diff --git a/src/graph/agent.rs b/src/graph/agent.rs
index 85a6a0b..974d8b8 100644
--- a/src/graph/agent.rs
+++ b/src/graph/agent.rs
@@ -18,65 +18,111 @@ use tokio::time::timeout;
 
 const DEFAULT_TIMEOUT_SECS: u64 = 300;
 
+#[derive(Debug, PartialEq, Eq)]
+pub(super) enum AgentExecutionOutcome {
+    Continue(String),
+    FellBack(String),
+}
+
 pub struct AgentNodeExecutor;
 
 impl AgentNodeExecutor {
-    pub async fn execute(
+    pub(super) async fn execute(
         node: &AgentNode,
         state_manager: &mut StateManager,
         parent_ctx: &mut RequestContext,
         retire_peer_on_return: bool,
-    ) -> Result<String> {
-        let prompt = state_manager
-            .interpolate(&node.prompt)
-            .with_context(|| format!("Failed to interpolate prompt for agent '{}'", node.agent))?;
-
-        let graph_inputs = resolve_inputs(node, state_manager)?;
-        if let Some(inputs) = &graph_inputs {
-            let mut keys: Vec<&String> = inputs.keys().collect();
-            keys.sort_unstable();
-            debug!("Agent '{}' graph inputs: {keys:?}", node.agent);
-        }
-
-        let secs = node.timeout.unwrap_or(DEFAULT_TIMEOUT_SECS);
-        let agent_name = node.agent.clone();
-
-        let mut run_attempt = attempt_runner(move |ctx| {
-            let agent_name = agent_name.clone();
-            let prompt = prompt.clone();
-            let graph_inputs = graph_inputs.clone();
-            boxed_attempt(async move {
-                bounded_attempt(
-                    &agent_name,
-                    secs,
-                    run_agent_for_graph(ctx, &agent_name, &prompt, graph_inputs),
-                )
-                .await
-            })
-        });
-        let raw =
-            run_with_retries(node, parent_ctx, retire_peer_on_return, &mut run_attempt).await?;
-
-        // Extraction stays outside the retry loop: by this point the agent
-        // itself succeeded, so an extraction failure is never retried.
-        let output_value = match &node.output_schema {
-            Some(schema) => structured::extract(&raw, schema, parent_ctx)
-                .await
-                .with_context(|| {
-                    format!(
-                        "Agent '{}' output failed structured-output extraction",
-                        node.agent
-                    )
-                })?,
-            None => Value::String(raw.clone()),
-        };
-
-        apply_state_updates(node, state_manager, &output_value);
-
-        Ok(raw)
+    ) -> Result<AgentExecutionOutcome> {
+        let result = run(node, state_manager, parent_ctx, retire_peer_on_return).await;
+        outcome_from(node, state_manager, result)
     }
 }
 
