AI for perishable food distribution

Know which crate dies first.

Ajwai grades incoming produce with computer vision, predicts each lot's remaining shelf life, and forecasts depot-level demand — so distributors sell the right stock, to the right buyer, before it turns.

MVP in development · Beta opening to selected distributors

Lot INT-2291 · tomato, grade BAjwai
61 hours of sell window left
IntakeSell nowLoss
Pepper · INT-228896hHold
Tomato · INT-229161hMove
Leafy greens · INT-229414hSell today
The problem

Spoilage is priced in as bad luck. It is actually an information gap.

A food distributor buys hundreds of crates a week with no reliable read on what condition they arrived in. Quality is judged by eye, in seconds, by whoever is on the loading bay. Stock is then dispatched roughly in the order it was stacked.

By the time a crate is visibly bad, the money is already gone — and the buyer who would have taken it two days earlier bought from somebody else.

Who carries the loss

Mid-size distributors, market wholesalers, and cold-store operators moving fruit, vegetables, and other short-life goods between farms and urban buyers.

What it costs them

Every discarded crate is paid-for stock, paid-for transport, and paid-for storage written off at once — on categories where margins are thin to begin with.

Why it compounds

Unsold stock forces panic discounting, which distorts pricing for the next cycle and damages the buyer relationships that make consistent volume possible.

The solution

A shelf-life clock on every lot, from the moment it hits the bay.

Ajwai turns intake into data. A phone or fixed camera photographs each lot; the model grades it, estimates remaining sell window from that grade plus storage and transit conditions, and ranks the whole warehouse by urgency. Demand forecasting then matches the most urgent stock to the buyers most likely to take it now.

Grade at intake

Consistent quality scoring that does not depend on who is on shift.

Predict the window

Hours of sell time remaining, updated as conditions change.

Rank the floor

A live dispatch order across every lot in storage.

Match the buyer

Demand forecasts that point urgent stock at the right customer.

AI technology

What the models actually do

Ajwai is not a spreadsheet with an assistant bolted on. The product does not exist without the models — grading, shelf-life estimation, and demand forecasting are the platform.

Data the AI uses

Intake photographs of each lot, category and variety labels, supplier and origin records, transit duration, storage temperature and humidity readings, historical sale timing, and per-buyer order history.

What it detects

Surface defects, bruising, mould, colour and ripeness stage, size distribution, and lot-level grade consistency from images captured in ordinary warehouse lighting.

What it predicts

Remaining sell window in hours per lot, spoilage risk under current storage conditions, and expected demand per product, per depot, per day.

What it generates

A ranked dispatch order, buyer-matching suggestions, markdown timing recommendations, and a written daily intake report summarising quality and risk across the warehouse.

Models and techniques

Convolutional and vision-transformer image classifiers for grading and defect detection; gradient-boosted and sequence models for time-series demand forecasting; survival-style modelling for shelf-life estimation; a large language model for report generation and natural-language querying of warehouse state.

Why accelerated compute

Grading has to return a result while the truck is still being unloaded. GPU inference keeps per-image latency low enough for the bay, and GPU training lets vision models be retrained per crop, per season, and per region as new labelled intake data arrives.

Product features

Built around one shift a day, not one report a quarter.

01

Intake grading

Photograph a lot on any phone and get a grade, defect breakdown, and confidence score before it is stacked.

02

Shelf-life clock

Every lot carries a live countdown that adjusts to storage temperature and time already spent in transit.

03

Dispatch ranking

A single ordered list of what leaves the warehouse next, refreshed as new stock arrives.

04

Demand forecasting

Expected volume per product and depot, so buying decisions stop being made on last week's feeling.

05

Buyer matching

Urgent stock surfaced against the buyers whose order patterns suit it, with suggested pricing.

06

Loss reporting

Written and exportable records of what spoiled, where it came from, and which suppliers underperform.

How it works

Four steps, inside the existing workflow.

STEP 01

Capture at the bay

Warehouse staff photograph each incoming lot in the Ajwai app and scan or enter the supplier reference. No new hardware is required to start.

STEP 02

Grade and score

The vision model returns a grade, defect breakdown, and an initial shelf-life estimate within seconds, attached to the lot record.

STEP 03

Rank and alert

The dashboard reorders the floor by urgency. Supervisors are alerted when a lot crosses into its final sell window.

STEP 04

Sell and learn

Sale and loss outcomes feed back into the models, so grading and demand forecasts improve for that crop, region, and season.

Product

The warehouse, ranked by hours remaining.

The operations view is the product's centre of gravity: one screen a supervisor can read from across the room, showing what came in, what condition it is in, and what has to go out today.

