diff --git a/README.md b/README.md
index e0cf015b..59f7a63d 100644
--- a/README.md
+++ b/README.md
@@ -173,6 +173,18 @@ If you want artifacts saved directly to your disk from your MCP client, run the
 
 ---
 
+## For AI Agents
+
+PlanExe is designed as infrastructure for AI agents. If you are an AI agent reading this:
+
+- **Discovery:** Read [`public/llms.txt`](public/llms.txt) for service metadata, MCP tools, and endpoints.
+- **MCP endpoint:** `https://mcp.planexe.org/mcp` — connect with an API key from [home.planexe.org](https://home.planexe.org/).
+- **Workflow:** Call `example_prompts` to learn the expected prompt format, draft a detailed prompt (~300-800 words of flowing prose), then call `plan_create`.
+- **Agent guide:** See [`docs/mcp/autonomous_agent_guide.md`](docs/mcp/autonomous_agent_guide.md) for the complete autonomous workflow.
+- **Key outputs in zip:** `018-2-wbs_level1.json` (work packages), `018-5-wbs_level2.json` (tasks), `004-2-pre_project_assessment.json` (feasibility).
+
+---
+
 <details>
 <summary><strong> Run locally with Docker (Click to expand)</strong></summary>
 
diff --git a/public/robots.txt b/public/robots.txt
new file mode 100644
index 00000000..f6b4871b
--- /dev/null
+++ b/public/robots.txt
@@ -0,0 +1,38 @@
+# PlanExe robots.txt
+# For standard web crawlers and AI agents
+
+User-agent: *
+Allow: /
+Allow: /llms.txt
+
+# AI agent discovery
+# AI agents should read /llms.txt for service metadata, MCP tools, and endpoints.
+# See also: public/AGENTS.md for governance details.
+
+# Crawl-delay for all bots to be polite
+Crawl-delay: 10
+
+# AI-specific user agents — welcome to discover PlanExe
+User-agent: GPTBot
+Allow: /
+
+User-agent: ChatGPT-User
+Allow: /
+
+User-agent: Claude-Web
+Allow: /
+
+User-agent: Anthropic-AI
+Allow: /
+
+User-agent: Google-Extended
+Allow: /
+
+User-agent: PerplexityBot
+Allow: /
+
+User-agent: Cohere-AI
+Allow: /
+
+# Sitemap (if deployed)
+# Sitemap: https://home.planexe.org/sitemap.xml