+/// Turns the node run's final result into a routing outcome. With a
+/// `fallback` declared, any failure — retries exhausted, hard error, or
+/// extraction failure — is written into state as
+/// `"Agent node failed: <chain>"` (through the node's own state_updates /
+/// output-schema path, so the fallback node can interpolate it) and routes
+/// to the fallback. Without one the error propagates unchanged; unlike llm
+/// nodes there is no teaching bail, because agent nodes always failed loudly
+/// and callers assert on the existing "Agent 'X' failed" chains.
+fn outcome_from(
+    node: &AgentNode,
+    state_manager: &mut StateManager,
+    result: Result<String>,
+) -> Result<AgentExecutionOutcome> {
+    match result {
+        Ok(raw) => Ok(AgentExecutionOutcome::Continue(raw)),
+        Err(e) => match &node.fallback {
+            Some(fb) => {
+                warn!("agent node failed, routing to fallback '{fb}': {e:#}");
+                state_updates::apply(
+                    state_manager,
+                    &Value::String(format!("Agent node failed: {e:#}")),
+                    node.output_schema.is_some(),
+                    node.state_updates.as_ref(),
+                );
+                Ok(AgentExecutionOutcome::FellBack(fb.clone()))
+            }
+            None => Err(e),
+        },
+    }
+}
+
+async fn run(
+    node: &AgentNode,
+    state_manager: &mut StateManager,
+    parent_ctx: &mut RequestContext,
+    retire_peer_on_return: bool,
+) -> Result<String> {
+    let prompt = state_manager
+        .interpolate(&node.prompt)
+        .with_context(|| format!("Failed to interpolate prompt for agent '{}'", node.agent))?;
+
+    let graph_inputs = resolve_inputs(node, state_manager)?;
+    if let Some(inputs) = &graph_inputs {
+        let mut keys: Vec<&String> = inputs.keys().collect();
+        keys.sort_unstable();
+        debug!("Agent '{}' graph inputs: {keys:?}", node.agent);
+    }
+
+    let secs = node.timeout.unwrap_or(DEFAULT_TIMEOUT_SECS);
+    let agent_name = node.agent.clone();
+
+    let mut run_attempt = attempt_runner(move |ctx| {
+        let agent_name = agent_name.clone();
+        let prompt = prompt.clone();
+        let graph_inputs = graph_inputs.clone();
+        boxed_attempt(async move {
+            bounded_attempt(
+                &agent_name,
+                secs,
+                run_agent_for_graph(ctx, &agent_name, &prompt, graph_inputs),
+            )
+            .await
+        })
+    });
+    let raw = run_with_retries(node, parent_ctx, retire_peer_on_return, &mut run_attempt).await?;
+
+    // Extraction stays outside the retry loop: by this point the agent
+    // itself succeeded, so an extraction failure is never retried.
+    let output_value = match &node.output_schema {
+        Some(schema) => structured::extract(&raw, schema, parent_ctx)
+            .await
+            .with_context(|| {
+                format!(
+                    "Agent '{}' output failed structured-output extraction",
+                    node.agent
+                )
+            })?,
+        None => Value::String(raw.clone()),
+    };
+
+    apply_state_updates(node, state_manager, &output_value);
+
+    Ok(raw)
+}
+
 /// One boxed attempt against the ctx. Boxed (rather than an opaque
 /// `AsyncFnMut` future) because agent nodes run inside `tokio::spawn`ed map
 /// branches, where higher-ranked opaque futures trip the `Send` auto-trait
@@ -236,6 +282,7 @@ mod tests {
             output_schema: None,
             timeout: None,
             max_attempts: 1,
+            fallback: None,
             inputs: None,
             teammates: false,
         }
@@ -533,6 +580,114 @@ mod tests {
         assert!(format!("{err:#}").contains("agent node exhausted retries"));
     }
 
