diff --git a/site/docs/examples/evals-sdk/chaos_failure_communication_evaluator.py b/site/docs/examples/evals-sdk/chaos_failure_communication_evaluator.py
new file mode 100644
index 000000000..d78ab0430
--- /dev/null
+++ b/site/docs/examples/evals-sdk/chaos_failure_communication_evaluator.py
@@ -0,0 +1,121 @@
+import logging
+from typing import Any
+
+from pydantic import BaseModel, Field
+
+from strands import Agent
+from strands_evals.chaos import ChaosCase, ChaosExperiment, ChaosPlugin, Timeout
+from strands_evals.chaos.effects import NetworkError
+from strands_evals.evaluators.chaos import FailureCommunicationEvaluator
+from strands_evals.mappers import StrandsInMemorySessionMapper
+from strands_evals.simulation.tool_simulator import ToolSimulator
+from strands_evals.telemetry import StrandsEvalsTelemetry
+from strands_evals.types.evaluation_report import EvaluationReport
+
+logging.basicConfig(level=logging.INFO, format="%(message)s")
+logger = logging.getLogger(__name__)
+
+telemetry = StrandsEvalsTelemetry().setup_in_memory_exporter()
+memory_exporter = telemetry.in_memory_exporter
+
+tool_simulator = ToolSimulator()
+
+
+class FlightSearchResponse(BaseModel):
+    flights: list[dict[str, Any]] = Field(default_factory=list)
+    total_results: int = Field(default=0)
+    status: str = Field(default="success")
+
+
+class BookFlightResponse(BaseModel):
+    booking_id: str = Field(default="")
+    flight_id: str = Field(default="")
+    status: str = Field(default="success")
+    message: str = Field(default="")
+
+
+@tool_simulator.tool(output_schema=FlightSearchResponse)
+def search_flights(origin: str, destination: str, date: str) -> dict[str, Any]:
+    """Search for available flights between two cities on a given date."""
+    pass
+
+
+@tool_simulator.tool(output_schema=BookFlightResponse)
+def book_flight(flight_id: str) -> dict[str, Any]:
+    """Book a specific flight by its flight ID."""
+    pass
+
+
+chaos_plugin = ChaosPlugin()
+
+# Two cases that test communication quality:
+# 1. Search times out — agent must inform user about the failure
+# 2. Both tools fail — agent must communicate multiple failures clearly
+chaos_cases = [
+    ChaosCase(
+        name="search_timeout",
+        input="Find me a flight from SFO to JFK on May 20 and book the cheapest one.",
+        effects={"tool_effects": {"search_flights": [Timeout(error_message="Tool call timed out after 30s")]}},
+    ),
+    ChaosCase(
+        name="all_tools_down",
+        input="Search for flights from Seattle to Tokyo next Tuesday and book one.",
+        effects={
+            "tool_effects": {
+                "search_flights": [NetworkError(error_message="DNS resolution failed")],
+                "book_flight": [NetworkError(error_message="Connection refused")],
+            },
+        },
+    ),
+]
+
+_search_tool = tool_simulator.get_tool("search_flights")
+_book_tool = tool_simulator.get_tool("book_flight")
+
+
+def travel_agent_task(case: ChaosCase) -> dict:
+    """Run the travel agent under chaos and return output + trajectory."""
