AI solutions

How Fruition redesigned assessments with Vocina

Learn about how we created, tested and implemented an oral AI agent with Fruition.

5 minutes Written by Zoe Morgan

What we were tasked with

In 2025, the Food and Fibre Centre for Vocational Excellence (FFCoVE) commissioned Scarlatti to research the use of AI in education and test the viability of structured AI-driven oral assessment in partnership with Fruition, a private training establishment based in the Bay of Plenty. This case study shares what happened next, and how Scarlatti’s Vocina platform emerged from that work.

Rethinking what assessments should capture

Fruition was interested in exploring how AI could help them develop assessments that genuinely captured learners’ understanding, not their ability to produce polished written work.

Written assessments are familiar, but they don’t always reveal how learners think. Capable learners sometimes struggle to express themselves in writing. Others may refine and edit text in ways that mask gaps in understanding. At the same time, careful management is always required for grade moderation to achieve consistency across tutors.

Fruition wanted to design accessible assessments that surface learners’ authentic understandings while retaining strong moderation and tutor control. Oral assessment has long been a highly effective, but highly expensive, way of examining learners’ capabilities; AI made it feasible to scale.

Designed for real-time reasoning

Following initial research and testing, Scarlatti designed and built the Vocina platform to deliver structured oral assessment agents.

Instead of submitting written answers, learners click a link in their learning management system, Moodle, to speak with an AI agent. The agent guides learners through a structured sequence of questions and can ask follow-up prompts when the learner’s responses lack clarity or depth. Assessments typically take five to ten minutes.

The tutor designs the questions and prompts in advance, aligning them to the learning outcomes and rubric criteria used for original written assessments.

From pilot to embedded tool

The initial trial of Vocina was well received by learners and tutors alike. As well as the details in this case study, you can view a recorded webinar on the Vocina pilot and a series of articles [AS1] [SS2] detailing further insights into the pilot. Following the successful trial, Fruition has built its use of Vocina across multiple programmes at a range of levels.

Vocina is now embedded in:

  • The Level 6 Diploma in Horticulture (Horticultural Innovations micro-credential), where it supports reflective journaling and documenting of applied innovation practice.
  • The Level 4 Emerging Leadership micro-credential, where learners complete structured oral reflections.
  • A Level 2 Primary Industry Skills unit standard, where it enables learners to demonstrate understanding in a way that better reflects their capability.

Across these, the purpose remains consistent: to capture understanding and reasoning through speech rather than relying on writing.

What changed for learners and tutors

  • Learners find the oral format more natural. Many feel more confident explaining their knowledge, including learners whose first language is not English.
  • Reasoning becomes more visible for tutors. With responses delivered in real time, learners must explain, justify and connect ideas without editing. Follow-up prompts often push them deeper than a written task might, creating stronger evidence of their capability.
  • Structured questions keep things consistent. Rubric criteria are aligned to learners’ answers and are reflected in the agent’s summary.
  • Transcripts and audio recordings make moderation easier as tutors can see how answers were reached.
  • AI-supported oral assessments are more efficient. They reduce time spent producing written material.

While Vocina plays a significant part in providing a reliable and consistent process for gathering evidence of learning, judged against consistent criteria, moderation via human judgement is also important. Our current moderation model involves tutors reading through transcripts and listening to audio recordings, then making the final decisions around assessment of particular pieces of learning.

As Tiffany Andrews, Academic Manager at Fruition Horticulture, explains:

“For us, this isn’t about replacing written assessment with technology. It’s about designing assessment that genuinely captures learner thinking. The oral format challenges learners to explain, justify, and connect their ideas in real time, which gives us clearer evidence of authentic understanding and applied capability. Importantly, tutors remain central to the process: professional judgement and robust moderation are non-negotiable.”

Assessments redesigned

One of the key motivations for Fruition's adoption of AI was to rethink the purpose of assessment and make it better for learners, rather than automate it. Since its initial trial, Fruition's use of AI-enabled oral assessment has firmly shifted from pilot phase to being embedded in everyday learning and teaching. Not only does Vocina deliver richer and clearer evidence of learners' understanding than traditional forms of assessment, it keeps tutors at the heart of the process

Want to capture how learners think, not just what they write?

Get in touch to see how Vocina can support structured oral assessments that capture reasoning, generate clear evidence, and keep tutor judgement at the centre.

Learn more about Vocina