Interface preview from the MVP in development. Figures shown are illustrative sample data.

ajwai — depot overview
Lots in store
148
Sell today
12
Graded today
37
Tomato34%
Pepper62%
Onion88%
Leafy greens19%
Plantain71%

Bars show percentage of sell window remaining, averaged per category.

Technology & infrastructure

How we use AWS

Ajwai runs on cloud infrastructure for image storage, model inference, API hosting, real-time alerting, analytics, and user management. Our planned AWS architecture:

ServiceWhat it does for Ajwai
Amazon S3Stores intake images and labelled training sets, with lifecycle rules moving older captures to cheaper tiers.
Amazon RDSHolds lot records, supplier and buyer data, sale outcomes, and the audit trail behind every prediction.
AWS Lambda / ECSRuns the grading API and scheduled forecasting jobs, scaling with intake volume rather than sitting idle overnight.
Amazon SageMakerTrains, versions, and serves the grading and shelf-life models, and hosts retraining as regional data accumulates.
Amazon BedrockPowers the written daily intake reports and natural-language querying of warehouse state.
Amazon CloudFrontServes the dashboard and app assets quickly to depots on constrained connections.
Amazon CognitoManages depot-level accounts and role separation between operators, supervisors, and owners.
Amazon CloudWatchMonitors inference latency, job failures, and model drift so grading quality is observable in production.

How we use NVIDIA

Grading is a computer vision workload, so accelerated computing is on the critical path rather than a nice-to-have.

TechnologyWhere it applies
CUDATraining the grading and defect-detection models on labelled intake imagery.
TensorRTOptimising those models for low-latency inference so results return while unloading is still in progress.
Triton Inference ServerServing multiple crop-specific models behind one endpoint as the catalogue grows.
JetsonPlanned edge deployment for fixed bay cameras at depots with unreliable connectivity.
Why now

Cameras and cloud inference finally cost less than the losses.

Food distribution across Africa is consolidating: buyers want consistent quality and reliable delivery, and distributors who cannot supply it lose contracts to those who can. At the same time, smartphone cameras in every warehouse and affordable GPU inference in the cloud have made per-lot quality assessment cheap enough to run on ordinary stock, not just premium export shipments.

The category has been managed by intuition because measuring it was uneconomic. That constraint has lifted, and the operators who instrument their intake first will hold the margin advantage.

Market opportunity

Focused on the operators who already count their losses.

Target users

Mid-size fresh-produce distributors, market wholesalers, cold-store operators, agro-processing buyers, and grocery and restaurant supply chains.

Launch markets

Nigeria first, with expansion planned across Ghana, Kenya, Rwanda, and South Africa as depot density supports it.

Revenue model

Per-depot subscription, tiered by monthly intake volume, with usage-based AI grading credits and enterprise plans for multi-depot groups.

Growth plan

Land single depots, expand across a distributor's network, then extend the buyer side into a demand marketplace built on accumulated quality data.

Fresh produce Cold storage Wholesale markets Agro-processing Grocery supply
Traction & status
MVP in development

Where the product stands today.

The intake grading flow and shelf-life scoring engine are in active development. Demand forecasting is being built against historical sale data collected during discovery interviews with distributors.

Beta access is opening to a limited number of depots in Lagos, prioritising operators handling short-life produce daily. We are collecting labelled intake imagery with early partners to strengthen grading accuracy per crop.

Join the beta list
Roadmap

What we are building next.

PhaseMilestone
Phase 1MVP: intake capture, grading model, and shelf-life scoring for core vegetable categories.
Phase 2Beta with pilot depots; labelled data collection and per-crop model tuning.
Phase 3Demand forecasting and buyer matching released to beta accounts.
Phase 4Full AWS production deployment with monitoring, retraining pipelines, and role-based access.
Phase 5GPU-accelerated inference at scale and edge grading for low-connectivity depots.
Phase 6Multi-depot enterprise tier and expansion into additional African markets.
Team

Who is building it.

Ajwai is being built by a team of software and AI engineers working alongside people who have moved perishable stock for a living.

Adeola Timileyin

Founder & technical lead

[One or two sentences: engineering background, what you have built before, why this problem.] LinkedIn

Abdulfaruk

AI engineer

[Computer vision and forecasting experience, relevant projects or models worked on.] LinkedIn

Samuel William

Operations lead

[Domain experience in food distribution, logistics, or market trading.] LinkedIn

Get started

See Ajwai on your own stock.

Tell us what you move and where you store it, and we will walk you through a grading demo on your produce. Beta places are limited while the models are being tuned per crop.

Or email us directly at hello@ajwai.site