Update a legacy Telegram bot and refactor an app
Many things are half-baked :P. Task: Many things are half-baked :P First on Catalan at: En Rub aprenent. A website to keep track of my digital collection of Pokémon cards. I already told you about this in the newsletter and went a lot further, I'll summarize the news at the end. A website to keep track of my digital collection of Pokémon cards. I already told you about this in the newsletter and went a lot further, I'll summarize the news at the end. A Habit Tracker to quit smoking (not for me :p). I haven't finished it yet, it's given me more headaches than I thought for being the kind of "absurd app" that everyone is building. I think my initial prompt was too demanding, and I had to correct it quite a bit... A Habit Tracker to quit smoking (not for me :p). I haven't finished it yet, it's given me more headaches than I thought for being the kind of "absurd app" that everyone is building. I think my initial prompt was too demanding, and I had to correct it quite a bit... A website for tracking and trading crypto with Hedera. Don't put red laser eyes on me yet. It was a proof of concept to encourage a more "crypto-bro" friend to use Replit and see if the chili could get into this garden. We discovered that the knowledge of the model towards the libraries of this was very old, and it didn't work out. It quickly monitored values on a testnet, but trading… no more. I don't have it published, either. A website for tracking and trading crypto with Hedera. Don't put red laser eyes on me yet. It was a proof of concept to encourage a more "crypto-bro" friend to use Replit and see if the chili could get into this garden. We discovered that the knowledge of the model towards the libraries of this was very old, and it didn't work out. It quickly monitored values on a testnet, but trading… no more. I don't have it published, either. A web-crawler to extract documentation on web accessibility WCAG from the W3C. A bit regular, to make crawlers you have to give it good examples of the HTML that you will “parse” and I wanted to trust it to see if it was more capable than using LLM directly. Spoiler: it is not. Although LLM dresses in silk, LLM stays. I had to use ChatGPT to fix “the mess” and everything went like, ahem, like silk, until the W3C blew me away for a supposed DDoS attack :p “they just don't have patience”! A web-crawler to extract documentation on web accessibility WCAG from the W3C. A bit regular, to make crawlers you have to give it good examples of the HTML that you will “parse” and I wanted to trust it to see if it was more capable than using LLM directly. Spoiler: it is not. Although LLM dresses in silk, LLM stays. I had to use ChatGPT to fix “the mess” and everything went like, ahem, like silk, until the W3C blew me away for a supposed DDoS attack :p “they just don't have patience”! A portal to consume RSS and create summaries with AI. I didn't give it a try, I was too lazy. A portal to consume RSS and create summaries with AI. I didn't give it a try, I was too lazy. Updating the Telegram bot of a channel I participate in a lot, Mossegalapoma , was a total disaster. I'll leave some comments about that later as well. Updating the Telegram bot of a channel I participate in a lot, Mossegalapoma , was a total disaster. I'll leave some comments about that later as well. MediaWikiConverter, the tool to extract data formatted like MediaWiki to JSON as a support tool for Pokémon card tracker. As an internal tool, I don't have it published. MediaWikiConverter, the tool to extract data formatted like MediaWiki to JSON as a support tool for Pokémon card tracker. As an internal tool, I don't have it published. A “visually beautiful” product website that talks about the goodness of Replit. It was a quick test to see Replit's knowledge of itself and how it put together a typical product website. Not bad, not great. I didn't publish it, either. A “visually beautiful” product website that talks about the goodness of Replit. It was a quick test to see Replit's knowledge of itself and how it put together a typical product website. Not bad, not great. I didn't publish it, either.; tools: Replit Agent. Human role: The original post does not say how a person stayed involved.; limitations: Replit Agent requires setting up a project first before importing code, which adds friction. The model's knowledge of specific library versions may be outdated, causing failures in dependency updates. The author noted significant credit consumption ($25 plus extras) for failed attempts. Human oversight is critical as the agent cannot reliably handle complex refactoring of legacy systems without precise, iterative guidance..