+    logger.info(f"\n{'─'*60}")
+    logger.info(f"  Case: {case.name}")
+    logger.info(f"  User: {case.input}")
+
+    agent = Agent(
+        system_prompt=(
+            "You are a travel booking assistant. Use the available tools to complete "
+            "the user's request. Today's date is May 18, 2025.\n\n"
+            "If a tool fails or returns an error:\n"
+            "- Acknowledge the failure honestly to the user\n"
+            "- Explain what went wrong in plain language\n"
+            "- Suggest next steps (retry later, try alternative)\n"
+            "- Do NOT hallucinate successful results"
+        ),
+        tools=[_search_tool, _book_tool],
+        plugins=[chaos_plugin],
+        callback_handler=None,
+        trace_attributes={"gen_ai.conversation.id": case.session_id, "session.id": case.session_id},
+    )
+
+    memory_exporter.clear()
+    try:
+        result = agent(case.input)
+        output = str(result)
+    except Exception as e:
+        output = f"Agent failed with error: {type(e).__name__}: {str(e)[:200]}"
+
+    logger.info(f"  Agent: {output[:300]}{'...' if len(output) > 300 else ''}")
+    logger.info(f"{'─'*60}")
+
+    finished_spans = memory_exporter.get_finished_spans()
+    mapper = StrandsInMemorySessionMapper()
+    session = mapper.map_to_session(finished_spans, session_id=case.session_id)
+
+    return {"output": output, "trajectory": session}
+
+
+experiment = ChaosExperiment(
+    cases=chaos_cases,
+    evaluators=[FailureCommunicationEvaluator()],
+)
+
+reports = experiment.run_evaluations(task=travel_agent_task)
+EvaluationReport.flatten(reports).run_display()
diff --git a/site/docs/examples/evals-sdk/chaos_partial_completion_evaluator.py b/site/docs/examples/evals-sdk/chaos_partial_completion_evaluator.py
new file mode 100644
index 000000000..d247ae0aa
--- /dev/null
+++ b/site/docs/examples/evals-sdk/chaos_partial_completion_evaluator.py
@@ -0,0 +1,138 @@
+import logging
+from typing import Any
+
+from pydantic import BaseModel, Field
+
+from strands import Agent
+from strands_evals.chaos import ChaosCase, ChaosExperiment, ChaosPlugin, TruncateFields
+from strands_evals.chaos.effects import NetworkError
+from strands_evals.evaluators.chaos import PartialCompletionEvaluator
+from strands_evals.mappers import StrandsInMemorySessionMapper
+from strands_evals.simulation.tool_simulator import ToolSimulator
+from strands_evals.telemetry import StrandsEvalsTelemetry
+from strands_evals.types.evaluation_report import EvaluationReport
+
+logging.basicConfig(level=logging.INFO, format="%(message)s")
+logger = logging.getLogger(__name__)
+
+telemetry = StrandsEvalsTelemetry().setup_in_memory_exporter()
+memory_exporter = telemetry.in_memory_exporter
+
+tool_simulator = ToolSimulator()
+
+
+class FlightSearchResponse(BaseModel):
+    flights: list[dict[str, Any]] = Field(default_factory=list)
+    total_results: int = Field(default=0)
+    status: str = Field(default="success")
+
+
+class BookFlightResponse(BaseModel):
+    booking_id: str = Field(default="")
+    flight_id: str = Field(default="")
+    status: str = Field(default="success")
+    message: str = Field(default="")
+
+
+class BookingConfirmationResponse(BaseModel):
+    confirmation_sent: bool = Field(default=False)
+    method: str = Field(default="email")
+    message: str = Field(default="")
+
+
+@tool_simulator.tool(output_schema=FlightSearchResponse)
+def search_flights(origin: str, destination: str, date: str) -> dict[str, Any]:
+    """Search for available flights between two cities on a given date."""
+    pass
+
+
+@tool_simulator.tool(output_schema=BookFlightResponse)
+def book_flight(flight_id: str) -> dict[str, Any]:
+    """Book a specific flight by its flight ID."""
+    pass
+
+
+@tool_simulator.tool(output_schema=BookingConfirmationResponse)
+def send_booking_confirmation(booking_id: str = "", flight_id: str = "", method: str = "email") -> dict[str, Any]:
+    """Send booking confirmation to the user via email or SMS."""
