docs: add web dashboard section to README with screenshot

README.md

@@ -20,7 +20,7 @@ Conductor provides the patterns that work: evaluator-optimizer loops for iterati
 - **Conditional routing** - Route between agents based on output conditions
 - **Human-in-the-loop** - Pause for human decisions with Rich terminal UI
 - **Safety limits** - Max iterations and timeout enforcement
-- **Web dashboard** - Real-time DAG visualization with agent detail streaming
+- **[Web dashboard](#web-dashboard)** - Real-time workflow visualization with interactive DAG graph, live streaming, and in-browser human gates
 - **Validation** - Validate workflows before execution
 
 ## Installation
@@ -104,6 +104,33 @@ conductor run my-workflow.yaml --input question="What is Python?"
 }
 ```
 
+## Web Dashboard
+
+Conductor includes a built-in real-time web dashboard that lets you visualize and interact with your workflows as they run. Launch it with `--web`:
+
+```bash
+conductor run workflow.yaml --web --input question="What is Python?"
+```
+
+![Web Dashboard](docs/img/web-dashboard.png)
+
+**Key features:**
+
+- **Interactive DAG graph** — Zoomable, draggable workflow graph with animated edges showing execution flow and conditional routing
+- **Live agent streaming** — Watch agent reasoning, tool calls, and outputs stream in real-time as each step executes
+- **Three-pane layout** — Resizable panels for the graph, agent detail, and a tabbed output pane (Log, Activity, Output)
+- **In-browser human gates** — Respond to human-in-the-loop decision points directly in the dashboard, no terminal needed
+- **Per-node detail** — Click any node to see its prompt, metadata (model, tokens, cost), activity stream, and output
+- **Background mode** — Run with `--web-bg` to start the dashboard in the background, print the URL, and exit. Use `conductor stop` to shut it down later.
+
+```bash
+# Run in background — prints dashboard URL and exits
+conductor run workflow.yaml --web-bg --input topic="AI in healthcare"
+
+# Stop a background workflow
+conductor stop
+```
+
 ## Providers
 
 Conductor supports multiple AI providers. Choose based on your needs:

examples/parallel-research.yaml

@@ -82,16 +82,15 @@ agents:
 
       Be specific and actionable.
     output:
-      plan:
-        type: object
-        description: Structured research plan
-        properties:
-          questions:
-            type: array
-          areas:
-            type: array
-          sources:
-            type: array
+      questions:
+        type: array
+        description: 3-5 key research questions to answer
+      areas:
+        type: array
+        description: 3-4 areas to investigate
+      sources:
+        type: array
+        description: Types of sources to consult
       summary:
         type: string
         description: One-sentence plan summary
@@ -111,14 +110,11 @@ agents:
 
       Topic: {{ workflow.input.topic }}
 
-      Research Plan:
-      {{ planner.output.plan | json }}
-
-      Focus on:
-      - Academic papers and research studies
-      - University publications
-      - Scientific journals
-      - Research institutions
+      Research Questions:
+      {{ planner.output.questions | json }}
+
+      Research Areas:
+      {{ planner.output.areas | json }}
 
       Provide credible, well-sourced findings based on your knowledge.
     output:
@@ -145,14 +141,11 @@ agents:
 
       Topic: {{ workflow.input.topic }}
 
-      Research Plan:
-      {{ planner.output.plan | json }}
-
-      Focus on:
-      - Recent news articles
-      - Industry blogs and publications
-      - Case studies and real-world examples
-      - Expert opinions and commentary
+      Research Questions:
+      {{ planner.output.questions | json }}
+
+      Research Areas:
+      {{ planner.output.areas | json }}
 
       Provide findings based on your knowledge of recent and authoritative sources.
     output:
@@ -179,14 +172,11 @@ agents:
 
       Topic: {{ workflow.input.topic }}
 
-      Research Plan:
-      {{ planner.output.plan | json }}
-
-      Focus on:
-      - Technical documentation
-      - API references and specifications
-      - Implementation guides
-      - Standards and best practices
+      Research Questions:
+      {{ planner.output.questions | json }}
+
+      Research Areas:
+      {{ planner.output.areas | json }}
 
       Provide findings based on your technical knowledge.
     output:
@@ -290,7 +280,7 @@ agents:
       Topic: {{ workflow.input.topic }}
 
       Original Research Questions:
-      {{ planner.output.plan.questions | json }}
+      {{ planner.output.questions | json }}
 
       Executive Summary:
       {{ synthesizer.output.executive_summary }}
@@ -331,7 +321,7 @@ agents:
       - to: $end
         when: "{{ output.quality_score >= 7 }}"
       - to: planner
-        when: "context.iteration < 3"
+        when: "{{ context.iteration < 3 }}"
         output:
           feedback: "{{ quality_checker.output.gaps | json }}"
       - to: $end

examples/research-assistant.yaml

@@ -126,7 +126,7 @@ agents:
       - to: synthesizer
         when: "coverage >= 70"
       - to: researcher
-        when: "context.iteration < 3"
+        when: "{{ context.iteration < 3 }}"
       - to: synthesizer
 
   - name: synthesizer
@@ -218,7 +218,7 @@ agents:
       - to: $end
         when: "{{ output.passed }}"
       - to: synthesizer
-        when: "context.iteration < 5"
+        when: "{{ context.iteration < 5 }}"
       - to: $end
 
 output:

tests/test_integration/test_examples.py

@@ -80,11 +80,9 @@ def mock_handler(agent, prompt, context):
             """Mock handler for testing parallel research workflow."""
             agent_outputs = {
                 "planner": {
-                    "plan": {
-                        "questions": ["Q1", "Q2", "Q3"],
-                        "areas": ["A1", "A2"],
-                        "sources": ["academic", "web", "technical"],
-                    },
+                    "questions": ["Q1", "Q2", "Q3"],
+                    "areas": ["A1", "A2"],
+                    "sources": ["academic", "web", "technical"],
                     "summary": "Research AI in healthcare",
                 },
                 "academic_researcher": {