Cases
Engineering breakdowns of real deployments: what we tried, what we threw away, and why the final system was harder than it looked at first.
Deployments
Each case study shows the problem, the system architecture, and the approaches we tried on the way there, including the ones we discarded. Under the spoiler blocks are the full engineering maps for readers who want the component-level view.
We deliberately write about mistakes and dead ends. In our experience, those explain why the system ended up the way it did and why the project took as long as it did. Without that context, the final result looks either trivial or unbelievable.
Investment Division of a Large Bank
The agent initiates the sale inside the mobile app. Seventeen triggers decide when to start the conversation, and a multi-layer compliance stack keeps the flow inside regulatory boundaries. Almost half of all changes across ten weeks came from real conversations with real clients.
One of the Largest Telecom Operators
Hundreds of thousands of tickets per month. Operators spent 15 to 25 minutes per case stitching together context from five internal systems.
Three architecture rebuilds, four approaches discarded, and more than sixty iterations on corporate tone.
Operator of an Urban Transport System
One hallucination is enough for a driver to believe the platform is down and skip a shift.
A confidence formula with 30+ parameters and eight hallucination markers. Every rule came from a concrete production failure.
In progress
We are preparing the full write-ups and will publish them as they are ready.
Top-20 Insurance Company
A live summarizer and operator copilot for the service workflow. The agent gathers ERP context, pre-fills guarantee letters and related documents, and helps with the hardest cases instead of replacing the human.
Urban Services Operator
AI agents for level-1 support in the categories where the deterministic bot kept failing. Ten high-frequency request types were automated above 80% quality, with speech analytics added on top for voice and chat QA.
National Rail Operator in Europe
A virtual senior engineer for the third line of support. The agent works with network equipment, VoIP, access control, monitoring, and track systems, combining knowledge retrieval, diagnostics, and operator-side validation.
Largest Beauty Retailer
An AI agent layer on top of Oracle CMS for twelve level-2 request categories. Agents repeat the operator workflow: receive the request, categorize it, clarify details, query internal systems, and contact counterparties without losing context between iterations.
Tell us which process you want to break down.
We will tell you whether the task fits AI agents and, if it does, outline a concrete plan.
Inquiry sent
We will reply within one business day to the email you provided.
or write directly to ilya@manaraga.ai