Agents In Use
What’s new todayLast update
3 use cases added today

How to use Claude to build an election dashboard

Kinjuriu used Claude Opus for planning and design and Claude Sonnet for most coding of a published US election dashboard covering 2000–2024, with Python data cleaning and Astro and D3 visualizations.

OUR ADAPTATION

Suggested prompt

Suggested prompt written by Agents In Use, not the source author. Replace bracketed inputs and review tool permissions first.

Help me plan and build an interactive election dashboard using [historical election dataset] for [year range]. Plan the views and design first, then implement with Astro and D3. Include geographic views using [map datasets], Python data cleaning, source notes, and GitHub Pages deployment through GitHub Actions. Clearly mark results that are pending certification.

Evidence at a glance

Sourced account
Source poster / publisher
Kinjuriu
Original account
Read the source ↗
Published
Source link checked
Reported result
The author published an interactive dashboard covering US congressional control from 2000–2024, including state-by-state Senate race and House delegation maps. The 2026 results were still pending certification and had not been added.
Human involvement
The post does not describe formal review steps; the author built and published the dashboard and planned to add certified 2026 results later.

A linked account supports attribution. It does not mean we independently reproduced its result.

Report an issue with this caseOpen correction email

Opens your email app with the case link included. Nothing is sent automatically.

How the agent did it

  1. Use Claude Opus to plan and design the election dashboard.
  2. Have Claude Sonnet write most of the dashboard code.
  3. Clean the election data using Python.

Kinjuriu built an interactive dashboard to explore which parties controlled the US House and Senate from 2000 through 2024. The idea came while watching the 2026 midterm elections: the author wanted to understand historical control, how often it changed, and whether the current election introduced anything new.

The author used Claude Opus for planning and design, then Claude Sonnet wrote most of the code. They describe building the dashboard with JavaScript and cleaning the data using Python. The site uses Astro and D3, with us-atlas TopoJSON and Natural Earth supplying geographic material for the maps. It includes state-by-state views of Senate races and House delegations, alongside pages covering Congress, governors, a Senate story, notes, and sources.

The finished site was hosted on GitHub Pages and deployed through GitHub Actions. Its historical coverage did not yet include the 2026 results; the author planned to add those after state certification. The post describes a published dashboard, but does not describe a formal review of Claude’s code or the cleaned election data.

Who it's for: Developers building historical data visualizations who want AI help with planning, design, and implementation.

Prompt
Suggested prompt (written by Agents In Use, not the author's)

Source: Hacker News · Kinjuriu

Frequently asked questions

Which Claude models contributed to the dashboard?

The author used Claude Opus to plan and design the dashboard, while Claude Sonnet wrote most of the code.

Does the dashboard include the 2026 election results?

Not at the time of the post. The author said the 2026 results would be added once the states certified the elections.

What tools supported the maps and deployment?

The author named Astro, D3, us-atlas TopoJSON, and Natural Earth for the site and geographic material, with GitHub Pages hosting and GitHub Actions deployment.

More details

Remaining steps

  1. Build the site using Astro, D3, and geographic datasets.
  2. Host the dashboard on GitHub Pages and deploy through GitHub Actions.

About this account

Claude supported planning and design and wrote most of the code; the author also reports data cleaning, site construction, hosting, and deployment.

Platform: Hacker News. Attribution: https://news.ycombinator.com/item?id=50392130. Prompt: Suggested (written by Agents In Use, not the author's). Sourced by the Agents In Use pipeline.

Credit: Kinjuriu on Hacker News

Source published

Added to Agents In Use

Source checked

Tools and topics

Claude Opus · Claude Sonnet · Python · Astro · D3 · us-atlas TopoJSON · Natural Earth · GitHub Pages · GitHub Actions

Data visualization · Elections · Web development

Editorial completeness: 100/100. Measures documented fields, not agent performance or verified outcomes.