Feed
Pro
Search

Sign in
FactoryKit - the AI software factory: tasks in, pull requests out Bug0 - The AI-native e2e QA regression testing The foreword by Hashnode - official blog from the Hashnode team Passmark - The open-source AI framework for regression testing Hashnode gql skill - let your AI agent publish to your Hashnode blog Hackathons Changelog Brand @hashnode on X Hashnode on LinkedIn Support - hello+support@hashnode.com Code of Conduct Terms Privacy Sitemap

Search Hashnode

Search posts, tags, users, and pages

@sarahpan

Sarah Pan

@sarahpan·Los Angeles, USA·Joined July 2026

Software engineer exploring AI, games, and creative workflows.

About

TokenBay Engineer Keep working on AI, Games and dogs

Available for

Happy to chat about AI infrastructure, open source, coffee, keyboards, or anything interesting you're building.

Sarah Pan's blogs

AI Experiments Lab-TokenBaysarahtokenbay.hashnode.dev9 posts

About

TokenBay Engineer Keep working on AI, Games and dogs

Available for

Happy to chat about AI infrastructure, open source, coffee, keyboards, or anything interesting you're building.

Sarah Pan's blogs

AI Experiments Lab-TokenBaysarahtokenbay.hashnode.dev9 posts

Articles Comments4

Recently published

SPSarah Paninsarahtokenbay.hashnode.dev·Jul 23 · 6 min read

When AI Models Disagree, Don’t Use Majority Vote

Asking a second AI model is one of the easiest ways to check an uncertain answer. But what happens when the second model disagrees with the first? You ask a third model. Now one model says A, another

SPSarah Paninsarahtokenbay.hashnode.dev·Jul 20 · 7 min read

Building a Model-Agnostic Agent Harness: What Breaks When You Switch LLMs

Six months ago, I made a bet on a project: let users pick their LLM. Three months later, I realized the dropdown was the easy part. This is what the hard part looked like. The Model Changed. Everythin

SPSarah Paninsarahtokenbay.hashnode.dev·Jul 16 · 6 min read

The API Call Succeeded. The Workflow Still Broke.

We're building TokenBay, a unified API that routes requests across GPT, Claude, Gemini, DeepSeek, and a few dozen other models. A few weeks ago we ran a fairly boring internal test: send the same stru

SPSarah Paninsarahtokenbay.hashnode.dev·Jul 15 · 5 min read

The Best AI Model Is Usually the Wrong Question

Developers keep asking which AI model is the best. It sounds like a reasonable question. There are leaderboards, benchmark charts, side-by-side comparisons, and a new “best model” every few weeks. But

SPSarah Paninsarahtokenbay.hashnode.dev·Jul 14 · 4 min read

Three AI APIs Now Look Almost Compatible. They Still Aren’t Interchangeable.

OpenAI, Claude, and Gemini now look surprisingly similar at the API level. In some cases, switching providers requires little more than changing an API key, a base URL, and a model name. But this comp