Claude Code

6 articles

47 Scripts to 15: Cleaning a Research Codebase

Research projects accumulate code debt. An AI agent can map dependencies, identify dead code, and reorganize months of accumulated scripts, with counterfactual tests to verify nothing broke.

Nov 2025 · Methodology

6,613 Stores, $147, Zero Lost Data: Robust API Collection

Collecting location data from Google Places API at scale requires handling rate limits, pagination, and failure recovery. A naive script fails in predictable ways.

Nov 2025 · Methodology

400 Labels to 94% Accuracy: Validating Grocery Store Data

Google Places returned thousands of 'grocery stores.' Many weren't. Here's how a classifier separates real grocery stores from gas stations and liquor stores.

Oct 2025 · Methodology

7 Copy-Paste Cycles to 1 Command: What Changes with Agent-Based Coding

The difference between chatbot-based coding and agent-based coding is categorical, not incremental. Here's what changes when AI can read your entire codebase.

Oct 2025 · Methodology

From Methods Paragraph to Working Pipeline: AI-Assisted Implementation

A well-written methodology section is almost executable code. The gap between describing a procedure and implementing it has narrowed dramatically with agent-based coding tools.

Oct 2025 · Methodology

One Context File, Zero Re-Explanations: Teaching AI Your Research Project

Every new coding session with AI starts the same way: re-explaining the project. A single CLAUDE.md file loads automatically every session. Write the context once; the agent reads it every time.

Oct 2025 · Methodology