All projects

Case study 03 / LLM applications · Conversational systems

Smart Financial Assistant

Multilingual dialogue, with deliberate control.

An FSM-controlled LLM dialogue system in English, Bengali and Hindi, with 36 automated evaluation trials.

  • LLaMA 3.1
  • Mistral 7B
  • Ollama
  • Finite-state machine
  • Evaluation

01 / Context

Problem

A multilingual dialogue system needs to handle language while maintaining a clear conversation flow. Generating a fluent answer and controlling the next dialogue step are separate engineering concerns.

The assistant supports English, Bengali and Hindi, with a finite-state machine controlling the flow around local LLM inference.

02 / Ownership

My Role

Built the multilingual LLM dialogue system with LLaMA 3.1 and Mistral 7B served through Ollama.

Implemented finite-state conversation control and a 36-trial automated evaluation pipeline to inspect dialogue behaviour across the supported languages.

03 / System design

Architecture

  1. 01User dialogue

    English · Bengali · Hindi

  2. 02State controller

    Finite-state conversation flow

  3. 03Local inference

    Ollama · LLaMA 3.1 / Mistral 7B

  4. 04Evaluation

    36 automated trials

Simplified conceptual architecture. The visual shows system structure rather than an actual conversation or measured trial result.

04 / Engineering decisions

Engineering Decisions

Separating conversation flow from model output.

The finite-state machine controls conversation flow while the local models provide language generation. This is a confirmed design choice, not a claim about an unreported failure.

TODO: Add a real failure transcript, the state transition or inference change that fixed it, and the corresponding evaluation result.

05 / Evidence

Results

3supported languages
36automated evaluation trials

The trial count describes the evaluation pipeline. Pass rate, language-specific scores, latency and model comparisons have not been supplied.

06 / Tools & capabilities

Stack

  • LLaMA 3.1
  • Mistral 7B
  • Ollama
  • Finite-state machine
  • Evaluation
Next case study

Healthcare NLP System