diff --git a/docs/configuration/ui.md b/docs/configuration/ui.md
index 548566375..713e45f4d 100644
--- a/docs/configuration/ui.md
+++ b/docs/configuration/ui.md
@@ -78,6 +78,10 @@ ui = lmai.ExplorerUI(
 
 1. Tuples of (Material icon name, button text)
 
+### Follow-up suggestions
+
+After each successful query, a lightbulb icon appears in the message footer. Click it to generate an AI-powered follow-up question that references actual column names from your data. The suggestion populates the chat input so you can review or edit before sending.
+
 ## Advanced parameters
 
 ### Enable chat logging
diff --git a/lumen/ai/coordinator/base.py b/lumen/ai/coordinator/base.py
index e79f04950..0048d24db 100644
--- a/lumen/ai/coordinator/base.py
+++ b/lumen/ai/coordinator/base.py
@@ -27,7 +27,7 @@
 from ..config import PROMPTS_DIR, MissingContextError
 from ..context import TContext
 from ..llm import LlamaCpp, Llm, Message
-from ..models import ThinkingYesNo
+from ..models import FollowUpSuggestion, ThinkingYesNo
 from ..report import ActorTask, Section, TaskGroup
 from ..tools import MetadataLookup, Tool, VectorLookupToolUser
 from ..tools.document_llm_tools import make_document_vector_llm_tools
@@ -301,6 +301,11 @@ class Coordinator(Viewer, VectorLookupToolUser):
                 "template": PROMPTS_DIR / "Coordinator" / "tool_relevance.jinja2",
                 "response_model": ThinkingYesNo,
             },
+            "follow_up": {
+                "template": PROMPTS_DIR / "Coordinator" / "follow_up_suggestions.jinja2",
+                "response_model": FollowUpSuggestion,
+                "llm_spec": "ui",
+            },
         },
     )
 
@@ -554,6 +559,45 @@ async def _check_tool_relevance(self, tool: Tool, tool_output: str, actor: Actor
 
         return result.yes
 
+    async def suggest_follow_up(self, plan: Plan) -> str | None:
+        """Generate a single follow-up suggestion from a completed plan.
+
+        Returns a suggestion query string, or None on failure.
+        """
+        pipeline = plan.out_context.get("pipeline")
+        if pipeline is None:
+            return None
+
+        data_summary = plan.out_context.get("data", "")
+        if not data_summary:
+            return None
+
+        sql = plan.out_context.get("sql", "")
+        previous_queries = [
+            m["content"] for m in plan.history
+            if m.get("role") == "user"
+        ]
+        output_type = "chart" if plan.out_context.get("view") else "table"
+
+        try:
+            result = await self._invoke_prompt(
+                "follow_up",
+                messages=[{"role": "user", "content": "Generate a follow-up suggestion."}],
+                context=plan.out_context,
+                data_summary=data_summary,
+                sql=sql,
+                output_type=output_type,
+                previous_queries=previous_queries,
+            )
+            return result.query
+        except Exception as e:
+            if state.notifications:
+                state.notifications.warning(
+                    f"Could not generate follow-up suggestion: {e}",
+                    duration=3000,
+                )
+            return None
+
     def __panel__(self):
         return self.interface
 
diff --git a/lumen/ai/models.py b/lumen/ai/models.py
index 271dd1abb..451dc632c 100644
--- a/lumen/ai/models.py
+++ b/lumen/ai/models.py
@@ -29,6 +29,13 @@ def model_post_init(self, __context):
             raise MissingContextError(self.insufficient_context_reason)
 
