Technology · Profession
Plain-language SQL, viz first-passes, and exec-summary drafts — speed-up, not autopilot.
Recommended tools · 12
Data analysts use Codeium to compress the boilerplate-and-tests phase of a task so judgment time stays focused on design and edge cases.
Data analysts use Cursor to compress the boilerplate-and-tests phase of a task so judgment time stays focused on design and edge cases.
Data analysts use GitHub Copilot as a coding pair — completion, refactor suggestions, test scaffolding — with code review still required before merge.
Data analysts use Replit AI as a coding pair — completion, refactor suggestions, test scaffolding — with code review still required before merge.
Data analysts use Sourcegraph Cody to compress the boilerplate-and-tests phase of a task so judgment time stays focused on design and edge cases.
Data analysts use Tabnine as a coding pair — completion, refactor suggestions, test scaffolding — with code review still required before merge.
Data analysts lean on ChatGPT for first-pass drafts, structured outlines, and rubber-duck thinking on tricky problems before client work goes out.
Data analysts use Claude to break a complex ask into pieces — surface the right questions, draft a candidate answer, then refine it before delivery.
Data analysts lean on Gemini for first-pass drafts, structured outlines, and rubber-duck thinking on tricky problems before client work goes out.
Data analysts use Monica to break a complex ask into pieces — surface the right questions, draft a candidate answer, then refine it before delivery.
Data analysts use Perplexity to break a complex ask into pieces — surface the right questions, draft a candidate answer, then refine it before delivery.
Data analysts lean on Poe for first-pass drafts, structured outlines, and rubber-duck thinking on tricky problems before client work goes out.
Prompts to try
You are assisting a data analyst. Look at the code below and propose a refactor. Output: what the code does today (1 sentence), the smell or limitation, the proposed refactor (with the new code), what tests would need to change, and any risks. Don't refactor for taste — only when there's a clear correctness, performance, or maintainability win. Code: [paste code here]
As a data analyst, summarize the error below for someone non-technical: what failed, the most-likely root cause (with confidence), what would fix it, and how to know we fixed it. End with what I should ask the engineer if I want to dig deeper. Keep under 200 words. Don't paste the trace back at me. Trace: [paste here]
Generate API documentation for the code below as a data analyst would write it. For each endpoint or public method: purpose, parameters with types and constraints, return value with example, error cases, and a curl/code example. Match the style of [existing docs / OpenAPI / Markdown]. Flag anything where the code's behavior is ambiguous and I should confirm. Code: [paste here]