
Vertex — Code Archaeologist is a developer tool designed to help developers understand unfamiliar and evolving codebases faster. As repositories grow, reading individual files is not enough to understand how the system is structured, which modules are tightly connected, where maintenance risks are concentrated, or how the architecture evolved. This information is often scattered across source code, dependencies, and Git history, forcing developers to manually piece everything together. Vertex brings these signals into a single interactive workspace by analyzing repository source code and Git history through six complementary views. Overview provides a high-level snapshot of repository structure, activity, health, and key findings. Architecture visualizes relationships between modules and highlights highly connected areas using dependency structure, fan-in, and fan-out. Dependencies provides detailed file and module relationships backed by evidence from actual source-code imports. Technical Debt identifies areas that may require greater maintenance attention. Its risk score is not a prediction of bugs; it is a maintenance/change-risk indicator based on signals such as complexity, code churn, coupling, size, and contributor concentration. History examines commits, contributors, churn, and files that frequently change together. These patterns can reveal architectural coupling that may not be obvious from the current code structure. Developer Guide helps developers entering an unfamiliar repository by identifying entry points, important modules, risky areas, and a recommended exploration path. Vertex is not intended to replace developers or simply summarize code. Its goal is to turn scattered technical information into actionable context, helping developers understand a system faster and make better-informed decisions. Ultimately, Vertex answers four questions: What is here? How is it connected? How did it evolve? Where should I look first?
10 Aug 2026

SWASTIK (Smart Workflow AI Support Triage & Knowledge) is an intelligent multi-agent orchestration platform designed to modernize customer support operations using AI-driven automation. Built on IBM watsonx Orchestrate, this system utilizes a coordinated team of autonomous agents to analyze, classify, resolve, and manage customer issues in real time. The platform includes a Supervisor Copilot that orchestrates three specialized agents: a Triage Agent to classify urgency and sentiment, a Knowledge Agent to retrieve policy-based solutions, and an Actions Agent that simulates ticket handling logic. These agents work together to generate structured insights such as issue category, priority, sentiment, suggested replies, and ticket recommendations. SWASTIK features a modern, dark-themed chat interface inspired by ChatGPT, delivering a seamless user experience for support teams. The system reduces manual effort, improves response speed, and ensures consistent, accurate customer communication across billing, technical, and account-related concerns. This project demonstrates how agentic AI can transform enterprise customer service workflows through orchestration, automation, and intelligent decision-making.
23 Nov 2025