Update a legacy Telegram bot and refactor an app
The author used Replit Agent to update a Telegram bot to a newer API, which only worked after some iterations, and to refactor a card-collection app including a database schema change.
Done withReplit Agent
- What they did
- For the Telegram bot, the author found the Agent needed a project created first, so they spent $0.25 on a fresh bot and then added their legacy code. They asked it to copy the new API's functionality. For the card app, they had it do non-trivial refactors, including a database schema change so cards could belong to multiple collections.
- How it went
- The card-app refactor went fairly smoothly. The Telegram update was a disappointment: even a basic bot took several iterations, and the legacy-code update did not work well. The author calls it a disaster.
- Worth knowing
- The whole month of experiments used the $25 plan plus about $4 of extra credit. Adding unit tests to the card app disrupted its Workflows, so the tests ended up unused.
Try it yourself with Replit Agent
Update my Telegram bot in [project name] from the old [library or API version] to the current [new library or API version], keeping all existing commands working. Run the bot after each change, fix any errors you hit, and tell me which commands you tested. Don't change the database schema or delete any data without showing me the plan first.
Want help getting this working? Join the Vibe Coding Academy ↗ Run by Alex Finn, who also runs this site.
Source: aiartisan.substack.com · Undated
Related use cases
Build a searchable map of funded companies
A software engineer had Replit Agent build a searchable map of Wefunder brick-and-mortar companies in about 3 hours for about $22.
Build and ship a micro-SaaS in three hours
A developer used paid Replit to build and deploy a micro-SaaS to production in about 3 hours, with database, domain, hosting and monitoring handled.
Build and deploy a meeting app from a prompt
A user had Replit Agent create a meeting app with dashboard, logic and analytics, and deploy it live without manual code changes.
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
Build and test a simple endpoint project with Devin
A reviewer had Devin set up a project, write code, install dependencies, test endpoints and add error handling in about 4 minutes on a simple task.
Diagnose Kubernetes alerts with MCP servers
An n8n agent triggered by Alertmanager queries Kubernetes, Grafana and other MCP servers and posts a diagnostic report with root-cause hypotheses in a Mattermost thread.
Get 5 like this every morning
The best things people got an AI agent to do, each with the prompt to try it.