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.
Build an agent
Pick a persona, give it a goal, hand it tools. The wizard composes a system prompt you can see, then streams Claude's response with every tool call visible.
Research fire-dept grants
A real Claude Code skill, repurposed as a web-runnable agent. Drop in a township's details and the agent web-searches FEMA, USDA, Indiana OCRA, Firehouse Subs and the rest, then produces a structured report.
How this is built
Nothing fancy — just the pieces, wired correctly.
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.
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.
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 Butler — Chief 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