Tools
Published on Agent Work Atlas:
Overview
Many things are half-baked :P
Workflow
Many things are half-baked :P First on Catalan at: En Rub aprenent. A website to keep track of my digital collection of Pokémon cards. I already told you about this in the newsletter and went a lot further, I'll summarize the news at the end. A website to keep track of my digital collection of Pokémon cards. I already told you about this in the newsletter and went a lot further, I'll summarize the news at the end. A Habit Tracker to quit smoking (not for me :p). I haven't finished it yet, it's given me more headaches than I thought for being the kind of "absurd app" that everyone is building. I think my initial prompt was too demanding, and I had to correct it quite a bit... A Habit Tracker to quit smoking (not for me :p). I haven't finished it yet, it's given me more headaches than I thought for being the kind of "absurd app" that everyone is building. I think my initial prompt was too demanding, and I had to correct it quite a bit... A website for tracking and trading crypto with Hedera. Don't put red laser eyes on me yet. It was a proof of concept to encourage a more "crypto-bro" friend to use Replit and see if the chili could get into this garden. We discovered that the knowledge of the model towards the libraries of this was very old, and it didn't work out. It quickly monitored values on a testnet, but trading… no more. I don't have it published, either. A website for tracking and trading crypto with Hedera. Don't put red laser eyes on me yet. It was a proof of concept to encourage a more "crypto-bro" friend to use Replit and see if the chili could get into this garden. We discovered that the knowledge of the model towards the libraries of this was very old, and it didn't work out. It quickly monitored values on a testnet, but trading… no more. I don't have it published, either. A web-crawler to extract documentation on web accessibility WCAG from the W3C. A bit regular, to make crawlers you have to give it good examples of the HTML that you will “parse” and I wanted to trust it to see if it was more capable than using LLM directly. Spoiler: it is not. Although LLM dresses in silk, LLM stays. I had to use ChatGPT to fix “the mess” and everything went like, ahem, like silk, until the W3C blew me away for a supposed DDoS attack :p “they just don't have patience”! A web-crawler to extract documentation on web accessibility WCAG from the W3C. A bit regular, to make crawlers you have to give it good examples of the HTML that you will “parse” and I wanted to trust it to see if it was more capable than using LLM directly. Spoiler: it is not. Although LLM dresses in silk, LLM stays. I had to use ChatGPT to fix “the mess” and everything went like, ahem, like silk, until the W3C blew me away for a supposed DDoS attack :p “they just don't have patience”! A portal to consume RSS and create summaries with AI. I didn't give it a try, I was too lazy. A portal to consume RSS and create summaries with AI. I didn't give it a try, I was too lazy. Updating the Telegram bot of a channel I participate in a lot, Mossegalapoma , was a total disaster. I'll leave some comments about that later as well. Updating the Telegram bot of a channel I participate in a lot, Mossegalapoma , was a total disaster. I'll leave some comments about that later as well. MediaWikiConverter, the tool to extract data formatted like MediaWiki to JSON as a support tool for Pokémon card tracker. As an internal tool, I don't have it published. MediaWikiConverter, the tool to extract data formatted like MediaWiki to JSON as a support tool for Pokémon card tracker. As an internal tool, I don't have it published. A “visually beautiful” product website that talks about the goodness of Replit. It was a quick test to see Replit's knowledge of itself and how it put together a typical product website. Not bad, not great. I didn't publish it, either. A “visually beautiful” product website that talks about the goodness of Replit. It was a quick test to see Replit's knowledge of itself and how it put together a typical product website. Not bad, not great. I didn't publish it, either.
Reported result
The update was described as a "total disaster" and a "total disappointment." The agent failed to create even a basic "hello world" bot without multiple iterations and errors. It did not successfully refactor the legacy code to use new API features, leaving the project unfinished and requiring manual intervention or abandonment.
Human role
The original post does not say how a person stayed involved.
Limitations
Replit Agent requires setting up a project first before importing code, which adds friction. The model's knowledge of specific library versions may be outdated, causing failures in dependency updates. The author noted significant credit consumption ($25 plus extras) for failed attempts. Human oversight is critical as the agent cannot reliably handle complex refactoring of legacy systems without precise, iterative guidance.
Try it
I need to update a legacy Telegram bot codebase located at [replaceable input: local path or repo URL] using Replit Agent. The goal is to migrate from [replaceable input: old API version] to [replaceable input: new API version]. First, create a new Replit project and import the code. Do not deploy or send any messages yet. Instruct the agent to identify deprecated API calls and propose a refactoring plan. Run a dry run on a single command handler to verify the new API integration works locally. Show me the diff and test results. Only proceed to full refactoring if the dry run passes. If the agent fails to update dependencies correctly, stop and report the specific error logs. I will manually review all changes before any deployment.
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.