+    pass
+
+
+chaos_plugin = ChaosPlugin()
+
+# Two cases that test partial completion:
+# 1. Search works (truncated) but booking fails — user gets degraded flight info but no reservation
+# 2. Search and booking work but confirmation fails — user gets most of what they asked for
+chaos_cases = [
+    ChaosCase(
+        name="search_degraded_booking_fails",
+        input="Find me a flight from SFO to JFK on May 20, book the cheapest one, and send me a confirmation.",
+        effects={
+            "tool_effects": {
+                "search_flights": [TruncateFields(max_length=5)],
+                "book_flight": [NetworkError(error_message="Connection reset by peer")],
+            },
+        },
+    ),
+    ChaosCase(
+        name="confirmation_fails",
+        input="Search for flights from Seattle to Tokyo next Tuesday, book one, and email me the confirmation.",
+        effects={
+            "tool_effects": {
+                "send_booking_confirmation": [NetworkError(error_message="SMTP server unreachable")],
+            },
+        },
+    ),
+]
+
+_search_tool = tool_simulator.get_tool("search_flights")
+_book_tool = tool_simulator.get_tool("book_flight")
+_confirm_tool = tool_simulator.get_tool("send_booking_confirmation")
+
+
+def travel_agent_task(case: ChaosCase) -> dict:
+    """Run the travel agent under chaos and return output + trajectory."""
+    logger.info(f"\n{'─'*60}")
+    logger.info(f"  Case: {case.name}")
+    logger.info(f"  User: {case.input}")
+
+    agent = Agent(
+        system_prompt=(
+            "You are a travel booking assistant. Use the available tools to complete "
+            "the user's request. Today's date is May 18, 2025.\n\n"
+            "If a tool fails or returns an error:\n"
+            "- Acknowledge the failure honestly\n"
+            "- Complete as much of the request as possible\n"
+            "- Do NOT hallucinate successful results\n"
+            "- Do NOT retry more than once"
+        ),
+        tools=[_search_tool, _book_tool, _confirm_tool],
+        plugins=[chaos_plugin],
+        callback_handler=None,
+        trace_attributes={"gen_ai.conversation.id": case.session_id, "session.id": case.session_id},
+    )
+
+    memory_exporter.clear()
+    try:
+        result = agent(case.input)
+        output = str(result)
+    except Exception as e:
+        output = f"Agent failed with error: {type(e).__name__}: {str(e)[:200]}"
+
+    logger.info(f"  Agent: {output[:300]}{'...' if len(output) > 300 else ''}")
+    logger.info(f"{'─'*60}")
+
+    finished_spans = memory_exporter.get_finished_spans()
+    mapper = StrandsInMemorySessionMapper()
+    session = mapper.map_to_session(finished_spans, session_id=case.session_id)
+
+    return {"output": output, "trajectory": session}
+
+
+experiment = ChaosExperiment(
+    cases=chaos_cases,
+    evaluators=[PartialCompletionEvaluator()],
+)
+
+reports = experiment.run_evaluations(task=travel_agent_task)
+EvaluationReport.flatten(reports).run_display()
diff --git a/site/docs/examples/evals-sdk/chaos_recovery_strategy_evaluator.py b/site/docs/examples/evals-sdk/chaos_recovery_strategy_evaluator.py
new file mode 100644
index 000000000..fc2903e11
--- /dev/null
+++ b/site/docs/examples/evals-sdk/chaos_recovery_strategy_evaluator.py
@@ -0,0 +1,134 @@
+import logging
+from typing import Any
+
+from pydantic import BaseModel, Field
+
+from strands import Agent
+from strands_evals.chaos import ChaosCase, ChaosExperiment, ChaosPlugin, Timeout
+from strands_evals.chaos.effects import ExecutionError
+from strands_evals.evaluators.chaos import RecoveryStrategyEvaluator
+from strands_evals.mappers import StrandsInMemorySessionMapper
+from strands_evals.simulation.tool_simulator import ToolSimulator
+from strands_evals.telemetry import StrandsEvalsTelemetry
+from strands_evals.types.evaluation_report import EvaluationReport
+
+logging.basicConfig(level=logging.INFO, format="%(message)s")
+logger = logging.getLogger(__name__)
+
+telemetry = StrandsEvalsTelemetry().setup_in_memory_exporter()
+memory_exporter = telemetry.in_memory_exporter
+
+tool_simulator = ToolSimulator()
+
+
+class FlightSearchResponse(BaseModel):
+    flights: list[dict[str, Any]] = Field(default_factory=list)
+    total_results: int = Field(default=0)
+    status: str = Field(default="success")
+
+
+class HotelSearchResponse(BaseModel):
+    hotels: list[dict[str, Any]] = Field(default_factory=list)
+    total_results: int = Field(default=0)
+    status: str = Field(default="success")
+
+
+class BookFlightResponse(BaseModel):
+    booking_id: str = Field(default="")
+    flight_id: str = Field(default="")
+    status: str = Field(default="success")
+    message: str = Field(default="")
+
+
+@tool_simulator.tool(output_schema=FlightSearchResponse)
+def search_flights(origin: str, destination: str, date: str) -> dict[str, Any]:
+    """Search for available flights between two cities on a given date."""
