Skip to content
AI agents, in practice

What AI agents look like when they actually do work.

Most "AI demos" hide the work. This one shows it — the system prompt, the tool calls, the streaming output, the cost. Build your own agent in 60 seconds, or run a real-world grants researcher and watch it scrape the FEMA / USDA / Indiana grant landscape live.

How this is built

Nothing fancy — just the pieces, wired correctly.

Static + streaming

Next.js exported to S3 + CloudFront. The agent runner is a Lambda Function URL with RESPONSE_STREAM — SSE all the way to the browser, no WebSockets.

Provider-agnostic

A small ProviderAdapter interface around Anthropic Claude (wired now), with OpenAI and Bedrock adapters slotting in next. The agent loop doesn't care which one runs.

Quota & cost-capped

Cognito guest identity gates per-visitor daily runs. A daily $-cap CloudWatch alarm trips an SSM circuit breaker the runner reads on every invocation.

Who built this

Tim ButlerChief Technology Officer

Hands-on software engineering leader with 20+ years cultivating people and AI agentic teams to design and deliver technical platforms and the service offerings that make them sticky. Currently CTO at Spektrum Labs, where the work centers on AI-orchestrated control monitoring, integration mapping (granted patent US12299162), and a turn-based LLM framework built on custom MCP and RAG.

Ask my resume anything