How to use Claude to build a stock viewer
An author generated a Rust desktop Indian-stock viewer in three days using Claude Code and OpenCode, with NSE report downloads and SQLite storage.
news.ycombinator.com
Suggested prompt
Suggested prompt written by Agents In Use, not the source author. Replace bracketed inputs and review tool permissions first.
Build a desktop viewer for [market data source] using Rust, egui and SQLite. Download [report format], store end-of-day prices locally and display them. Use [application logs] to diagnose failures, and keep [future analytics features] separate from the initial viewer.
Reach people exploring AI agents
See placements →Evidence at a glance
Sourced account- Source author
- brainless
- Original account
- Read the source ↗
- Published
- Source link checked
- Reported result
- The author reports generating Indistocks in three days and describes it as fast out of the box; chart improvements and an AI analyst remained planned.
- Human involvement
- The author supplied feature descriptions and occasional logs; the post does not describe a formal review or testing process.
A linked account supports attribution. It does not mean we independently reproduced its result.
Report an issue with this case
Open correction emailOpens your email app with the case link included. Nothing is sent automatically.
How the agent did it
- Described features to Claude Code and OpenCode to generate the desktop app.
- Copied application log output into prompts at a few troubleshooting points.
- Built the Indian-stock viewer with an NSE report downloader and SQLite3 data.
The author built Indistocks, a desktop application for viewing Indian stocks, using a mix of Claude Code and OpenCode. The application uses Rust, egui and SQLite3. Its downloader retrieves NSE India reports containing daily end-of-day stock prices, giving the viewer a local database of market data.
The author says generating the application took three days. Most of the time, describing desired features was enough to move development forward. At a few points, they copied standard application log output into prompts to address issues. They credit the Rust compiler with doing much of the heavy lifting and describe the resulting application as fast out of the box, without providing a measured benchmark.
OpenCode used either GLM 4.5 or Grok Code Fast 1 alongside the Claude Code work. The post does not separate which agent built particular components. Chart improvements and an AI-assisted stock analyst were future plans, rather than completed features. The proposed analyst would translate screening ideas into SQL against the existing database. Who it's for: developers interested in local market-data viewers who can steer a coding agent using feature requests and diagnostic logs.
Prompt
Suggested prompt (written by Agents In Use, not the author's)
Source: Hacker News · brainless
Frequently asked questions
Which tools were used to build the viewer?
The author used Claude Code and OpenCode, with OpenCode running either GLM 4.5 or Grok Code Fast 1. The app uses Rust, egui and SQLite3.
Was the AI stock analyst already implemented?
No. The author describes it as a planned addition, along with stock-chart improvements. The completed app includes a downloader for NSE India end-of-day reports.
More details
About this account
Claude Code and OpenCode generated the application from feature descriptions, with occasional diagnostic logs supplied by the author.
Platform: Hacker News. Attribution: https://news.ycombinator.com/item?id=45564200. Prompt: Suggested (written by Agents In Use, not the author's). Sourced by the Agents In Use pipeline.
Credit: brainless on Hacker News
Source published
Added to Agents In Use
Source checked
Tools and topics
Claude Code · OpenCode · Rust · egui · SQLite3
Desktop apps · Rust · Market data
Editorial completeness: 100/100. Measures documented fields, not agent performance or verified outcomes.