+    pass
+
+
+@tool_simulator.tool(output_schema=HotelSearchResponse)
+def search_hotels(city: str, check_in: str, check_out: str) -> dict[str, Any]:
+    """Search for available hotels in a city for given dates."""
+    pass
+
+
+@tool_simulator.tool(output_schema=BookFlightResponse)
+def book_flight(flight_id: str) -> dict[str, Any]:
+    """Book a specific flight by its flight ID."""
+    pass
+
+
+chaos_plugin = ChaosPlugin()
+
+# Two cases that test recovery strategy:
+# 1. Flight search times out but hotel search works — agent should pivot to hotel search
+# 2. Flight search fails permanently — agent should try once, then move on
+chaos_cases = [
+    ChaosCase(
+        name="flight_timeout_hotel_available",
+        input="Plan my trip to Tokyo: find flights from SFO and hotels for May 20-23.",
+        effects={"tool_effects": {"search_flights": [Timeout()]}},
+    ),
+    ChaosCase(
+        name="flight_and_booking_fail",
+        input="Find a flight from NYC to London on June 1 and book the cheapest option.",
+        effects={
+            "tool_effects": {
+                "search_flights": [ExecutionError(error_message="Internal server error")],
+                "book_flight": [ExecutionError(error_message="Service unavailable")],
+            },
+        },
+    ),
+]
+
+_search_flights_tool = tool_simulator.get_tool("search_flights")
+_search_hotels_tool = tool_simulator.get_tool("search_hotels")
+_book_tool = tool_simulator.get_tool("book_flight")
+
+
+def travel_agent_task(case: ChaosCase) -> dict:
+    """Run the travel agent under chaos and return output + trajectory."""
+    logger.info(f"\n{'─'*60}")
+    logger.info(f"  Case: {case.name}")
+    logger.info(f"  User: {case.input}")
+
+    agent = Agent(
+        system_prompt=(
+            "You are a travel planning assistant. Use the available tools to complete "
+            "the user's request. Today's date is May 18, 2025.\n\n"
+            "If a tool fails:\n"
+            "- Try alternative tools that can partially fulfill the request\n"
+            "- Do NOT retry the same failed tool more than once\n"
+            "- Do NOT hallucinate results\n"
+            "- Complete as much of the request as possible with working tools"
+        ),
+        tools=[_search_flights_tool, _search_hotels_tool, _book_tool],
+        plugins=[chaos_plugin],
+        callback_handler=None,
+        trace_attributes={"gen_ai.conversation.id": case.session_id, "session.id": case.session_id},
+    )
+
+    memory_exporter.clear()
+    try:
+        result = agent(case.input)
+        output = str(result)
+    except Exception as e:
+        output = f"Agent failed with error: {type(e).__name__}: {str(e)[:200]}"
+
+    logger.info(f"  Agent: {output[:300]}{'...' if len(output) > 300 else ''}")
+    logger.info(f"{'─'*60}")
+
+    finished_spans = memory_exporter.get_finished_spans()
+    mapper = StrandsInMemorySessionMapper()
+    session = mapper.map_to_session(finished_spans, session_id=case.session_id)
+
+    return {"output": output, "trajectory": session}
+
+
+experiment = ChaosExperiment(
+    cases=chaos_cases,
+    evaluators=[RecoveryStrategyEvaluator()],
