# Conversational AI Agent Case Study: Chatwit | DevOps TechLab

> Ask why sales changed; the agent plans, queries and explains, with follow-up questions. How DevOps TechLab built it on AWS.

- Page: https://devopstechlab.com/resources/cases/chatwit
- Last updated: 2026-11-14
- Contact: sales@devopstechlab.com · +91 90670 77200 (call or WhatsApp) · Monday to Friday, 10 AM to 7 PM IST
- This is a plain-text copy of the page above for AI tools. The page itself is the reference.

---
1. [Home](https://devopstechlab.com/)
2. [Resources](https://devopstechlab.com/resources/)
3. [Case studies](https://devopstechlab.com/resources/case-studies)
4. Chatwit

AI & GenAI AWS QueryDash Client story

Chatwit

# Evidence-backed sales answers in a conversation, without waiting for SQL

DevOps TechLab deployed an agentic AI investigation platform on Amazon Bedrock that lets Chatwit’s business users ask why sales performance changed and receive an explained, evidence-backed answer, with production data protected by read-only controls.

By Janak Thakkar, Founder & CEO, DevOps TechLab Sales analytics 6 min read

Investigate why sales performance changed and guide me through the findings.

QD

1. Planning the investigation
2. Finding the sales data
3. Running validated, read-only queries
4. Comparing periods
5. Explaining what changed, with evidence

Ask a follow-up… *↑*

Illustration

In short

Chatwit uses QueryDash, DevOps TechLab's agentic investigation platform on AWS, for sales analytics. Built on Amazon Bedrock with Amazon Nova Pro, it lets users ask why sales changed in plain language. The agent plans, writes and validates read-only SQL, then explains its findings with evidence, so users no longer wait for a technical team.

Official references: [What is Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html) · [AWS Well-Architected Framework](https://docs.aws.amazon.com/wellarchitected/latest/framework/welcome.html)

ISO 27001 · SOC 2 · Working with companies across India and abroad from Ahmedabad, in IST

## Executive summary

Chatwit’s leaders and business users kept asking the same kind of question: why did sales performance change? Every answer depended on technical staff to find the right data, write SQL, run several queries and interpret the results. DevOps TechLab deployed QueryDash, its agentic investigation platform built on Amazon Bedrock, so users can ask that question in plain language and receive a step-by-step, evidence-backed explanation. Every query is validated as read-only before it touches production data, and DevOps TechLab runs and improves the service as a managed engagement.

**Client:** Chatwit · Sales analytics

**Business problem:** Every answer to “why did sales change?” depended on technical staff writing and running SQL.

**What we delivered:** An AI investigation agent (QueryDash) on Amazon Bedrock with Amazon Nova Pro, connected read-only to Chatwit’s business data.

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

**Outcome:** Business users investigate sales performance themselves, in plain language, with evidence for every finding.

## The business challenge

Chatwit wanted its users to understand business and sales performance without waiting for a technical team. Getting to an answer meant identifying the right data, preparing SQL, running multiple queries and interpreting the results before anyone could act.

### Why it mattered

- **Decisions waited on analysts**

  Each new question had to go to technical staff, which slowed the move from a business question to an action.
- **Skilled people on repeat work**

  Technical staff spent time finding data, writing SQL and running several queries for every request.
- **Dashboards answer “what”, not “why”**

  Fixed reports show that a number moved. Explaining the cause meant connecting several data points by hand.
- **Every follow-up started again**

  There was no way to keep the context of an investigation, so each follow-up question meant another request.

## What Chatwit set out to achieve

1. Let business users investigate performance in plain language, with no SQL and no ticket queue.
2. Return explained, evidence-backed findings, not just raw numbers.
3. Keep the context of an investigation so users can ask follow-up questions.
4. Remove any risk to production data from AI-generated queries.
5. Use one platform for new questions, instead of a new analytics project for each.

## The solution: an AI analyst that investigates, not just queries

Users describe a business concern in plain language, for example *“Investigate why sales performance changed and guide me through the findings.”* The agent plans the investigation, finds the relevant data, writes and validates each query, analyses the results and decides the next step, recovering on its own when a query fails. Users watch the investigation unfold in real time and can ask follow-up questions in the same conversation.

The agent loop

**Understand the goal.** The agent restates what you are trying to find out.

### 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 Chatwit’s existing operational databases directly, read-only, instead of copying data into a new warehouse.
- **Conversations 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

Architecture as built (QueryDash platform)

| AWS service | Role in the solution |
| --- | --- |
| Amazon Bedrock · Amazon Nova Pro | Agent reasoning, planning and tool use |
| Amazon ECS on AWS Fargate · Application Load Balancer | Runs the investigation service without servers to manage |
| Amazon RDS (MySQL) · Amazon Aurora PostgreSQL | The business data the agent investigates, read-only |
| Amazon DynamoDB | Conversation and investigation memory |
| Amazon CloudFront · Amazon S3 | Delivers the web application securely |
| AWS Secrets Manager · AWS IAM | Credentials and access control |
| Amazon CloudWatch | Application, infrastructure and agent monitoring |

## How we delivered

1. 01 **Discover**

   Mapped the questions business users ask, the data behind them and how it relates, and defined secure, read-only access to production.
2. 02 **Build & onboard**

   Connected Chatwit’s data, configured Amazon Bedrock and Nova Pro, set up read-only validation and conversation memory, deployed on AWS and tested against real investigation scenarios.
3. 03 **Run**

   DevOps TechLab operates the service: monitoring the application, the AWS environment and the agent, managing credentials and access, and resolving production issues.
4. 04 **Improve**

   Ongoing tuning of agent planning, query generation and recovery, plus reviews of performance, cost and security, and new investigation scenarios as Chatwit’s needs grow.

