Cultive

I’ve worked on projects at various stages of maturity, which call for different approaches depending on product-level priorities. These stages blend between one another, are often iterative, and the projects I’ve been exposed to have defined their phase segmentations differently, but here’s a generalised overview:

Conceptualisation & Definition

Proof-of-concept Prototype

Early-stage Prototypes

Late-stage Prototypes

Start-of- / Post-production

Product Development Stages

- Searching for product market fit
- Primary and secondary research to scope end-customer needs
- Ultra-low fidelity prototyping to demonstrate design intent

- MVP: defined product category and value proposition(s)
- Gathering feedback from early adopters
- Quick iterations with rapid prototyping and off-the-shelf components

- Early low-volume testing (engineering validation tests)
- Soft-tooled parts
- Top-down analysis: requirements listing and system decomposition

- Detailed function and manufacturing de-risking (design and production validation tests)
- First-off hard-tooled parts
- Pre-production sample runs
- Bottom-up tests: verification and integration

- Change management for mid- / post-manufacturing updates
- Detailed optimisation for cost-down and reliability factors

2019-2021

Cultive is a soil sensor network and data analytics platform that provides holistic water management for arable crop farmers in the UK. By providing on-field digital infrastructure, the system assists farmers towards improve their crop yields, reducing their water bills, and building resilience from weather uncertainty induced by climate change.

Cultive was a final-year enterprise group project from my undergraduate studies at Imperial College London, and was invited to exhibit and pitch at Dubai Design Week Global Grad Show 2020 ↗.

Stage

Conceptualisation & Definition

ResponsibilitiesRapid Prototyping // Digital Product Design // Product Marketing & User Research

Conceptualisation of a New Product

The project started off with a desire to solve a problem in the intersection between agriculture and climate change. Initial research quickly led to a direction - weather uncertainty induced by climate change was negatively affecting the yield and quality of arable crops. Further research and speaking to industry stakeholders led to a collection of insights within this problem area. The slides below frame this approach as the first half of a “Double Diamond” design thinking process.

A unique value proposition was identified - there was an overlooked ‘in-between’ solution that sits between remote sensing technologies and on-site soil inspections, providing medium-frequency data with adequate precision to assist farmers in decision-making.

Product Marketing

Compiled insights led to the definition of the target beachhead market of potatoes and grapes in France and the UK (high-value crops relative to other crops which require similar resources), as well as the total addressable market.

These slides from Cultive’s pitch deck show the outcomes in building business defensibility, by focusing on product positioning, and effectively reaching the right customers at the right price.

A breakdown of incumbent competitors in the market shows how a combination of features enables Cultive to stand out towards prospective customers.

Product pricing is based on: an estimated number of sensors that an average-sized farm requires; expected value generated over time; intended ROI for farmers who adopt the platform.

Paying close attention to farmers’ touchpoints to gather information within their community, and annual crop cycle timings, led to formation of a customer acquisition plan, and a customer service timeline.

Prototyping - Form Factor and Functionality

Cultive's remote sensors are designed to withstand outdoor weather conditions, and provide an appearance and form factor which allows farmers to identify, interact and install them with convenience. A physical prototype of the enclosure was printed for ergonomic testing, and to gather feedback from farmers.

Hardware and back-end communications utilised existing off-the-shelf components and readily available APIs, such that development time was kept to a minimum. Using a Raspberry Pi, simple IoT hardware was set up. A Python script was written to collect soil moisture data and broadcasted to an AWS server.

Data Dashboard Development

A set of dashboard mockup screens were developed to demonstrate the design intent of the data dashboard. Starting from initial sketches, feedback from farmers was incorporated to iterate towards higher fidelity designs.

Early variants of the dashboard displayed weather data and action recommendations in graphical and text boxes. However, feedback pointed out a lack of visibility into actual soil conditions (historical and if possible forecasted), as farmers are most comfortable with using data to augment their decision-making, instead of being directly given recommendations.

Field Mapping:
A map view, combined with toggles, allows farmers to quickly get the contextual view they’re after. A status overview of installed sensors is also available.

Forecast:
Having knowledge of future soil moisture content, based on recent trends, is invaluable for farmers as it helps them plan their irrigation schedule. This information is displayed in a graph format that displays the outcome of recommended actions. A text-based statement also summarises all relevant content into actionable advice.

Scrolling down, daily and hourly weather ‘cards’ highlight any irregular conditions that farmers need to pay special attention to.

Records:
Farmers are able to access full historical records of soil moisture and precipitation, with a easy-to-navigate bar to zoom in/out with respect to time.

These dashboard mockups were the final version of the data dashboard design, at the conclusion of the project.