+)
+
+reports = experiment.run_evaluations(task=travel_agent_task)
+EvaluationReport.flatten(reports).run_display()
diff --git a/site/docs/examples/evals-sdk/chaos_testing.py b/site/docs/examples/evals-sdk/chaos_testing.py
new file mode 100644
index 000000000..86e366103
--- /dev/null
+++ b/site/docs/examples/evals-sdk/chaos_testing.py
@@ -0,0 +1,173 @@
+import logging
+from typing import Any
+
+from pydantic import BaseModel, Field
+
+from strands import Agent
+from strands_evals import Case
+from strands_evals.chaos import (
+    ChaosCase,
+    ChaosExperiment,
+    ChaosPlugin,
+    CorruptValues,
+    NetworkError,
+    RemoveFields,
+    Timeout,
+    TruncateFields,
+)
+from strands_evals.chaos.effects import ExecutionError
+from strands_evals.evaluators import GoalSuccessRateEvaluator
+from strands_evals.mappers import StrandsInMemorySessionMapper
+from strands_evals.simulation.tool_simulator import ToolSimulator
+from strands_evals.telemetry import StrandsEvalsTelemetry
+from strands_evals.types.evaluation_report import EvaluationReport
+
+logging.basicConfig(level=logging.INFO, format="%(message)s")
+logger = logging.getLogger(__name__)
+
+# Setup telemetry
+telemetry = StrandsEvalsTelemetry().setup_in_memory_exporter()
+memory_exporter = telemetry.in_memory_exporter
+
+# 1. Set up ToolSimulator and register tools
+tool_simulator = ToolSimulator()
+
+class FlightSearchResponse(BaseModel):
+    """Response from the flight search tool."""
+
+    flights: list[dict[str, Any]] = Field(default_factory=list, description="List of available flights")
+    total_results: int = Field(default=0, description="Total number of results found")
+    status: str = Field(default="success", description="Operation status")
+
+class BookFlightResponse(BaseModel):
+    """Response from the flight booking tool."""
+
+    booking_id: str = Field(default="", description="Booking confirmation ID")
+    flight_id: str = Field(default="", description="The booked flight ID")
+    status: str = Field(default="success", description="Booking status")
+    message: str = Field(default="", description="Status message")
+
+class BookingConfirmationResponse(BaseModel):
+    """Response from the booking confirmation tool."""
+
+    confirmation_sent: bool = Field(default=False, description="Whether confirmation was sent")
+    method: str = Field(default="email", description="Delivery method")
+    message: str = Field(default="", description="Confirmation details")
+
+@tool_simulator.tool(output_schema=FlightSearchResponse)
+def search_flights(origin: str, destination: str, date: str) -> dict[str, Any]:
+    """Search for available flights between two cities on a given date."""
+    pass
+
+@tool_simulator.tool(output_schema=BookFlightResponse)
+def book_flight(flight_id: str) -> dict[str, Any]:
+    """Book a specific flight by its flight ID. Returns booking confirmation."""
+    pass
+
+@tool_simulator.tool(output_schema=BookingConfirmationResponse)
+def send_booking_confirmation(booking_id: str = "", flight_id: str = "", method: str = "email") -> dict[str, Any]:
+    """Send booking confirmation or fallback link to the user via email or SMS."""