## Business outcomes

Chatwit’s users now move from a business question to an explained answer in a single conversation, instead of a chain of requests to a technical team.

- **Self-service answers**

  Business users investigate sales performance themselves, in plain language, without SQL or a ticket queue.
- **Decisions backed by evidence**

  Each finding comes with the data, metrics and reasoning behind it, so leaders can act on it with confidence.
- **Technical teams freed up**

  Less manual SQL analysis means engineers spend less time on repeat data requests.
- **Zero write access to production**

  AI-generated queries are validated and read-only, so production data is never changed by the agent.
- **A platform, not a one-off**

  New investigation scenarios are added on the same platform, without a separate analytics project for each.

## What’s next

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

The same platform, other teams

- [**TNBT Tech** “Identify unusual operational changes and determine their likely causes.”](https://devopstechlab.com/resources/cases/tnbt)
- [**Dexlyn** “Determine the main factors affecting quarterly revenue.”](https://devopstechlab.com/resources/cases/dexlyn)
- [**Trueestate** “Investigate why property bookings declined.”](https://devopstechlab.com/resources/cases/trueestate)

**About DevOps TechLab**

DevOps TechLab is an AWS Advanced Tier Services Partner with the AWS Generative AI Competency and AWS SMB Competency. We design, build and run cloud and generative AI solutions on AWS for growing businesses, with 265+ cloud environments under management.

### Want answers like these from your own data?

Share the questions your leadership team asks most often. We will show how an AI investigation agent on Amazon Bedrock could answer them, safely and read-only.

[Next story · AI & GenAI **TNBT Tech: AI agent that finds unusual operational changes and their likely causes** Ops monitor design · 2 min read](https://devopstechlab.com/resources/cases/tnbt)

## More client stories

[AI & GenAI **Trueestate: AI agent that investigates property and booking performance**](https://devopstechlab.com/resources/cases/trueestate) [AI & GenAI **EasyGift: An AI gifting platform that turns a request into an on-budget quote in minutes**](https://devopstechlab.com/resources/cases/easygift) [AI & GenAI **The One Technologies: AI quote and proposal automation for corporate gifting**](https://devopstechlab.com/resources/cases/the-one)

Keep exploring

## The work behind this story

- [Service **AI consulting services** Assistants, chatbots and agents on Bedrock, Azure OpenAI or Vertex AI.](https://devopstechlab.com/solutions/generative-ai-data/)
- [Partner **AWS partner in India** Advanced Tier Services Partner with SMB and Generative AI Software Competencies.](https://devopstechlab.com/partners/aws/)
- [Guide **RAG on AWS, Azure or Google Cloud** AI that answers from your own documents: how it works and what it costs.](https://devopstechlab.com/resources/blog/ask-your-documents)
- [Case study **AI BI agent case study** Dexlyn: an agent that explains what drives revenue.](https://devopstechlab.com/resources/cases/dexlyn)

FAQ

## Questions about the Chatwit sales analytics agent

**Still have a question?**

Send it with the form below and an engineer will reply.

Ask us

###

The QueryDash platform behind Chatwit runs on Amazon Bedrock with Amazon Nova Pro, Amazon ECS Fargate, Aurora PostgreSQL, DynamoDB and AWS Secrets Manager. Responses stream in real time, and conversation context is kept across an investigation.

No. Every SQL statement the agent writes is validated before it runs, and write or schema-changing operations are rejected. Queries run against production data in read-only mode, and database credentials are managed securely.

No. Users ask questions in plain language. The agent finds the relevant data, writes and validates the queries, analyses the results and explains what changed. Follow-up questions keep the context of the investigation.

The agent replans or retries. If a query fails or the answer is incomplete, it adjusts its plan and tries again. It keeps going until it can explain the answer.

DevOps TechLab runs the solution and its AWS environment day to day. That covers application, infrastructure and agent monitoring, database connectivity support, troubleshooting, fixing production issues, logging, and ongoing tuning of planning and SQL generation.

Talk to an engineer

## Start with a 20-minute review. Leave with a plan.

An engineer looks at your current setup, points out what’s costing you money or risk, and tells you what we’d fix first. No sales deck, no obligation to go ahead.

[Sales and general enquiries **sales@devopstechlab.com**](mailto:sales@devopstechlab.com) [Call us **+91 90670 77200**](tel:+919067077200)

Every month you wait, the bill grows, the audit gets harder and the AI project waits another quarter.