 
+class FollowUpSuggestion(BaseModel):
+    query: str = Field(
+        description="A single dataset-specific follow-up question referencing actual column names",
+        max_length=100
+    )
+
+
 class ErrorDescription(BaseModel):
     """
     Represents a user-facing error explanation.
diff --git a/lumen/ai/prompts/Coordinator/follow_up_suggestions.jinja2 b/lumen/ai/prompts/Coordinator/follow_up_suggestions.jinja2
new file mode 100644
index 000000000..79d7749f3
--- /dev/null
+++ b/lumen/ai/prompts/Coordinator/follow_up_suggestions.jinja2
@@ -0,0 +1,31 @@
+{% extends 'Actor/main.jinja2' %}
+
+{% block instructions %}
+Suggest ONE concise follow-up question based on the user's query and the resulting data.
+
+Rules:
+- MUST reference specific column names from the data summary
+- Keep it short and actionable (under 100 characters)
+- Do NOT repeat any previous queries
+- Do NOT suggest analyses the data cannot support
+{% endblock %}
+
+{% block examples %}
+Examples:
+- "Show revenue trend over date by product"
+- "Compare revenue across region"
+- "Filter to top 5 products by revenue"
+{% endblock %}
+
+{% block context %}
+Data Summary:
+{{ data_summary }}
+{% if sql %}
+SQL Executed: {{ sql }}
+{% endif %}
+Output Type: {{ output_type }}
+{% if previous_queries %}
+Previous Queries (do NOT repeat):
+{% for q in previous_queries %}- {{ q }}
+{% endfor %}{% endif %}
+{% endblock %}
diff --git a/lumen/ai/ui.py b/lumen/ai/ui.py
index 0629e03a1..0bee6eefe 100644
--- a/lumen/ai/ui.py
+++ b/lumen/ai/ui.py
@@ -1664,6 +1664,50 @@ async def _add_analysis_suggestions(self, plan: Plan):
             num_objects=len(self.interface.objects),
         )
 
+    def _add_follow_up_icon(self, plan: Plan):
+        """Add follow-up suggestion icon to the last message footer.
+
+        The icon appears immediately. On click, it calls the coordinator
+        to generate a suggestion and populates the chat input.
+        """
+
+        async def _generate_follow_up():
+            follow_up_button.disabled = True
+            follow_up_button.description = "Generating suggestion..."
+            try:
+                suggestion = await self._coordinator.suggest_follow_up(plan)
+                if suggestion:
+                    self._chat_input.value = suggestion
+            finally:
+                follow_up_button.disabled = False
+                follow_up_button.description = "Suggest a follow-up question"
+
+        if not plan.out_context.get("pipeline"):
+            return
+        if not plan.out_context.get("data"):
+            return
+
+        follow_up_button = IconButton(
+            icon="lightbulb",
+            description="Suggest a follow-up question",
+            size="small",
+            icon_size="0.9em",
+            margin=(5, 0),
+            on_click=lambda _: state.execute(_generate_follow_up),
+            name="FollowUp",
+            disabled=self.interface.param.loading,
+            color="default",
+            sx={"color": "#FFD700", "padding": "0 0.1em"},
+        )
+
+        if len(self.interface):
+            message = self.interface.objects[-1]
+            existing = [
+                obj for obj in (message.footer_objects or [])
+                if getattr(obj, 'name', '') != "FollowUp"
+            ]
+            message.footer_objects = existing + [follow_up_button]
+
     def __panel__(self):
         return self._main
 
@@ -2566,6 +2610,7 @@ async def _postprocess_exploration(
             await self._sync_sources(SimpleNamespace(new=plan.out_context), global_context=plan.out_context)
             if "pipeline" in plan.out_context:
                 await self._add_analysis_suggestions(plan)
+                self._add_follow_up_icon(plan)
 
             if is_new:
                 plan.param.watch(partial(self._update_views, exploration), "views")
diff --git a/lumen/tests/ai/test_coordinator.py b/lumen/tests/ai/test_coordinator.py
index 04510c08e..934ced906 100644
--- a/lumen/tests/ai/test_coordinator.py
+++ b/lumen/tests/ai/test_coordinator.py
@@ -24,7 +24,7 @@
 from lumen.ai.coordinator import Coordinator, Plan, Planner
 from lumen.ai.coordinator.planner import Reasoning, make_plan_model
 from lumen.ai.editors import SQLEditor
-from lumen.ai.models import ReplaceLine, RetrySpec
+from lumen.ai.models import FollowUpSuggestion, ReplaceLine, RetrySpec
 from lumen.ai.report import ActorTask
 from lumen.ai.schemas import get_metaset
 from lumen.ai.tools import FunctionTool, define_tool
@@ -566,6 +566,84 @@ async def test_process_files_duplicate_table_name():
     assert df.iloc[0, 0] == 99
 
