Home/Lab
Lab

Working demos and experiments

Hands-on builds showing AI concepts in practice — not slides, not theory. Each lab ships with source code, a live demo, and an honest writeup.


Latest
liveClaude Haiku · Neon Postgres · SSE · Next.js

Why Are We Always Late?

A CFO-facing agent that diagnoses why a month-end close keeps running late, tracing the recurring cause through system evidence and attributed interview testimony, and predicts the next occurrence before it happens. Proposes a controlled corrective action with a real authorization boundary — approval never grants authority, and the tool re-checks the acting role after every approval, against a live Postgres audit trail.

AgentsGovernanceClaudeSAP
Open live demo ↗
live

What Is an Agent?

A beginner lab that explains what an AI agent actually is. Learn how models, tools, tool definitions, agent loops, memory, and the harness work through a simple enterprise leave assistant with exactly two tools. Ask it a question and watch every decision in a safe execution trace: which tool it picked, with what input, and what came back. Level: Beginner. Time: 10 to 15 minutes.

AgentsTool CallingLangChainGroq
Open live demo ↗
live

When Does Fine-Tuning Earn Its Keep?

The same conversation run live through three models, base BART, a fine-tuned BART, and Claude Haiku, side by side with cost and latency. A working demo plus a CIO decision framework: prompt first, RAG for missing facts, and fine-tune only for proprietary judgment, volume economics, or data that can't leave.

AI/MLFine-tuningLLMsInference Economics
Open live demo ↗
live

Procurement Exception Triage Agent

An enterprise agentic AI pilot on Claude Haiku. The agent investigates delayed POs, blocked invoices, and vendor risk through governed MCP tools — with a deterministic $25K approval hook, structured errors, human-review escalation, live agent-loop streaming, and per-run cost tracking (~half a cent per triage).

AgentsMCPGovernanceClaude
Open live demo ↗
live

Structured Data Extraction Pipeline

A self-correcting structured output pipeline for enterprise contracts. Implements Pydantic validation schemas, self-healing retry loops, Message Batches API for 100+ documents, and a human-in-the-loop exception dashboard.

Structured OutputValidationBatches APIHITL
View lab →
live

Configuring Claude Code for a Team Workflow

Project CLAUDE.md hierarchies, path-scoped rules, an isolated forked skill, and multi-server MCP config with credential expansion — with an interactive rule-matcher demo and a knowledge-check quiz.

Claude CodeMCPDevEx
View lab →
live

MCP HTTP Transport & Tool Use

A live demo of the Model Context Protocol over HTTP. Claude uses MCP tools to manage a real file workspace — read, write, list, delete — with every tool call visible in the trace panel. Includes a deep-dive on MCP concepts.

MCPTool UseClaudeHTTP Transport
View lab →
live

Resolve: Autonomous Support Resolution on MCP

An AI agent that reconciles two siloed systems of record in real time — billing and access control — and shows every step of its reasoning in a live trace panel. Built on a real MCP client–server architecture.

MCPAgentsClaudeNext.js
View lab →
live

Fine-tuning a Language Model: A Working Demo

Side-by-side comparison of base GPT-2 vs a domain fine-tuned model. Shows exactly what fine-tuning changes — and when RAG is the better call.

AI/MLLLMsOpen Source
View lab →
Coming next
RAG Pipeline from Scratch
RAGVector DB
Multi-Agent Orchestration Deep Dive
AgentsLLMs