Your inbox answers itself. In their language.

Production LLM agents that work inbound on Telegram, WhatsApp, Instagram and Discord, and wake a human only when the deal earns it.

Dubai11 languages~50 agents in productionSince 2022

Real outbound, anonymized. Channel, language, reply latency.

One agent, seventeen days

The number that matters is the one where nobody answered.

Messages handled7,128Across one deployment, seventeen consecutive days.
Customers883Unique people, not sessions.
Closed with no human9 / 10Escalated only when the deal justified a call.
Model spend, that month$0.65Prompt caching, model routing, context discipline.

Nobody has asked mine if it was a bot.

It does not open with a menu. It does not say it is an assistant. It answers the question that was asked, in the language it was asked in, at the length a person would use.

Language detection runs on a fastText classifier, not a guess. Reply timing is randomised inside human bounds. When a conversation stops being a support ticket and starts being a deal, it hands you the thread with the context attached.

Cumulative, all deployments

MESSAGES 7,128
CUSTOMERS 883
LANGUAGES 11
AUTONOMOUS 90%

Totals since launch. The dashboard behind this link shows the same figures live, per day and per channel.

Running now

Three of them, named, with the parts that were hard.

Surush
Telegram · Sales

Multilingual inbound across eleven languages. Warm-up discovery, twenty-four hour follow-up, and a wallet-scrub layer that strips crypto-scam bait before a customer ever sees it.

7,128 messages · 883 customers · 17 days

Sophia
Instagram · DM sales

On the official Graph API rather than a scraper, which is why it still runs. Multi-tenant OAuth, cleared Meta App Review and Business Verification.

Official API · Multi-tenant

Hassan
Telegram · B2B partnerships

Sells broker partnerships in a regulated vertical, so it never quotes terms in chat. A backstop classifier catches meetings the main path misses, which it has done.

3 meetings in 11 days · 0 crashes

The layer underneath
Infrastructure

Six model providers behind one abstraction with automatic failover and a per-call cost ledger. Hybrid retrieval on pgvector and SQLite FTS5, answering with the source attached.

47 cron jobs · Self-provisioned VPS

TelegramWhatsAppInstagramDiscord

The agent is the part you can see.

Most of the work is the plumbing behind it. Scraping and enrichment, CRM writes, document pipelines that turn unstructured reporting into queryable data, scheduled jobs that reconcile things nobody wants to reconcile by hand, and voice in and out where a channel needs it.

Python, FastAPI, PostgreSQL, Redis, Docker, Linux, n8n. Claude through the Messages API, the Agent SDK and MCP, alongside OpenAI, Gemini, DeepSeek and local models on Ollama when data cannot leave the building.

I also run five trading systems of my own against MT5, Interactive Brokers, Bybit and Alpaca. That is where the paranoia about silent failure comes from.

What things cost

Fixed scope, fixed price, no discovery phase.

EngagementScopeFrom
AI sales agent One channel, your tone, your rules, escalation to you. Runs and is maintained.Additional channels priced per channel. $300 / month
Landing page One screen, built and deployed. Your copy.Turnaround measured in days. $499
Full site Design, copy, build, deploy, and the domain wired up.End to end. No handoff to a third party. $1,500
App MVP A working product, not a prototype. Backend, data, auth, deploy.Scoped before anything is charged. $6,000

Consulting and longer engagements bill at $90 to $125 per hour. If a fixed scope is cleaner for you, say what you need and I will quote it as one number.

Put one on your inbound for a week.

Then read the transcripts and decide. That is a faster answer than any call I could give you.