Case study — DTC beverage brand

A decision platform for a DTC beverage brand

This case study walks through one real engagement: a platform Anneal built and runs end to end for a DTC beverage brand, automating customer service, delivery exceptions, fulfilment and marketing-spend decisions in production.

The brief

A small eCommerce business, run by a group of friends who all had full-time jobs, was struggling to keep up with a growing ready-to-drink (RTD) beverage brand. Nobody had a complete view of the day-to-day business, every task meant logging into several systems, and decisions were often made reactively. The platform below is what got built: agentic workflows, a marketing-mix model, operational and inventory monitoring, and the engineering discipline (testing, incident response, evaluation) that keeps it trustworthy in production.

Analytical use cases

01

Inventory-stretch via marketing throttle

Using the marketing model backwards: finding the spend that slows demand to match supply.

Read the replay →
02

ROAS optimisation

Reallocate spend across channels interactively and compare against the model's own optimum.

Read the replay →

The Solver

Try the interactive spend-scenario planner — built on the real fitted marketing-mix model.

Agentic workflows

01

Customer service email

Refunds and returns, classified and resolved automatically — with an honest look at what happens when confidence is low.

Read the replay →
02

Delivery exception auto-resolution

Shipping problems detected, customers notified, reshipments created — no human touch on the happy path.

Read the replay →
03

Sample-pack zero-touch fulfilment

From nineteen identical manual requests to a fully automated intake-to-invoice flow.

Read the replay →
04

Self-modifying playbook

A plain-language Telegram message becomes a committed, deployed policy change — or a filed issue if it needs real code.

Read the replay →
05

Evaluation framework

How the agent's behaviour gets tested before it ever reaches a customer.

Read the replay →

Stack

  • Python
  • FastAPI
  • SQLAlchemy
  • Alembic
  • PostgreSQL
  • Streamlit
  • PyMC
  • APScheduler
  • Anthropic Claude
  • JupyterLab
  • pytest
  • Caddy
  • GitHub Actions