๐Ÿค– I Built 2 Telegram Bots with Qwen3.8-Max โ€” and the Results Were Seriously Impressive

์ž‘์„ฑ์ž

์นดํ…Œ๊ณ ๋ฆฌ:

โ† ํ”ผ๋“œ๋กœ
DEV Community ยท Vic Shรณstak ยท 2026-08-17 ๊ฐœ๋ฐœ(SW)
Cover image for ๐Ÿค– I Built 2 Telegram Bots with Qwen3.8-Max โ€” and the Results Were Seriously Impressive

Vic Shรณstak

๐Ÿ’ฌ Following up on the story about the release of Qwen3.8-Max, I finally tried it on real-world tasks.

Specifically, for building AI consultants for text channels (messengers) in my favorite programming language โ€” Go.

Spoiler: itโ€™s really good, especially for such a low price per 1M tokens! ๐Ÿ˜

As a result, I built 2 demo Telegram bots, where GPT-4.1-mini acts as the brains ๐Ÿ‘‡

1๏ธโƒฃ A bot for qualifying a customer and booking a car repair appointment, which asks for details about the vehicle and the issue, answers questions about service pricing, and schedules a convenient visit time.

2๏ธโƒฃ A bot for calculating kitchen pricing for furniture companies, which ัƒั‚ะพั‡ะฝัะตั‚ kitchen parameters through guiding questions, calculates the cost, sends the final estimate, and books the client at the company office for a detailed design session.

Before implementation, of course, I wrote a detailed spec for each of these bots and connected MCP Context7.

I also had to make 1โ€“2 corrective prompts for code style and some business-logic details… but otherwise, Qwen3.8-Max worked fully autonomously in the engineering loop (questioning itself at every stage and adjusting its own reasoning and code).

Token usage (input + output) totaled ~12.8 million, across about 400 API requests to the Chinese model. Thatโ€™s seriously impressive! For comparison, I ran the same task through DeepSeek V4 Flash Latest: with similar output results, it used over 15 million tokens.

By the way, the whole development process was done in the next-gen AI IDE Kodik, by our local guys โ€” ArchiTech AI.

Highly recommend downloading and trying it. Not an Ad! Iโ€™ve been using it for over a month now, and itโ€™s truly a very high-quality product, especially in the era of account bans from Anthropic and OpenAI ๐Ÿ˜

…and soon, a local model called Qwen3.8-27b is also expected to drop, which Alibaba has promised to release any day now… thatโ€™s definitely something that can make the big AI model vendors nervous!

๐Ÿ˜‰ And if you need to design, build, and launch an AI solution for you and/or automate your business processes, feel free to DM me: t.me/koddr

๐Ÿ’ก Interesting to read? Follow me on all platforms so you donโ€™t miss new posts ๐Ÿ‘‰ Telegram, VK, TenChat, Dzen, Teletype, or vc.ru

์›๋ฌธ์—์„œ ๊ณ„์† โ†—

์ถ”์ถœ ๋ณธ๋ฌธ ยท ์ถœ์ฒ˜: dev.to ยท https://dev.to/vic_makes_ai/i-built-2-telegram-bots-with-qwen38-max-and-the-results-were-seriously-impressive-4ceg