18 builds. The six on the map run right now, and every plum line is the same rule: nothing sends, posts, or executes until a human approves. Click any node.
A TypeScript agent with a tool-use loop and memory that spans a whole guest stay, plus a guardrail that force-escalates money, safety, and legal before the model gets a turn.
Alagà · Guest AI Agent →Wired to my n8n instance through its official MCP server. A workflow gets described in a sentence, written as SDK code, validated, created, and published without opening the editor.
n8n Workflow Builder Agent →The page engine registers three tools over stdio, so any MCP client can call the same draft-and-grade pipeline I use.
Landing Page Engine →Seven Claude Code skills hold the rules, an eight-step orchestrator runs the contract, and twelve sub-agents do the judgment-heavy authoring.
Cywareness Simulation Archive →The pattern under six of these builds: the model proposes, code decides. Severity floors, flag counts, confidence thresholds, and escalation rules live outside the prompt, where they cannot be talked out of.
MSP Ticket Triage →Each workflow carries its own locked template, and the prompt tool re-syncs Anthropic's live docs so its guidance cannot quietly go stale.
Prompt Maker →Sonnet's thinking block breaks a naive content[0].text parse, max_tokens is tuned per job, and the sim pipeline has one named seam where a better model swaps in while the deterministic half stays byte for byte.
Cywareness Simulation Archive →