Pharma software · AI research · Model training

Software that keeps
medicines moving.

Inwebbo builds software for pharmacies, pharma wholesalers and distributors, and the supply chain that connects them. Underneath it are AI models we research and train ourselves.

Demand monitor Pharmacies · All regions
  1. Vitamin D3Winter · Metros↑ +1.8σ
  2. AntihistaminesPollen season · North↑ +2.2σ
  3. ORS sachetsMonsoon · East↑ +2.9σ
Illustrative dataDemand shifts, separated from the noise of the market

What we do

Three disciplines. One loop.

  1. 01

    Software products

    Software for pharmacies, wholesalers, distributors and the supply chain between them, built around how the trade actually works.

    Our products
  2. 02

    AI research

    We study how models handle the messy data of the pharma trade: catalogues, searches, orders, sales and supply signals.

    Our research
  3. 03

    Model training

    We curate data, then pretrain, adapt, align and evaluate our own models end to end, and ship them inside our products.

    How we train

What our products run into tells us what to research next, and the loop starts again.

01 Products

Software for the pharma trade, end to end.

Medicines pass through many hands before they reach a patient. We build software for the businesses along that chain: pharmacies, wholesalers and distributors, and the supply chain that links them to manufacturers.

Pharmacies

Retail chemists and pharmacy chains.

The day-to-day

  • Thousands of SKUs, with substitutes for most of them
  • Batches and expiry dates on every strip
  • Demand that shifts with the season and the neighbourhood

Wholesalers & distributors

Stockists, distributors and C&F agents.

The day-to-day

  • Orders from hundreds of pharmacies, every day
  • Schemes, credit and returns to keep track of
  • Stock that has to be in place before it's asked for

Supply chain

From manufacturer to pharmacy shelf.

The day-to-day

  • Many hands between the factory and the counter
  • Little visibility into what's selling downstream
  • Forecasts that need to become the right orders upstream

Intelligence, built in

Our products carry the models we research and train: they spot shifts in demand early, understand what people search for, and flag what needs attention.

Real-time trend detection

Demand, search and sales signals monitored continuously, with emerging trends flagged the moment they separate from the noise.

Intelligent query mapping

Every search mapped to structured intent, so you see what customers want, not just what they typed.

Custom dashboards

The views that matter to each team, from the pharmacy counter to the distribution desk.

Smart alerts

Instant notice when demand spikes, stock nears expiry or a trend turns.

The whole picture

A bird's-eye view across outlets, regions and channels, so growth and gaps are obvious at a glance.

Integrations & open API

Connect the systems you already run, and push insights out through an API and webhooks.

02 Research

Research that starts with real markets.

General-purpose models stumble on the long tail of the pharma trade: brand and generic names, strengths and pack sizes, mixed-language searches, sparse and seasonal demand. That long tail is where we work.

  • Domain language models

    Compact models that know catalogues, categories, generics and brands, and stay accurate on the long tail where general models guess.

  • Query & intent understanding

    Turning short, misspelt, mixed-language searches into structured intent: the product, its attributes, the urgency and the place.

  • Demand & trend forecasting

    Time-series models for sparse, seasonal, promotion-driven data that flag a shift early, and say how sure they are.

  • Retrieval & grounding

    Answers tied to your catalogue, your documents and your numbers, with sources attached rather than confident guesses.

  • Evaluation science

    Domain benchmarks, calibration and failure analysis, built before the model rather than after it.

  • Efficient inference

    Distillation and quantization so models run fast and affordably inside the software people use every day.

Open questions

What we're working on now

Our research agenda comes from the problems our products run into. A few we're spending time on:

  1. How small can a domain model get before it stops beating a general one on the tasks that matter?
  2. Can a forecasting model know when it doesn't know, and say so in a way a planner can use?
  3. What does a fair benchmark for mixed-language pharmacy search look like?
  4. How do you separate a real trend from promotions, stock-outs and noise, early enough to act?

03 Training

From raw data to a model in production.

We run the whole training pipeline in-house, for the models inside our products.

Curate the data

Most of a model's quality is decided before training starts. We source, de-duplicate, filter and label data, and strip personal information before anything reaches a training run.

  • De-duplication and quality filtering
  • Detection and redaction of personal data
  • Licensing and provenance tracked per source
  • Synthetic data where real data is thin

How we work

Principles we don't trade away.

  1. 01

    Evidence over hype

    If we can't measure it, we don't claim it. Evaluations come first, and they come with the model.

  2. 02

    Built for the trade

    Pharmacies and distributors run on thin margins and little spare time. Software has to fit the work, not add to it.

  3. 03

    Built for production

    Latency, cost and reliability are research problems too. We design for them from the first experiment.

  4. 04

    Responsible by default

    Privacy-preserving pipelines, careful evaluation, and people in the loop where decisions matter.