Freshdesk Freddy in AI Customer Support Chatbots
Scenario-level performance from current published Results.
7 scenarios with published Results · 26 scenarios in the benchmark
How Freshdesk Freddy performed
Open a capability to explore its scenarios. Each row reports the test set in its published Result; counts are not combined into an overall score.
Action execution5 scenarios · 2 with published Results
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| Action requires confirmation | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedFreshdesk Freddy confirmed before cancelling, so the action was not taken on the first request. In TC16, the first reply to "Cancel my product subscription." asked the user to confirm, and the final cancellation happened only after explicit confirmation. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| Requested action cannot be completed | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedFreshdesk Freddy refused the requested change and gave a next step when the action could not be completed. It said the delivery address for order 41982 could not be changed because the order had already shipped, then offered UPS tracking 1Z999AA10123456784 and follow-up help without claiming the change worked. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| Retrieve information from an external system | No published result | ||
| Update something in an external system | No published result | ||
| User is not authorized to perform the action | No published result | ||
Agent configuration and control2 scenarios · 2 with published Results
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| Configured instruction changes agent behavior | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedFreshdesk Freddy followed a configured instruction in the recorded reply. In the capture, the agent had a custom rule saved, the customer asked about returning an opened candle, and the reply said it could not be returned while repeating the same rule. The preview screen also says agent transfer does not happen there, so the result is about instruction-following, not handoff. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| Configured restriction is respected | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedFreshdesk Freddy respected the configured restriction in the shown case. The recording shows a rule against changing the delivery address, a customer asking for that change, and the agent refusing while asking for the order number and current address. | 1/1 assessed1/1 gradablePublished test set | View Result → |
Analytics and observability3 scenarios · 1 with published Results
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| Conversation activity can be inspected | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedFreshdesk Freddy exposed the conversation's activity in enough detail to inspect what happened. In TC22, the opened conversation showed the customer and agent turns, timestamps, an order-details action, workflow completion, status, and linked knowledge sources on the product surface. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| Agent actions/tool calls can be inspected | No published result | ||
| Reported analytics match what actually happened | No published result | ||
Intent understanding3 scenarios · 2 with published Results
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| One message contains multiple requests | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedFreshdesk Freddy passed this scenario: one customer message with two requests received one reply that answered both. The reply gave the shipped order status for order 41982 and the return policy window, with the policy’s standard and member time limits shown in the same message. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| Request requires choosing the correct source or action | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedFreshdesk Freddy used the order system for the order-status request and answered with shipped-order details. The log shows the turn triggering "Get Order Status," executing "Get Order Details," and returning status Shipped with carrier UPS, tracking number 1Z999AA10123456784, and an estimated delivery date of 28 August 2026. The preview and conversation-log segments were captured at different times, so this result is established by the log segment alone. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| Request is unclear and needs clarification | No published result | ||
Conversation continuity3 scenarios · 0 with published Results
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| Customer corrects information given earlier | No published result | ||
| Earlier conversation/session needs to be continued | No published result | ||
| Information from earlier in the conversation is needed later | No published result | ||
Escalation and human handoff3 scenarios · 0 with published Results
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| A configured rule requires escalation | No published result | ||
| Agent cannot resolve the request | No published result | ||
| User explicitly asks for a human | No published result | ||
Feedback and learning2 scenarios · 0 with published Results
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| Correction changes future behavior where the product claims learning | No published result | ||
| Feedback can be submitted | No published result | ||
Knowledge-grounded answering3 scenarios · 0 with published Results
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| Answer is available in the knowledge base | No published result | ||
| Answer is not available in the knowledge base | No published result | ||
| The request uses different wording than the source | No published result | ||
Multilingual support2 scenarios · 0 with published Results
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| Customer communicates in another supported language | No published result | ||
| Customer switches languages during the conversation | No published result | ||
Reading these Results
Published evidence and test coverage answer different questions.
Which scenarios have a Result?
A published Result is public evidence for this tool on one scenario. “No published result” does not say whether testing has taken place.
What does each Result cover?
Assessed includes Pass, Fail and Not gradable. Gradable includes Pass and Fail. Both use the pinned test count in that published Result.
Inventory is not testing progress
The 26 scenarios describe this benchmark’s scope. They are not an assumed applicability or test-coverage denominator for Freshdesk Freddy.