Demo applications from recent engineering work.
A curated set of applications and experiments I have built around voice intake, workforce matching, model comparison, planning, learning workflows, and orchestration. The demos are here so people can try the work directly and understand the engineering behind it.
Selected demos and experiments.
Each item highlights a different slice of the work: application design, backend services, data modeling, AI-assisted workflows, evaluation tooling, and deployment. Some links open public prototypes; others provide context for lab work still in progress.
Voice Intake Assistant
A browser-based voice and text interface for intake, summarization, and follow-up notes. It shows frontend audio controls, backend routing, and review-oriented conversation capture.
Workforce Intelligence
A resume and job-matching prototype that extracts skills, compares roles, scores fit, and drafts tailored materials. It demonstrates multi-user app structure, data modeling, matching logic, and refinement loops.
Model Comparison Lab
A small evaluation tool for comparing model responses, cost, tokens, latency, and output quality across providers. It is meant to make tradeoffs visible instead of treating model choice as guesswork.
Project Planning Assistant
A planning prototype that turns a goal into phases, tasks, and dependencies, then helps keep the plan updated as work changes. It demonstrates task decomposition and program-control support.
Little Monsters Study Companion
A learning workflow prototype for classes, recorded lectures, generated replay materials, flashcards, and a tutor grounded in uploaded course content.
Workflow Console
An internal beta console for experimenting with role-based workflows, build pipelines, incident RCA flows, and work queues. Sign-in required.
Agent Orchestration Lab
A behind-the-scenes note on controller-led tasks, scoped roles, provider routing, cost visibility, and review gates.
SAP BTP Experiments
Early work around SAP Business Technology Platform, cloud-native patterns, and enterprise integration. This is listed as active development, not a public demo yet.
Workflow orchestration notes.
A short note on the lab work behind some of the demos: controller-led tasks, scoped roles, provider routing, cost visibility, and human review. OSHAL is an internal working name, not a product line.
What this shows
This section is supporting context for the demo applications, not a company pitch. It explains the architecture ideas I am experimenting with behind the scenes.
The claim is deliberately narrow: beta framework engineering, demo applications, and internal proof points. Not an awarded federal system. Not a universal benchmark.
Workflow controller
Receives work, applies workflow rules, assigns roles, and moves the ticket through bounded stages.
Message queue
Message streams and queues connect controller, workers, and runtime agents.
Scoped agents
Specialist agents execute scoped work through approved harnesses, tools, and providers.
Cost and quality
Provider use, token cost, artifacts, and assumptions stay visible for review.
Reviewed delivery
Work is packaged only after review gates, not treated as unmanaged AI output.
Guardrail: This is beta lab work and supporting technical evidence. It is not a product line, deployed government platform, awarded federal performance, or a universal benchmark.
A portfolio page for hands-on work.
Agentic Federal collects demo applications, prototypes, and technical notes in one place. It is meant to support resumes, conversations, and technical review by making the work easy to find and try.
Browse the demos.
Use whatever looks interesting. The links point to demos, prototypes, and notes from active project work.
Back to demos