# Only what you can verify.

> Case studies of AI agents, lead generation, demand forecasting and custom software in production: what we built, how it works and how fast it paid back.

URL: https://emilus.dev/en/cases/
Emilus · hello@emilus.dev · https://t.me/brrr28

1. [Emilus](https://emilus.dev/en/)
2. Case studies

Case studies

What we built for clients, how it works and how fast it pays back. All nine projects are in production. Every number shows where it comes from: “per client data” or “estimate”.

**9 systems in production** · **payback from 2 months** · every number is labeled with its source: *per client data* · *estimate*

We describe clients by type and publish names only with their consent.

- Procurement · Integrator · in production [Forecast-based purchasing for restaurants and catering](https://emilus.dev/en/cases/restaurants-catering/) Client Restaurant group in Czechia: 4 restaurants and catering; before the project, one kilogram of food in five went to waste, ≈€170k a year What we built POS data from every location, a forecast per item and location, tomorrow's order drafted automatically; the manager approves it with one tap in Telegram, and at 07:45 the suppliers have their orders Status In production **7.5%** · *per client data* · waste instead of 21%: 2.8 times less
- Agent · Integrator · in production [An AI salesperson in Direct, from reel comment to shipping label](https://emilus.dev/en/cases/clothing-store-instagram/) Client Clothing store on Instagram, 17 products in ≈350 variants What we built An agent for Direct and comments: replies within a minute day and night, finds the product from a photo, checks stock in the CRM, creates the order and the shipping label, upsells; the owner confirms payment Status In production **+15%** · *per client data* · revenue in the first 2 months with the agent
- Agent · Voice · in production [AI front desk for a dental clinic chain](https://emilus.dev/en/cases/dental-clinic-chain/) Client Dental clinic chain in Ukraine: 3 clinics, 11 chairs; before the project, one patient in six missed the visit What we built 24/7 booking in chats and by phone, reminders and reconfirmation, a waitlist for every cancellation; the administrator confirms complex bookings Status In production **6%** · *per client data* · no-shows instead of 17%: 2.8 times fewer
- Agent · Voice · in production [Four AI agents for a car dealer hub](https://emilus.dev/en/cases/car-dealer-hub/) Client Car hub importing from US and Korean auctions; before the project, lead conversion was 3% and a request took 1–1.5 days to handle What we built The agents message and call a lead right away, qualify it in the CRM without duplicates, find cars, guide the client until pickup and buy a “Buy Now” lot when the manager taps the button Status In production **up to 3 min** · *per client data* · to first contact with a lead, instead of 1–1.5 days
- Leadgen · in production [Cold outreach where no letter goes out without a human](https://emilus.dev/en/cases/merch-maker-leadgen/) Client Ukrainian maker of corporate merch, B2B. Before the project: 2,000 cold leads in 5 months, worked by hand What we built A dossier and a letter written for each addressee, sent after the manager's “ok”, conversations on Instagram and Telegram, prices, invoice and payment, follow-ups and an AI assistant for the whole business Status In production **20–25%** · *per client data* · of addressees reply to cold outreach, averaged across all channels
- Custom software · Agent · Integrator · in production [Custom CRM and an AI salesperson for an electronics store chain](https://emilus.dev/en/cases/electronics-store-chain/) Client Chain of stores selling used electronics from Europe: retail and B2B What we built A custom CRM with every channel, lead routing, roles and Binotel telephony; the AI salesperson filters out irrelevant requests, closes simple sales and learns from the best managers Status In production **+5–8%** · *per client data* · sales conversion in the first month
- Procurement · in production [Demand forecast and a ready order to manufacturers](https://emilus.dev/en/cases/vet-pharma-purchasing/) Client Veterinary and pharmacy products brand: up to 200 items, 2 contract manufacturers, 10 years of sales history What we built A forecast for each item and a ready order to the manufacturer within the stock budget, with an explanation and a shortage warning; the buyer confirms Status In production **−22%** · *per client data* · money tied up in stock
- Custom software · Integrator · in production [A lending pipeline that sets personal terms in 40 seconds](https://emilus.dev/en/cases/lending-pipeline/) Client Non-bank lender in Ukraine: ≈40,000 applications a year; before the project, an underwriter spent 1–2 days checking each one What we built Scoring trained on the lender's own loans, document checks, a personal rate, limit and schedule; the underwriter decides gray-zone cases with a ready analysis Status In production **40 s** · *per client data* · from application to terms, instead of 1–2 days
- Custom software · Integrator · in production [A therapy booking platform with a catalog, packages, payment and calendar](https://emilus.dev/en/cases/b2b-saas-therapy-booking/) Client Company from Czechia, an online platform for psychological support What we built A product built from scratch: a matching quiz, Calendly slots, card payment, packages, accounts for three roles, emails and a funnel from click to payment Status In production; development continues **2 min** · *per client data* · from the button on the website to payment: a full-cycle system

Next step

## Write to us. A human replies.

[Message us on Telegram](https://t.me/brrr28)

[All contacts](https://emilus.dev/en/contact/)