diff --git a/.kiro/settings/mcp.json b/.kiro/settings/mcp.json
new file mode 100644
index 0000000..dfb070d
--- /dev/null
+++ b/.kiro/settings/mcp.json
@@ -0,0 +1,8 @@
+{
+  "mcpServers": {
+    "factbase": {
+      "command": "/Users/daniel/work/factbase/target/release/factbase",
+      "args": ["mcp"]
+    }
+  }
+}
diff --git a/.kiro/steering/general.md b/.kiro/steering/general.md
new file mode 100644
index 0000000..9b6db09
--- /dev/null
+++ b/.kiro/steering/general.md
@@ -0,0 +1,27 @@
+# agent-claw Project Context
+
+This is a Telegram bot running on AWS AgentCore (Bedrock) with Google Workspace integration.
+
+## Architecture
+- AgentCore runtime: Python 3.14, Strands SDK, Claude Sonnet 4.6
+- workspace_mcp Lambda: Mangum/FastMCP + workspace-mcp package, AWS_IAM Function URL auth + SigV4
+- tg-ingest Lambda: Telegram webhook ingest → SQS
+- agent-runner Lambda: SQS consumer → invokes AgentCore
+
+## Key Directories
+- agentclaw/app/agent_claw_main/ — AgentCore runtime code (Python)
+- cdk/lib/agent-claw-stack.ts — AWS infrastructure (CDK TypeScript)
+- src/lambdas/agent-runner/ — SQS → AgentCore bridge
+- src/lambdas/tg-ingest/ — Telegram webhook ingest
+- src/lambdas/workspace-mcp/ — Google Workspace MCP server
+- src/lambdas/oauth-handler/ — Google OAuth callback
+
+## Deploy
+- CDK: cd cdk && AWS_PROFILE=ai1 npx cdk deploy --require-approval never [context params]
+- AgentCore: cd agentclaw && AWS_PROFILE=ai1 agentcore deploy --yes
+- Both required for any change
+
+## Rules
+- Do NOT restart com.openclaw.vikunja-proxy
+- Do NOT use mcporter
+- Always run both deploy steps after code changes