跳转到主要内容
Agent Evaluation provides three safety checkpoints for agentic AI systems: evaluate tool calls before execution, scan tool results before passing them back to the agent, and detect prompt injection in any text the agent is about to process.

​
The three checkpoints

Tool Call Evaluation

ALLOW / FLAG / BLOCK before a tool runs. 1.5–3.0 credits.

Tool Result Scanning

PII detection + injection check on tool output. 0.5–1.0 credits.

Prompt Injection Detection

Fast injection scan on any input text. 0.5 credits.

​
Quick example

from rail_score_sdk import RailScoreClient

client = RailScoreClient(api_key="YOUR_RAIL_API_KEY")

# 1. Check for injection in user input
injection = client.agent.detect_injection(text=user_input)
if injection.injection_detected:
    return "Invalid input detected."

# 2. Evaluate tool call before execution
tool_check = client.agent.evaluate_tool_call(
    tool_name="send_email",
    tool_input={"to": "user@example.com", "body": agent_draft},
    agent_context="Customer support agent",
)
if tool_check.recommendation == "block":
    return f"Tool call blocked: {tool_check.explanation}"

# 3. Execute the tool, then scan the result
tool_output = execute_tool(tool_name, tool_input)
result_scan = client.agent.scan_tool_result(
    tool_name="send_email",
    tool_result=tool_output,
)
if result_scan.pii_detected:
    tool_output = result_scan.redacted_result

​
What’s next

API Reference: Tool Call

Full specification for tool call evaluation.

Python SDK: Agent Evaluation

Python SDK reference for all three agent endpoints.