Te Pae Oranga o Ruahine o Tararua
Multi-modal data processing across structured and unstructured sources, scored against iwi-defined pou.
The challenge
Te Pae Oranga o Ruahine o Tararua works across multiple dimensions of community wellbeing. The organisation collects data in a range of formats - including audio, video, and text - that contains rich insight into outcomes and community experience.
This material is valuable but difficult to analyse systematically. Processing multi-modal data is resource-intensive, and without a structured framework it is hard to assess how well the evidence aligns with the organisation's stated priorities and pou.
The configuration
This configuration represents Mindstake's multi-modal capability - extending the data pipeline beyond text documents to audio, visual, and other unstructured sources.
Data ingestion begins with multi-modal sources. A data transformation pipeline processes these into structured content, preserving the context and nuance of the original material.
Criteria are aligned to the iwi's pou, similar in structure to other Mindstake configurations. The difference is the data source - instead of processing written documents alone, the pipeline handles audio, video, and text.
Scoring is applied to the processed content against the rubric, producing alignment scores across multiple dimensions. This transforms rich qualitative material into structured, comparable assessments.
The outcome
Multi-modal data produces structured alignment scores. The organisation can see how evidence from multiple sources and formats relates to their stated priorities.
This enables evidence-based governance conversations that draw on the full range of available data - not just the parts that happened to arrive in written form.
Our people share their experiences in many ways, not just in written reports. We needed a way to honour that while still producing the structured evidence our governance requires.
- Te Pae Oranga
The broader lesson
Te Pae Oranga demonstrates that Mindstake's analysis framework is not limited to written documents. The same criteria-and-rubric structure can be applied to any data source that can be processed into structured content - including audio, video, and other multi-modal formats.
The pattern is consistent: take whatever data the organisation has, process it through a configured pipeline, and map the results to weighted criteria. The data source changes; the analytical framework stays the same.
Same engine, different decisions
Every Mindstake configuration starts with the same question: what does your organisation value, and how well are your options delivering?
Raukawa
Consistent, values-based review of documents - using the simplest Mindstake configuration.
Ngāi Tahu
Seeing whether each investment is delivering what it set out to achieve, beyond the financial.
Tapuwae Roa
Measuring alignment between organisational values and outcomes across five pou, using multi-modal data processing.
Getting started
Most teams are up and running within a few weeks. We work alongside you to set up your first decision process - criteria, rubrics, and scoring - then hand it over so you can run it yourself.
An initial conversation to understand your decision context
We help you define criteria and build your rubric
Your team runs the process on your own Mindstake instance