Case studies

LLM, RAG and agents

Dialogue systems on top of large language models: answers drawn strictly from the client’s knowledge base, deterministic scenarios instead of free generation, and hand-off to a human for hard cases.

5 projects in this category · ML, LLM, RAG and analytics

LLM agent with RAG

Task: Remove routine first-line consultation from the lawyer without the risk of legal hallucination.

Solution: A deterministic state machine on top of the LLM: an 8-field questionnaire drives the dialogue order, legal answers are generated only from the knowledge base index, and 14 stop factors escalate the client to a human.

Result: Metrics: acceptance suite of 110 cases, PASS 100% against a 95% acceptance threshold, no critical violations; ~980 automated tests; a legal answer without a source citation is technically impossible.

LLM · RAG

AI lawyer for personal bankruptcy

Context: A conversational agent for a law firm: it qualifies clients along the sales script, answers legal questions strictly with a citation to the source, and hands complex cases to a human lawyer. Built from scratch in Python.

RAG on client data

Task: Speed up access to team knowledge.

Solution: RAG assistants with quality control.

Result: Metrics: median response time 18s -> 6.4s (x2.8), inaccurate answers down ~43%.

LLM · RAG

Conversational assistant on client data

Context: LLM assistant with RAG: drives the dialogue script and answers from a knowledge base with business context.

LLM · RAG

RAG scenarios with business context

Context: Enterprise search and assistants on client data.

Chatbots and agents

Task: Remove routine work from sales and support.

Solution: AI dialogue agents and request orchestration.

Result: Metrics: ~68% of routine requests closed automatically, operator load down ~37%, first response about 25 sec.

Agents and bots

Telegram bot: matching and recommendations

Context: Orchestration and dialogue scenarios.

Agents and bots

Telegram bot: booking and requests

Context: Process and communication automation.

Other areas

Machine learning and data analysis Web platforms and enterprise systems Generative content Interface design and motion

Discuss a project

Describe the task, the data and the timeline. We will propose a format and an outline plan. Reply within one business day, NDA on request.

Discuss a project