+    fn failure_capture_updates() -> HashMap<String, String> {
+        let mut u = HashMap::new();
+        u.insert("failure".into(), "{{output}}".into());
+        u
+    }
+
+    #[tokio::test]
+    async fn execute_failure_with_fallback_routes_and_records_the_failure() {
+        let mut ctx = plain_ctx();
+        ctx.current_depth = default_max_agent_depth();
+        let mut node = node_with("hi", Some(failure_capture_updates()));
+        node.fallback = Some("recover".into());
+        let mut state = manager_with(&[]);
+
+        let outcome = AgentNodeExecutor::execute(&node, &mut state, &mut ctx, false)
+            .await
+            .unwrap();
+
+        assert_eq!(outcome, AgentExecutionOutcome::FellBack("recover".into()));
+        let failure = state
+            .state()
+            .get("failure")
+            .and_then(Value::as_str)
+            .expect("failure text must land in state for the fallback node")
+            .to_string();
+        assert!(failure.starts_with("Agent node failed: "), "{failure}");
+        assert!(failure.contains("Agent 'test_agent' failed"), "{failure}");
+        assert!(failure.contains("Max agent depth exceeded"), "{failure}");
+    }
+
+    fn extraction_error() -> Error {
+        anyhow!("no JSON object found in output")
+            .context("Agent 'test_agent' output failed structured-output extraction")
+    }
+
+    #[test]
+    fn outcome_from_success_is_continue() {
+        let node = node_with("hi", None);
+        let mut state = manager_with(&[]);
+
+        let outcome = outcome_from(&node, &mut state, Ok("raw".into())).unwrap();
+
+        assert_eq!(outcome, AgentExecutionOutcome::Continue("raw".into()));
+    }
+
+    #[test]
+    fn outcome_from_extraction_failure_with_fallback_falls_back() {
+        let mut node = node_with("hi", Some(failure_capture_updates()));
+        node.fallback = Some("recover".into());
+        let mut state = manager_with(&[]);
+
+        let outcome = outcome_from(&node, &mut state, Err(extraction_error())).unwrap();
+
+        assert_eq!(outcome, AgentExecutionOutcome::FellBack("recover".into()));
+        let failure = state
+            .state()
+            .get("failure")
+            .and_then(Value::as_str)
+            .unwrap();
+        assert!(
+            failure.contains("structured-output extraction"),
+            "{failure}"
+        );
+        assert!(failure.contains("no JSON object found"), "{failure}");
+    }
+
+    #[test]
+    fn outcome_from_failure_without_fallback_propagates_the_error_unchanged() {
+        let node = node_with("hi", Some(failure_capture_updates()));
+        let mut state = manager_with(&[]);
+
+        let err = outcome_from(&node, &mut state, Err(extraction_error()))
+            .expect_err("no fallback must propagate");
+
+        assert_eq!(
+            format!("{err:#}"),
+            "Agent 'test_agent' output failed structured-output extraction: \
+             no JSON object found in output"
+        );
+        assert!(state.state().get("failure").is_none());
+    }
+
+    #[tokio::test]
+    async fn fallback_engages_only_after_transient_retries_exhaust() {
+        let mut ctx = plain_ctx();
+        let mut node = retryable_node(2);
+        node.fallback = Some("recover".into());
+        let mut attempts = 0u32;
+
+        let result = run_with_retries(
+            &node,
+            &mut ctx,
+            false,
+            &mut attempt_runner(|_ctx| {
+                attempts += 1;
+                boxed_attempt(async move {
+                    Err::<String, _>(anyhow!("connection error: reset by peer"))
+                })
+            }),
+        )
+        .await;
+        let mut state = manager_with(&[]);
+        let outcome = outcome_from(&node, &mut state, result).unwrap();
+
+        assert_eq!(attempts, 2, "fallback must not preempt the retry budget");
+        assert_eq!(outcome, AgentExecutionOutcome::FellBack("recover".into()));
+    }
+
     fn node_with_inputs(pairs: &[(&str, &str)]) -> AgentNode {
         let mut node = node_with("hi", None);
         node.inputs = Some(
diff --git a/src/graph/executor.rs b/src/graph/executor.rs
index 1367c88..805516d 100644
--- a/src/graph/executor.rs
+++ b/src/graph/executor.rs
@@ -1,4 +1,4 @@
-use super::agent::AgentNodeExecutor;
+use super::agent::{AgentExecutionOutcome, AgentNodeExecutor};
 use super::llm::{LlmExecutionOutcome, LlmNodeExecutor};
 use super::logging::{GraphLogger, narrate_node_complete, narrate_node_failed};
 use super::map::MapNodeExecutor;
@@ -574,8 +574,14 @@ pub(super) async fn step(
 ) -> Result<StepResult> {
     match &node.node_type {
         NodeType::Agent(agent_node) => {
-            AgentNodeExecutor::execute(agent_node, state, ctx, !step_ctx.branch_mode).await?;
-            let targets = static_next_targets(node, current, "agent", step_ctx.branch_mode)?;
+            let outcome =
+                AgentNodeExecutor::execute(agent_node, state, ctx, !step_ctx.branch_mode).await?;
+            let targets = match outcome {
+                AgentExecutionOutcome::Continue(_) => {
+                    static_next_targets(node, current, "agent", step_ctx.branch_mode)?
+                }
+                AgentExecutionOutcome::FellBack(target) => vec![target],
+            };
             Ok(StepResult::Continue(targets))
         }
         NodeType::Script(script_node) => {
@@ -828,6 +834,7 @@ mod tests {
                 output_schema: None,
                 timeout: None,
                 max_attempts: 1,
+                fallback: None,
                 inputs: None,
                 teammates,
             }),
diff --git a/src/graph/map.rs b/src/graph/map.rs
index 6d74543..2f982fc 100644
--- a/src/graph/map.rs
+++ b/src/graph/map.rs
@@ -465,6 +465,7 @@ mod tests {
             output_schema: None,
             timeout: None,
             max_attempts: 1,
+            fallback: None,
             inputs: None,
             teammates,
         })
@@ -1609,6 +1610,55 @@ nodes:
         assert_eq!(collected(&result), vec![json!("fb")]);
     }
 
