PROJECTS

AI systems built around real engineering constraints.

Autonomy is useful only when the system is observable, testable, grounded, and bounded. These projects explore those constraints through data reliability, research, support automation, and developer workflows.

01Working build
Agentic Data Reliability

Self-Healing Data Pipeline Agent

An agentic ETL system that detects schema drift, drafts controlled fixes, requires human approval, validates recovery, and automatically rolls back failed mutations.

PythonAgentic AIETLPytest
02Working build
Trustworthy AI Research

Deep Research Agent with Citation Graph

A multi-hop research agent that expands questions, retrieves evidence, builds a citation graph, grades sources, detects contradictions, and produces a traceable report.

PythonNetworkXPydanticAgentic Research
03Project build / roadmap
Agentic Operations

Autonomous Ticket Resolution Engine

An agentic support workflow designed to read tickets, inspect data, plan safe versus destructive actions, request confirmation where needed, and produce auditable resolution records.

PythonAgentic AIWorkflow OrchestrationMock DB
04Project build / roadmap
AI for Developer Workflows

CI Triage Agent

An engineering agent designed to read failing CI logs, classify errors, reproduce failures, propose code patches, validate fixes, and open approval-ready pull requests.

PythonOpenAI-compatible LLMCI/CDGit