Cold outreach where a human approves every message
A Ukrainian maker of corporate merch sells to other companies. We built them a system of three agents. The lead-gen agent finds the decision-maker and writes to them in the right channel, the inbound agent runs conversations with clients, and an AI assistant helps the whole team. Every cold message goes out only after a manager's OK.
- Client
- A Ukrainian maker of corporate merch and brandingB2B, sells to other companies
- Service
- emilus. Leadgen
- Status
- In production at the clientcampaigns run through an approval queue
- Channels
- Email, LinkedIn, Telegram, Instagramcold sequences and inbound conversations
A human in the loop. A manager reads and approves every message before it is sent.
Where the client started
The company makes corporate merch and sells it to other businesses. The team worked cold leads by hand: 2,000 companies in 5 months, and 26 purchases. Inbound messages on Instagram and Telegram arrive as text, photos, voice notes and files. A manager answered each one personally, dug up examples of past work, passed the details on for the invoice and tracked payment across several systems. Nobody replied in the evening or at the weekend, and a client's files got lost somewhere in the chat history.
cold leads in 5 months, worked by hand
per client datapurchases from those leads
per client datarevenue from those purchases
per client dataspent on this work
per client dataSo 1.3% of contacts became clients: 26 purchases from 2,000 leads, and behind each one sat hours of manual research and back-and-forth.
The client's main conditionNo message goes out without a human's approval.
What the system does
- Researches every company in the list on its own: website, job posts, LinkedIn. It finds the decision-maker and scores the lead, so a manager doesn't lose half an hour to manual searching.
- Writes to a specific person in a specific channel: a personal email, a shared inbox, LinkedIn or Telegram, with the company's real projects in the text. It keeps the follow-up sequence going until the person replies.
- Shows every message to a manager before it goes out. The manager reads, edits and approves it, so the company's reputation stays in its own hands.
- Handles Instagram and Telegram conversations like an account manager, with new and existing clients and by the company's rules. It qualifies each request and passes on only what needs a person.
- Understands the client's photos, files and voice notes and keeps every material in one company card, by date, so the order history doesn't vanish into the chat.
- Quotes prices from the company's own calculator and picks examples of past work to fit the request. One click turns a manager's correction into a rule.
- Runs follow-ups and repeat sales across existing clients: a feedback request after delivery, holiday greetings, a reorder. It stops as soon as the client replies.
- Sends the approved mockup to the production team's Telegram group and keeps reminding the people responsible until they answer, so no order gets stuck between departments.
- Issues the invoice in FinMap, the company's finance app, spots the payment and confirms it to the client in the same conversation, so the manager doesn't have to check bank statements.
- Works as an AI assistant for the whole business. It answers any question about clients, conversations, orders and figures, pulls together analytics, helps train new staff and carries out actions in the system after one confirmation.
The architecture in plain terms
A web app for the manager on desktop and phone, a log of every action, and daily and monthly spending limits. In lead generation the AI works in three roles: researcher, critic and copywriter. Two more agents work alongside it. The inbound agent talks to new and existing clients, and the AI assistant works with all the data in the system for the whole team. A human stands between the AI and the send button.
- Agents
- lead generationinbound agentAI business assistant
- Channels
- emailLinkedInTelegramInstagram
- Data sources
- company websitesjob sitesLinkedInpublic registersemail verification
- Integrations
- FinMap: invoices and paymentsproduction team's Telegram group
- Notifications
- Telegram bot for the manager
How it works
- managerCompany listUploads companies or contacts
- AI researcherDossier and scoreDecision-maker, sources and a score
- AI writerMessage for the channelEmail, LinkedIn or Telegram
- managerA human confirmsReads, edits and gives the OK
- clientReplyThe follow-up sequence stops
- inbound agentConversationTalks with the client on Instagram and Telegram
- agentPrice and examplesFrom the company's calculator
- FinMapInvoiceCreated with no manual entry
- systemPayment confirmedThe client sees it in the same chat
- agentFollow-upsFeedback, holidays, reorders
Results and payback
of recipients reply to cold outreach, averaged across all channels
per client dataof contacts become clients
per client datacompanies with a dossier: the decision-maker and a score for each
per client dataProject payback: ≈5 months per client dataThe same contacts now bring 2.5–3 times as many clients, at an average order of 32,885 UAH. One system of three agents: lead generation, inbound and a business assistant.
What's live
- live
Dossiers, a message written for each recipient and the approval queue
- live
Campaigns by email, LinkedIn and Telegram
- live
The inbound agent and an AI assistant for the whole team
A similar task in your business?Solomiia, Pavlo's AI assistant, will ask about the details and prepare your conversation with him.
emilus. Leadgen
Finding B2B clients: a list of companies, a dossier on each, and a message written for the person and the channel. No message goes out without a human's approval. Price after the brief.