+    #[tokio::test]
+    async fn map_chain_agent_failure_routes_to_fallback() {
+        if !cmd_available("python3") {
+            eprintln!("skipping: python3 not available");
+            return;
+        }
+        let ws = TestWorkspace::new();
+        ws.write_py(
+            "recover.py",
+            r#"print(json.dumps({"output": "recovered"}))"#,
+        );
+
+        let yaml = r#"
+name: chain
+start: fan_out
+settings:
+  validate_before_run: false
+initial_state:
+  items: [1, 2]
+nodes:
+  fan_out:
+    type: map
+    over: "{{items}}"
+    as: item
+    branch: worker
+    collect_into: results
+    next: done
+  worker:
+    type: agent
+    agent: no-such-agent
+    prompt: "hi"
+    fallback: recover
+  recover:
+    type: script
+    script: recover.py
+  done:
+    type: end
+    output: "{{results}}"
+"#;
+        let result = run_graph(yaml, &ws)
+            .await
+            .unwrap_or_else(|e| panic!("executor failed: {e:#}"));
+
+        assert_eq!(
+            collected(&result),
+            vec![json!("recovered"), json!("recovered")]
+        );
+    }
+
     struct Harness {
         ws: TestWorkspace,
         graph: Arc<Graph>,
diff --git a/src/graph/types.rs b/src/graph/types.rs
index b69d442..6a8c02f 100644
--- a/src/graph/types.rs
+++ b/src/graph/types.rs
@@ -243,6 +243,9 @@ pub struct AgentNode {
     #[serde(default = "default_max_attempts")]
     pub max_attempts: u32,
 
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub fallback: Option<String>,
+
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub inputs: Option<HashMap<String, String>>,
 
@@ -678,6 +681,41 @@ nodes:
         }
     }
 
+    #[test]
+    fn agent_node_fallback_parses_and_defaults_to_none() {
+        let yaml = r#"
+name: g
+start: a
+nodes:
+  a:
+    id: a
+    type: agent
+    agent: helper
+    prompt: hi
+    fallback: b
+    next: b
+  b:
+    id: b
+    type: agent
+    agent: helper
+    prompt: hi
+    next: e
+  e:
+    id: e
+    type: end
+    output: done
+"#;
+        let graph: Graph = serde_yaml::from_str(yaml).unwrap();
+        match &graph.get_node("a").unwrap().node_type {
+            NodeType::Agent(n) => assert_eq!(n.fallback.as_deref(), Some("b")),
+            _ => panic!("expected Agent variant"),
+        }
+        match &graph.get_node("b").unwrap().node_type {
+            NodeType::Agent(n) => assert!(n.fallback.is_none()),
+            _ => panic!("expected Agent variant"),
+        }
+    }
+
     #[test]
     fn agent_node_inputs_parse_optionally_and_empty_map_is_some() {
         let yaml = r#"
diff --git a/src/graph/validator.rs b/src/graph/validator.rs
index c190b1f..0fb3fde 100644
--- a/src/graph/validator.rs
+++ b/src/graph/validator.rs
@@ -719,6 +719,7 @@ impl GraphValidator {
                 .filter_map(|(_, n)| match &n.node_type {
                     NodeType::Script(s) => s.fallback.as_deref(),
                     NodeType::Llm(l) => l.fallback.as_deref(),
+                    NodeType::Agent(a) => a.fallback.as_deref(),
                     _ => None,
                 })
                 .collect();
@@ -982,12 +983,17 @@ fn declared_targets(node: &Node) -> Vec<(String, &'static str)> {
                 out.push((t.clone(), "llm 'fallback'"));
             }
         }
+        NodeType::Agent(a) => {
+            if let Some(t) = &a.fallback {
+                out.push((t.clone(), "agent 'fallback'"));
+            }
+        }
         NodeType::Map(m) => {
             out.push((m.branch.clone(), "map 'branch'"));
         }
-        // `agent`/`input`/`rag` route only via `next` (already collected
-        // above); `end` is terminal. No type-specific routing edges to add.
-        NodeType::Agent(_) | NodeType::Input(_) | NodeType::Rag(_) | NodeType::End(_) => {}
+        // `input`/`rag` route only via `next` (already collected above);
+        // `end` is terminal. No type-specific routing edges to add.
+        NodeType::Input(_) | NodeType::Rag(_) | NodeType::End(_) => {}
     }
     out
 }
@@ -1056,8 +1062,8 @@ fn main_flow_reachable(graph: &Graph) -> HashSet<String> {
 }
 