+    pass
+
+# 2. Create the ChaosPlugin
+chaos_plugin = ChaosPlugin()
+
+# 3. Define named effect maps
+effect_maps = {
+    # Single-tool, pre-hook: tool call is cancelled before execution
+    "search_timeout": {
+        "tool_effects": {"search_flights": [Timeout()]},
+    },
+    # Two-tool, post-hook: tools execute but responses are silently corrupted
+    "book_corrupt_and_confirm_truncated": {
+        "tool_effects": {
+            "book_flight": [CorruptValues(corrupt_ratio=0.8)],
+            "send_booking_confirmation": [TruncateFields(max_length=5)],
+        },
+    },
+    # All-tool, mixed pre+post: combines hard failures with silent corruption
+    "total_chaos": {
+        "tool_effects": {
+            "search_flights": [NetworkError()],
+            "book_flight": [ExecutionError()],
+            "send_booking_confirmation": [RemoveFields(remove_ratio=0.7)],
+        },
+    },
+}
+
+# 4. Define the task function
+# Pre-create tool instances once (avoids registry issues across runs)
+_search_tool = tool_simulator.get_tool("search_flights")
+_book_tool = tool_simulator.get_tool("book_flight")
+_confirm_tool = tool_simulator.get_tool("send_booking_confirmation")
+
+def travel_agent_task(case: ChaosCase) -> dict:
+    """Run the travel agent with a single user query."""
+    logger.info(f"\n{'─'*60}")
+    logger.info(f"  Case: {case.name}")
+    logger.info(f"  User: {case.input}")
+
+    agent = Agent(
+        system_prompt=(
+            "You are a travel booking assistant. You help users search for flights, "
+            "book them, and send confirmations. Use the available tools to complete "
+            "the user's request. Today's date is May 18, 2025.\n\n"
+            "Always use the tools directly — do not ask the user for clarification "
+            "if you can infer reasonable values from context.\n\n"
+            "If a tool fails or returns an error:\n"
+            "- Acknowledge the failure honestly to the user\n"
+            "- Try an alternative approach if possible\n"
+            "- Do NOT hallucinate successful results\n"
+            "- Do NOT retry more than once\n\n"
+            "If tool results look suspicious (e.g., $0 fares, past dates):\n"
+            "- Inform the user that results seem unreliable\n"
+            "- Suggest alternatives"
+        ),
+        tools=[_search_tool, _book_tool, _confirm_tool],
+        plugins=[chaos_plugin],
+        callback_handler=None,
+        trace_attributes={"gen_ai.conversation.id": case.session_id, "session.id": case.session_id},
+    )
+
+    memory_exporter.clear()
+    try:
+        result = agent(case.input)
+        output = str(result)
+    except Exception as e:
+        output = f"Agent failed with error: {type(e).__name__}: {str(e)[:200]}"
+
+    logger.info(f"  Agent: {output[:300]}{'...' if len(output) > 300 else ''}")
+    logger.info(f"{'─'*60}")
+
+    finished_spans = memory_exporter.get_finished_spans()
+    mapper = StrandsInMemorySessionMapper()
+    session = mapper.map_to_session(finished_spans, session_id=case.session_id)
+
+    return {"output": output, "trajectory": session}
+
+# 5. Define test cases and expand with effect maps
+test_cases = [
+    Case(
+        name="book_a_flight",
+        input="Find me a flight from SFO to JFK on May 20, book the cheapest one, and send me a confirmation.",
+    ),
+    Case(
+        name="search_and_confirm",
+        input="Search for flights from Seattle to Tokyo next Tuesday, book one, and email me the confirmation.",
+    ),
+]
+
+# Expand: 2 cases × (3 effect maps + 1 baseline) = 8 ChaosCase objects
+chaos_cases = ChaosCase.expand(test_cases, effect_maps, include_no_effect_baseline=True)
+
+# 6. Create and run the ChaosExperiment
+evaluators = [GoalSuccessRateEvaluator()]
+
+experiment = ChaosExperiment(
+    cases=chaos_cases,
+    evaluators=evaluators,
+)
+
+# Run: 8 chaos cases = 8 agent invocations
+reports = experiment.run_evaluations(task=travel_agent_task)
+EvaluationReport.flatten(reports).run_display()