Skip to content
View ksokoll's full-sized avatar

Block or report ksokoll

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. invoice-booking-agent invoice-booking-agent Public

    Portfolio project: LLM-driven agent that books supplier invoices into SAP. Deterministic Coordinator with tool-calling, DDD with four bounded contexts, Constraint Hierarchy for LLM safety, pure-Pyt…

    Python

  2. customer-support-ai-ddd-refactor customer-support-ai-ddd-refactor Public

    RAG-based customer support pipeline refactored from flat-file structure to Domain-Driven Design incl. bounded contexts, Protocol-based DI, and full test suite.

    Python

  3. retail-demand-forecasting retail-demand-forecasting Public

    Retail demand forecasting benchmark comparing foundation models (Chronos-small, Chronos-2) against engineered LightGBM on large-scale retail sales data. Evaluates accuracy, covariate integration, f…

    Jupyter Notebook

  4. AI_Project_Template_V3 AI_Project_Template_V3 Public

    Minimal production-oriented AI/ML service template with modular FastAPI architecture, strict protocol-based design, typed LLM and embedding clients, optional RAG support, and enterprise-grade testi…

    Python

  5. car_damage_detection_API car_damage_detection_API Public

    An ML API that validates car damage photos for insurance claims, including quality checks, ONNX inference, DynamoDB persistence, deployed on AWS Lambda via Terraform. Built as a portfolio project, …

    HTML

  6. AI_headline_evaluator AI_headline_evaluator Public

    Production-focused collection of AI/ML systems showcasing LLM pipelines, RAG, and classical ML. Emphasis on clean architecture, feature engineering, evaluation layers, and production patterns (Fast…

    Python