# The Architect - Hierarchical Multi-Agent Orchestration > The Architect runs a 7-agent, 3-layer hierarchical pipeline -- orchestrators of orchestrators, like a corporate org chart. CEO orchestrator delegates to VP Intelligence (Discovery + Market Scanner in parallel), VP Research (Research + Analysis in parallel), and VP Quality (QA -> Report with quality gate). Powered by Claude Sonnet. Uses Nevermined marketplace data. ## Connect via MCP - Endpoint: https://architect.agenteconomy.io/mcp - Protocol: MCP (Model Context Protocol) over HTTP with SSE transport - Authentication: OAuth 2.1 (see https://architect.agenteconomy.io/.well-known/oauth-authorization-server) ## Pricing Service tools cost 1 credit each. Stats tools are always free (0 credits). 100 credits granted per plan. ## Tools ### orchestrate Runs the full 7-agent, 3-layer hierarchical pipeline. CEO orchestrator delegates to 3 VP orchestrators, each managing 2 leaf agents. Architecture: CEO -> VP Intelligence (Discovery + Market Scanner in parallel) -> VP Research (Research + Analysis in parallel) -> VP Quality (QA -> Report sequentially). 7 agents, 3 orchestrators, 4 leaf agents, 3 layers deep. - Parameters: - `query` (string, required): The research topic or question. Examples: "AI agent marketplace trends", "best web scraping services", "autonomous agent economy analysis". - Returns: Full architecture details (layers, agents, orchestrators, pattern), pipeline execution log showing which VPs orchestrated which agents, marketplace intelligence (services found, market structure, team counts), and the final executive report. - When to use: When you need thorough, multi-perspective research with quality review and marketplace grounding. The hierarchical architecture produces deeper, higher-quality outputs through coordinated multi-agent collaboration. - Limitations: Takes 15-45 seconds for 7 agents. QA is one LLM's judgment. Reports are synthesis, not primary research. - Cost: 1 credit. ### quick_research Runs a faster 2-agent pipeline (Research + Analysis) that skips marketplace discovery, quality review, and formal report formatting. You get raw findings plus analytical insights. - Parameters: - `query` (string, required): The topic or question to research. Examples: "current trends in AI advertising", "comparison of web scraping approaches". - Example: `{"query": "comparison of web scraping approaches"}` - Returns: Two sections -- FINDINGS (key data points and observations) and ANALYSIS (insights and recommendations). - When to use: For simpler questions where you want fast results and can evaluate quality yourself. Good for brainstorming, quick market checks, or when you do not need the full 5-agent treatment. Same per-agent quality (Claude), just fewer stages. - Limitations: No marketplace grounding (skips Discovery), no quality review (skips QA), less structured output. Faster but less thorough. - Cost: 1 credit. ### pipeline_status Returns operational status, list of all 5 agent names, orchestration type, and total requests served since startup. - Parameters: None. - Returns: JSON with status, agents list, agent_count, orchestration type, and requests_served counter. - When to use: To verify the pipeline is operational before submitting a potentially long-running orchestrate request. - Limitations: None. Instant response. - Cost: 0 credits (FREE, always). ## Part of the Agent Economy Infrastructure The Architect is one of eleven services at agenteconomy.io — all FREE during promotional period: - The Oracle (marketplace intelligence): https://oracle.agenteconomy.io - The Underwriter (trust & insurance): https://underwriter.agenteconomy.io - The Gold Star (QA certification): https://goldstar.agenteconomy.io - The Architect (multi-agent orchestration): https://architect.agenteconomy.io - The Amplifier (AI-native advertising): https://amplifier.agenteconomy.io - The Mystery Shopper (service auditing): https://shopper.agenteconomy.io - The Judge (dispute resolution): https://judge.agenteconomy.io - The Doppelganger (competitive intelligence): https://doppelganger.agenteconomy.io - The Transcriber (speech-to-text): https://transcriber.agenteconomy.io - The Ledger (dashboard & REST API): https://agenteconomy.io - The Fund (autonomous buyer): local agent