Every evening enquiry waited overnight
Anything asked between 17:30 and 08:30 sat untouched until the next business day.
Pinkcube sells branded merchandise to Dutch and Belgian businesses that order for events with fixed dates. Evening and weekend chats used to wait for 08:30 on the next business day. The agent Ovidius built answers in Dutch or English, checks live order status and files a pre-sorted HubSpot ticket when it cannot help. It went live seven weeks after kickoff.
Up from 45 staffed hours. Every evening and weekend now has an answer.
Mean 12.0 s, against a sub-20-second target. Down from next business day.
29 Dec 2025 to 26 Aug 2026. 196 closed in the chat with no ticket.
76 hostile test scenarios before launch, 64 of them scored 5 out of 5.
Phone and chat ran Monday to Friday, 08:30 to 17:30. Four weeknight gaps of 15 hours and a 63-hour weekend added up to 123 hours with no coverage at all. Pinkcube’s buyers order for dated events. When an evening question about a print file or a delivery date goes unanswered, the buyer asks another supplier for a quote.
Anything asked between 17:30 and 08:30 sat untouched until the next business day.
Support staff arrived at 08:30 to unsorted questions with no category, no context and no order lookup done.
A B2B buyer ordering merchandise for a dated event does not wait overnight for an answer.
The Pinkcube agent answers from a knowledge base built from Pinkcube’s own resolved support conversations. The second agent, the Gatekeeper, checks every draft before the customer sees a word. It passes the draft or sends it back for a rewrite, up to ten times.
This replay follows the scenario that scored worst in testing: a customer sends two product links and asks about sizing. The agent cannot open links, so any answer about those products is a guess. Switch the Gatekeeper off to see what would have shipped.
Recreation of evaluation scenario 1, two product links and a sizing question. Message wording is illustrative; the BLOCK, the rewrite and the escalation rule follow the shipped system.
A chat agent that says “I’ve created a ticket” usually hasn’t. So the chat agent has no ticket permissions at all. A separate triage agent reads the finished conversation. Wherever the chat agent made a promise, the triage agent creates the ticket the chat agent only claimed to make.
The Chat AI conversing with the user has NO permissions to create tickets or execute actions, even if it claims otherwise.
If the Chat AI says “I have created a ticket,” “I have escalated this,” or “Support will reach out,” IT HAS NOT ACTUALLY HAPPENED.
In these cases, you MUST output true to ensure the system actually creates the ticket the Chat AI promised.
{ "status": "PASS" | "BLOCK", "reason": "VIOLATION NAME + FIX INSTRUCTION" }A BLOCK never reaches the customer. It goes back to the Pinkcube agent as a rewrite instruction.
Pick what the chat agent told the customer.
Choose a line above.
An evaluation workflow, connected to a scoring sheet, scored every scenario from 1 to 5. The agent averaged 4.62, and 64 of the 76 scored a perfect 5. The twelve that fell short became the hardcoded business rules that shipped.
“The AI provided specific information about where to find a size chart, which contradicts the expected output stating it cannot visit links or know about specific products. The core requirement of acknowledging limitations or escalating was not met.”
Measured by Ovidius in December 2025, before deployment. Grader comment quoted verbatim from the scoring sheet.
Pinkcube’s HubSpot holds master deals with sub-deals beneath them. To reach a tracking code, the lookup has to work down through each level first. The builders reverse-engineered the schema mid-build and did the extra work without moving the launch date.
Median first response, from message timestamps logged since 2 Jun 2026
Mean first response over the same period
The response target in the project requirements, met on both measures
Scope: after-hours chat on HubSpot and AfterShip.
Scored 1 to 5 before any customer saw the agent.
Seven weeks from kickoff, on the planned date.
Production chat logs counted from here.
Message timestamps added for response times.
508 tickets, 196 closed in the chat.
Coverage compares the stated support hours (Monday to Friday, 08:30 to 17:30) with a 168-hour week. Ovidius measured the quality score across 76 scenarios in December 2025, before deployment. Volume comes from production chat logs, 29 Dec 2025 to 26 Aug 2026: 704 conversations, 508 tickets created, 27.8% resolved without a ticket. Response times come from message timestamps logged since 2 Jun 2026.
Ovidius went from project vendor to standing partner, and three extensions are scoped for the next phase.
From project vendor to 2026 partner, with the after-hours agent still answering every evening and weekend.
Bring your support hours and your CRM. In a discovery call we map which questions an agent can answer and which need a person. A build like Pinkcube’s goes from kickoff to live in 5 to 7 weeks.
We use Google Analytics cookies to see which pages visitors read, so we can improve the site. Accept to allow them or reject to keep them off. Privacy policy