---
id: "lib-2026-10-12-an-ai-secretary-for-77-a-month"
type: "library"
title: "An AI secretary for $77 a month"
title_original: "ИИ-секретарь за $77 в месяц: 88% ответов даёт DeepSeek, а три четверти денег съедают 7% запросов к Opus"
lang: "RU"
org: "Habr (independent builder)"
source_type: "Practitioner post"
date: "2026-10-12"
week: "2026-W42"
url: "https://nosov.ai/library/lib-2026-10-12-an-ai-secretary-for-77-a-month/"
original_url: "https://habr.com/ru/articles/1093274/"
tier: "B"
tier_name: "Useful, limited"
tier_reason: "Solo developer's Habr post with production routing, cost and usage figures from a small Telegram assistant; numbers are concrete but self-reported, small-sample and unaudited."
summary_basis: "full-text"
original_minutes: "6"
tags: ["ai technology", "model cost routing", "internal assistants", "usage data"]
---

# An AI secretary for $77 a month

Original title: ИИ-секретарь за $77 в месяц: 88% ответов даёт DeepSeek, а три четверти денег съедают 7% запросов к Opus

Tier B (Useful, limited): Solo developer's Habr post with production routing, cost and usage figures from a small Telegram assistant; numbers are concrete but self-reported, small-sample and unaudited.

Summary based on the full text.

## In short

A Habr post (12 October 2026) by the developer of "Liza Petrovna", a Telegram and MAX bot that answers in one chat and hands work to internal specialist agents (doctor, lawyer, designer, navigator). The core design choice is routing: a cheap model answers by default and a readable regex plus a length rule decides when to escalate to Opus. The post gives a month of production costs, a topic breakdown of what people ask, and a frank list of failure cases.

## Key numbers

- 88%: share of the secretary's answers produced by DeepSeek, at $0.002-0.007 per answer
- 7%: share of answers sent to Claude Opus 5, which took $39 of the secretary's $51 monthly spend (77%)
- 8568: requests from 118 people since 30 May
- 21%: share of requests that were small talk or tests rather than tasks
- 4.7%: share of real tasks about calendar and reminders, the classic secretary work

## What it reports

- Last 30 days: $77 in LLM spend across all agents; the secretary alone cost $51, of which $39 went on Opus answers.
- Of 2,500 secretary answers: DeepSeek 88% (2.5-12 s, $0.002-0.007), Opus 5 7% (18-38 s, $0.21-0.24), Haiku 4.5 2.4%, GLM 5.2 2.2% as an experiment. One Opus answer costs about as much as 50 DeepSeek answers.
- Escalation triggers: a regex on words such as "analyse", "compare", "plan", "calculate", "write code", and any message plus context over 2,500 characters. Web search is not a trigger because every model has it.
- Memory: 7,933 stored episodes from 97 people, hybrid vector plus keyword search, mean 33 ms, median 17 ms; falls back to keyword search if the embedding service is down.
- Of 6,796 real tasks: photo or document parsing 19.6%, images and video 12.5%, IT help 9.2%, fact lookup 9.1%; health and legal together almost 12%; calendar and reminders 4.7%.
- Failure cases: answering an earlier photo instead of the new one, wrong reply language driven by a mislabelled metadata field, wrong "today", saving the note "link saved" instead of the link, and misreading domain jargon.

## How they got it

Production logs from the developer's own service. Topic shares come from DeepSeek classifying each message into one of 16 topics in batches of 80; the author says no one read the conversations and the shares may be off by a couple of points. Prompt-injection tests are listed with verbatim refusals.

## Limits

- Single developer, single small service, one month of cost data; no quality evaluation of cheap versus expensive answers.
- Topic classification was done by an LLM without a checked sample.
- The bot is promoted at the end of the post, and the post received a negative community rating.

## Why it matters for companies

The cost profile is typical of assistant workloads: a small share of hard requests drives most of the bill, so routing policy matters more than the default model. A plain, testable rule is easier to audit than a model-based classifier and adds no latency. The usage mix is a warning for anyone scoping an "assistant": people bring photos, health and legal questions, not calendar tasks, so the risky domains need their own guarded paths. The failure list is a practical checklist for agent testing: explicit dates, explicit "new message" markers, and checks that a tool actually stored what it claims.

## Key passages in translation

> Секретарь за 30 дней стоил $51. Из них $39 — это ответы Opus. То есть 7% ответов съедают 77% денег

Over 30 days the secretary cost $51. Of that, $39 was Opus answers. So 7% of answers eat 77% of the money.

> Да, это регулярка, а не классификатор на модели. Зато её можно прочитать, покрыть тестами и всегда объяснить, почему конкретный запрос ушёл на Opus.

Yes, it is a regex, not a model-based classifier. But you can read it, cover it with tests and always explain why a given request went to Opus.

> Классической секретарской работы меньше 5%.

Classic secretary work is under 5%.

Original: https://habr.com/ru/articles/1093274/