 /// Nodes reachable from `entry` over the edges a chain can follow at run
-/// time: `next` targets and script/llm `fallback`s. Approval routes and a
-/// nested map's `branch` are not followed. Neither may appear inside a
+/// time: `next` targets and script/llm/agent `fallback`s. Approval routes
+/// and a nested map's `branch` are not followed. Neither may appear inside a
 /// branch, and the validator reports them separately.
 pub(super) fn branch_subgraph(graph: &Graph, entry: &str) -> HashSet<String> {
     let mut reachable: HashSet<String> = HashSet::new();
@@ -1082,6 +1088,7 @@ pub(super) fn branch_subgraph(graph: &Graph, entry: &str) -> HashSet<String> {
         match &node.node_type {
             NodeType::Script(s) => edges.extend(s.fallback.as_ref()),
             NodeType::Llm(l) => edges.extend(l.fallback.as_ref()),
+            NodeType::Agent(a) => edges.extend(a.fallback.as_ref()),
             _ => {}
         }
         for next in edges {
@@ -1925,6 +1932,7 @@ mod tests {
                 output_schema: None,
                 timeout: None,
                 max_attempts: 1,
+                fallback: None,
                 inputs: None,
                 teammates: false,
             }),
@@ -2018,6 +2026,51 @@ mod tests {
         );
     }
 
+    #[test]
+    fn flags_missing_agent_fallback_target() {
+        let mut a = agent_node("a", "helper", Some("end"));
+        if let NodeType::Agent(ref mut an) = a.node_type {
+            an.fallback = Some("ghost".into());
+        }
+        let graph = graph_with(vec![("a", a), ("end", end_node("end"))], "a");
+
+        let result = validator().validate(&graph);
+
+        assert!(!result.is_valid());
+        assert!(
+            result
+                .errors
+                .iter()
+                .any(|e| e.message.contains("non-existent node 'ghost'")
+                    && e.message.contains("agent 'fallback'"))
+        );
+    }
+
+    #[test]
+    fn agent_fallback_target_is_not_flagged_unreachable() {
+        let mut a = agent_node("a", "helper", Some("end"));
+        if let NodeType::Agent(ref mut an) = a.node_type {
+            an.fallback = Some("recover".into());
+        }
+        let recover = agent_node("recover", "helper", Some("end"));
+        let graph = graph_with(
+            vec![("a", a), ("recover", recover), ("end", end_node("end"))],
+            "a",
+        );
+
+        let result = validator().validate(&graph);
+
+        assert!(
+            !result
+                .warnings
+                .iter()
+                .any(|w| w.node_id.as_deref() == Some("recover")
+                    && w.message.contains("unreachable")),
+            "fallback target 'recover' incorrectly marked unreachable: {:?}",
+            result.warnings
+        );
+    }
+
     #[test]
     fn detects_two_node_cycle() {
         let mut a = end_node("a");
@@ -2857,6 +2910,62 @@ mod tests {
         );
     }
 
+    #[test]
+    fn map_branch_agent_fallback_escaping_the_branch_gets_hint() {
+        let map = map_node_basic("m", "br", Some("end"));
+        let mut branch = agent_node("br", "helper", None);
+        if let NodeType::Agent(ref mut an) = branch.node_type {
+            an.fallback = Some("end".into());
+        }
+        let graph = graph_with(
+            vec![("m", map), ("br", branch), ("end", end_node("end"))],
+            "m",
+        );
+
+        let result = validator().validate(&graph);
+
+        assert!(
+            result.errors.iter().any(|e| e.message.contains("'end'")
+                && e.message.contains("end node")
+                && e.message.contains("never honored")
+                && e.node_id.as_deref() == Some("m")),
+            "expected end-node error with the fallback hint: {:?}",
+            result.errors
+        );
+    }
+
+    #[test]
+    fn map_branch_agent_fallback_to_branch_local_node_passes() {
+        let map = map_node_basic("m", "br", Some("end"));
+        let mut branch = agent_node("br", "helper", None);
+        if let NodeType::Agent(ref mut an) = branch.node_type {
+            an.fallback = Some("recover".into());
+        }
+        let recover = agent_node("recover", "helper", None);
+        let graph = graph_with(
+            vec![
+                ("m", map),
+                ("br", branch),
+                ("recover", recover),
+                ("end", end_node("end")),
+            ],
+            "m",
+        );
+
+        let result = validator().validate(&graph);
+
+        // Agent-existence errors on 'br'/'recover' are expected (no agent
+        // dirs in the test cwd); branch-locality errors land on the map.
+        assert!(
+            !result
+                .errors
+                .iter()
+                .any(|e| e.node_id.as_deref() == Some("m")),
+            "a branch-local agent fallback is allowed: {:?}",
+            result.errors
+        );
+    }
+
     #[test]
     fn map_branch_deep_approval_node_errors_on_the_map() {
         let map = map_node_basic("m", "br", Some("end"));