Building With DEV: A Practical System
Label, prioritize, and route incoming issues without a maintainer. The problem it solves: OSS maintainers spend hours triaging duplicate or under-specified issues. This guide pulls together everything on Onexial tagged dev — 14 connected nodes across definitions, workflows, tool stacks, comparisons, prompts and applied use cases — and orders it the way you would actually learn it: vocabulary first, then process, then tooling, then execution. Every item below links to a full node with its own examples and connections, so you can go as deep as you need without losing the map.
Workflows: how DEV runs end to end
Concepts only matter once they become a repeatable process. Below are 1 documented workflows that apply DEV to a concrete problem, with the steps, the tools involved and the variations worth testing.
The DEV tool stack
A stack is a set of tools chosen for one job, not a list of favourites. These 2 stacks show which combinations hold up in production for DEV, and what each layer is actually responsible for.
Trade-offs and comparisons
Most DEV decisions are trade-offs rather than right answers. These 6 comparisons break down the real differences, when each option wins, and the recommendation for the common case.
LangChain vs Vercel AI SDK
Kitchen-sink orchestration vs lean SDK for shipping apps.
Cloudflare Workers vs Vercel Functions
Two edge runtimes for AI apps.
TanStack Start vs Next.js
The new full-stack React contender vs the incumbent.
Cursor vs Windsurf vs GitHub Copilot
Three AI coding environments.
Cursor Agents vs Devin vs Lovable
Three ways AI writes code for you in 2026.
tRPC vs REST vs GraphQL
Three API styles for TypeScript apps.
Prompts you can reuse
Prompts are reusable components. Each of these 4 prompts is written to be dropped into a DEV workflow with minimal editing, including the context it expects and an example output.
SQL Explainer Prompt
Explain a SQL query in plain English with data implications.
Error Diagnoser Prompt
Turn a stack trace + code into a ranked diagnosis with next steps.
Code Refactor Advisor Prompt
Get a ranked list of refactors before touching a file.
Test Case Generator Prompt
Generate meaningful test cases from a function signature.
Real applications of DEV
Finally, 1 applied use cases: the situation, the system used to solve it, and the outcome. This is the layer that turns DEV from an idea into leverage.
Frequently asked questions
- What does the Automated GitHub Issue Triage workflow do?
- On issue open, embed and compare to existing issues; classify severity and area; comment with next steps.
- What problem does Automated GitHub Issue Triage solve?
- OSS maintainers spend hours triaging duplicate or under-specified issues.
- How many steps does Automated GitHub Issue Triage take?
- 5 steps. It starts with github webhook fires on new issue. and ends with post a checklist of missing info if the template wasn't followed..
- Which tools does Automated GitHub Issue Triage need?
- It uses no-code-automation-stack — each linked below with its own node.
- What is the difference in LangChain vs Vercel AI SDK?
- LangChain covers every pattern under the sun; Vercel AI SDK focuses on typed, streaming-first primitives for TypeScript apps.
- What are the main points of comparison?
- Scope: Everything (LangChain) vs Focused (Vercel) · Type safety: Improving (LangChain) vs First-class (Vercel) · Streaming UX: Manual (LangChain) vs Batteries included (Vercel) · Learning curve: Steep (LangChain) vs Shallow (Vercel)
- Which one should I choose?
- Prefer Vercel AI SDK for product surfaces. Reach for LangChain when you need its long tail of integrations.
- What is the difference in Cloudflare Workers vs Vercel Functions?
- Both run at the edge. Cloudflare is cheaper at scale and integrates with R2/D1/Vectorize; Vercel ships tighter with Next.js and the AI SDK.