on a platform that extends to new questions.

What’s next

Because the architecture is reusable, Trueestate can extend the agent to new business questions without building a separate analytics workflow for each. DevOps TechLab continues to advise on new investigation scenarios and further opportunities for AI-driven automation.