 
+# --- Follow-up suggestion coordinator tests ---
+
+async def test_suggest_follow_up_returns_suggestion(llm):
+    """Coordinator.suggest_follow_up should return a query string."""
+    suggestion_response = FollowUpSuggestion(query="Show value by category")
+    llm.set_responses([suggestion_response])
+
+    coordinator = Coordinator(llm=llm)
+    plan = Plan(
+        ActorTask(ChatAgent(llm=llm)),
+        history=[{"content": "Sum value column", "role": "user"}],
+        title="test",
+        context={},
+    )
+    plan.out_context = {
+        "pipeline": object(),
+        "data": "columns: category, value",
+        "sql": "SELECT * FROM t",
+    }
+
+    result = await coordinator.suggest_follow_up(plan)
+    assert result == "Show value by category"
+
+
+async def test_suggest_follow_up_no_pipeline(llm):
+    """Should return None when plan has no pipeline."""
+    coordinator = Coordinator(llm=llm)
+    plan = Plan(
+        ActorTask(ChatAgent(llm=llm)),
+        history=[],
+        title="test",
+        context={},
+    )
+    plan.out_context = {}
+
+    result = await coordinator.suggest_follow_up(plan)
+    assert result is None
+
+
+async def test_suggest_follow_up_no_data(llm):
+    """Should return None when plan has no data summary."""
+    coordinator = Coordinator(llm=llm)
+    plan = Plan(
+        ActorTask(ChatAgent(llm=llm)),
+        history=[],
+        title="test",
+        context={},
+    )
+    plan.out_context = {"pipeline": object(), "data": ""}
+
+    result = await coordinator.suggest_follow_up(plan)
+    assert result is None
+
+
+async def test_suggest_follow_up_llm_failure(llm):
+    """Should return None when LLM call fails."""
+    def raise_error():
+        raise RuntimeError("LLM unavailable")
+
+    llm.set_responses([raise_error])
+
+    coordinator = Coordinator(llm=llm)
+    plan = Plan(
+        ActorTask(ChatAgent(llm=llm)),
+        history=[{"content": "test", "role": "user"}],
+        title="test",
+        context={},
+    )
+    plan.out_context = {
+        "pipeline": object(),
+        "data": "columns: a, b",
+        "sql": "SELECT * FROM t",
+    }
+
+    result = await coordinator.suggest_follow_up(plan)
+    assert result is None
+
+
 # -------------------------------------------------------------------
 # _serialize — image propagation
 # -------------------------------------------------------------------
diff --git a/lumen/tests/ai/test_ui.py b/lumen/tests/ai/test_ui.py
index f07d818bf..41fdefde4 100644
--- a/lumen/tests/ai/test_ui.py
+++ b/lumen/tests/ai/test_ui.py
@@ -15,6 +15,7 @@
 except ModuleNotFoundError:
     pytest.skip("lumen.ai could not be imported, skipping tests.", allow_module_level=True)
 
