Customer Agent: Objection Handling
Monitors the agent's ability to handle customer objections, disinterest, hesitation, or refusals effectively and politely.
Customer Agent Objection Handling checks how an agent responds when a customer pushes back, hesitates, or declines an offer. Run it to confirm the agent backs off gracefully instead of pressuring the user.
What it does
Customer Agent Objection Handling is an LLM-as-Judge eval. It reads the full conversation and scores how well the agent handles objections raised by the customer.
Input
| Required Input | Type | Description |
|---|---|---|
conversation | string | The full conversation history between the customer and agent |
Output
| Field | Type | Description |
|---|---|---|
| Result | never / occasionally / frequently / always | Indicates how well the agent handles objections |
| Reason | string | A plain-language explanation of the objection handling assessment |
Run it from code
Call evaluate() with the template name and the eval’s required inputs. It returns the score and the reason.
Note
Before running: install the SDK and set FI_API_KEY / FI_SECRET_KEY. The model argument in the snippets is the evaluator model Future AGI uses to run the eval; turing_flash is a fast default.
from fi.evals import evaluate
result = evaluate(
"customer_agent_objection_handling",
conversation="User: I'm not interested in upgrading right now.\nAgent: I completely understand. There's no pressure at all. If you change your mind, our upgrade offer is available anytime. Is there anything else I can help you with today?",
model="turing_flash",
)
print(result.score)
print(result.reason)import { evaluate } from "@future-agi/ai-evaluation";
const result = await evaluate(
"customer_agent_objection_handling",
{
conversation: "User: I'm not interested in upgrading right now.\nAgent: I completely understand. There's no pressure at all. If you change your mind, our upgrade offer is available anytime. Is there anything else I can help you with today?"
},
{ modelName: "turing_flash" }
);
console.log(result);When to use
Run Customer Agent Objection Handling on agents that make offers, upsells, or requests the customer might decline.
- Sales and upsell flows, to check the agent doesn’t push after a clear refusal
- Support conversations where the customer expresses hesitation or frustration
- Reviewing agent scripts for tone when a customer says no
What to do when Customer Agent Objection Handling fails
Review cases where the agent pushed back after a clear refusal, and train the agent to acknowledge objections empathetically instead of repeating the pitch. Ensure the agent doesn’t repeat sales pitches after the user has declined.
Add logic to gracefully close the topic when an objection is firm, so the conversation can move on.
Questions & Discussion