+from panel.io import state
 from panel.layout import Column, Row
 from panel.tests.util import async_wait_until
 from panel.util import edit_readonly
@@ -26,7 +27,7 @@
 from lumen.ai.config import PROVIDED_SOURCE_NAME
 from lumen.ai.coordinator import Plan
 from lumen.ai.editors import SQLEditor
-from lumen.ai.models import ErrorDescription
+from lumen.ai.models import ErrorDescription, FollowUpSuggestion
 from lumen.ai.report import ActorTask
 from lumen.ai.schemas import get_metaset
 from lumen.ai.ui import UI, Exploration, ExplorerUI
@@ -1610,3 +1611,128 @@ async def noop_callback(contents, user, instance):
     # Parent and Home still intact
     assert len(ui._explorations.items) == 2
     assert parent_exploration.plan is not None
+
+
+# --- Follow-up suggestions tests ---
+
+def _get_footer_objects(msg):
+    """Get footer objects from message."""
+    return msg.footer_objects or []
+
+
+def test_follow_up_suggestion_model():
+    """FollowUpSuggestion model should validate correctly."""
+    result = FollowUpSuggestion(query="Show value by category")
+    assert result.query == "Show value by category"
+
+
+def test_follow_up_suggestion_model_max_length():
+    """FollowUpSuggestion should reject queries over 100 characters."""
+    with pytest.raises(Exception):
+        FollowUpSuggestion(query="x" * 101)
+
+
+async def test_follow_up_icon_after_query(explorer_ui):
+    """After a successful SQL query, a follow-up icon should appear in footer (no LLM call)."""
+    ui = explorer_ui
+    test_source = ui.context["source"]
+    SQLQueryWithTables = make_sql_model([(test_source.name, "test_table")])
+
+    ui.llm.set_responses([
+        SQLQueryWithTables(
+            query="SELECT SUM(value) as value_sum FROM test_table",
+            table_slug="test_sql_agg",
+            tables=["test_table"]
+        ),
+        "Summary of results",
+    ])
+
+    sql_agent = SQLAgent(llm=ui.llm)
+    chat_agent = ChatAgent(llm=ui.llm)
+    plan = Plan(
+        ActorTask(sql_agent),
+        ActorTask(chat_agent),
+        history=[{"content": "Sum value column", "role": "user"}],
+        title="Sum of value",
+        context=ui.context
+    )
+    await ui._execute_plan(plan)
+
+    last_msg = ui.interface.objects[-1]
+    follow_up_icons = [
+        f for f in _get_footer_objects(last_msg)
+        if getattr(f, 'name', '') == "FollowUp"
+    ]
+    assert len(follow_up_icons) == 1
+    assert follow_up_icons[0].icon == "lightbulb"
+
+
+async def test_follow_up_icon_not_on_error(explorer_ui_with_error):
+    """Follow-up icon should NOT appear when plan errors."""
+    ui = explorer_ui_with_error
+    await asyncio.sleep(0.3)
+
+    last_msg = ui.interface.objects[-1]
+    follow_up_icons = [
+        f for f in _get_footer_objects(last_msg)
+        if getattr(f, 'name', '') == "FollowUp"
+    ]
+    assert len(follow_up_icons) == 0
+
+
+async def test_follow_up_icon_not_shown_without_pipeline(explorer_ui):
+    """Follow-up icon should NOT appear when plan has no pipeline in context."""
+    ui = explorer_ui
+
+    chat_agent = ChatAgent(llm=ui.llm)
+    ui.llm.set_responses(["Here is my answer"])
+    plan = Plan(
+        ActorTask(chat_agent),
+        history=[{"content": "What is lumen?", "role": "user"}],
+        title="Chat only",
+        context=ui.context,
+    )
+    await ui._execute_plan(plan)
+
+    last_msg = ui.interface.objects[-1]
+    follow_up_icons = [
+        f for f in _get_footer_objects(last_msg)
+        if getattr(f, 'name', '') == "FollowUp"
+    ]
+    assert len(follow_up_icons) == 0
+
+
+async def test_follow_up_icon_description(explorer_ui):
+    """Follow-up icon should have the correct description."""
+    ui = explorer_ui
+    test_source = ui.context["source"]
+    SQLQueryWithTables = make_sql_model([(test_source.name, "test_table")])
+
+    ui.llm.set_responses([
+        SQLQueryWithTables(
+            query="SELECT SUM(value) as value_sum FROM test_table",
+            table_slug="test_sql_agg",
+            tables=["test_table"]
+        ),
+        "Summary of results",
+    ])
+
+    sql_agent = SQLAgent(llm=ui.llm)
+    chat_agent = ChatAgent(llm=ui.llm)
+    plan = Plan(
+        ActorTask(sql_agent),
+        ActorTask(chat_agent),
+        history=[{"content": "Sum value column", "role": "user"}],
+        title="Sum of value",
+        context=ui.context
+    )
+    await ui._execute_plan(plan)
+
+    last_msg = ui.interface.objects[-1]
+    follow_up_icons = [
+        f for f in _get_footer_objects(last_msg)
+        if getattr(f, 'name', '') == "FollowUp"
+    ]
+    assert len(follow_up_icons) == 1
+    assert follow_up_icons[0].description == "Suggest a follow-up question"
+    assert follow_up_icons[0].icon == "lightbulb"
diff --git a/pixi.toml b/pixi.toml
index 18b60b578..489694b4d 100644
--- a/pixi.toml
+++ b/pixi.toml
@@ -20,7 +20,7 @@ lint = ["py312", "lint"]
 [dependencies]
 bokeh = "*"
 holoviews = ">=1.17.0"
-panel-material-ui = ">=0.8.1"
+panel-material-ui = ">=0.9.1"
 hvplot = "*"
 intake = "<2"
 jinja2 = ">3.0"
diff --git a/pyproject.toml b/pyproject.toml
index 2e34a4009..512bf8568 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -42,7 +42,7 @@ dependencies = [
     "pandas",
     "panel >=1.7.5",
     "panel-graphic-walker[kernel] >=0.6.4",
-    "panel-material-ui >=0.8.1",
+    "panel-material-ui >=0.9.1",
     "panel-splitjs >=0.3.2",
     "param >=2.2.1",
     "pyarrow",