## Metadata - Author: [[Benn stancil|Benn Stancil]] - Full Title:: The Smol Analyst - Category:: #🗞️Articles - Document Tags:: [[GPT-3 me va a quitar el trabajo pero yo tengo que estar entrenando algoritmia de bajo nivel|Gpt 3 Me Va A Quitar El Trabajo Pero Yo Tengo Que Estar Entrenando Algoritmia De Bajo Nivel]], - URL:: https://benn.substack.com/p/the-smol-analyst - Finished date:: [[2023-08-19]] ## Highlights > One of the small ironies of today’s SQL chatbots is that they help people do exactly a thing that data teams try to discourage. As analysts, we ask our colleagues to help us understand [how our work will be used](https://www.caitlinhudon.com/posts/2020/09/16/data-intake-form). They shouldn’t request some piece of data; they should instead [tell us what they’re trying to achieve](https://davidsj.substack.com/p/dear-stakeholder#:~:text=When%20you%20ask%20us%20for%20help%2C%20tell%20us%20what%20you%E2%80%99re%20trying%20to%20achieve.%20Don%E2%80%99t%20just%20say%20%E2%80%9CI%20need%20this%20piece%20of%20data%E2%80%9D%E2%80%A6). And if they don’t tell us what they want to use some data pull for, the less tactful among us [pepper them with demands](https://www.youtube.com/watch?v=wCoJ8YS6Pr0&t=175s) to explain why they need it. ([View Highlight](https://read.readwise.io/read/01h85cm3283a87qhete1d8476w)) > we don’t recommend that analysts ask these questions just to make their jobs easier; we also recommend it because [we can’t give a useful answer](https://win.hyperquery.ai/p/should-we-be-more-persuasive#%C2%A7understand-how-your-work-will-be-used) without it. ([View Highlight](https://read.readwise.io/read/01h85cqpmbrmd98gz8vxbfe12m)) > But, encoding “business context” into some YAML file sounds ridiculous, and describing every detail to a chatbot anytime you want to answer a question sounds exhausting.[6](https://benn.substack.com/p/the-smol-analyst#footnote-6) For this reason ([among others](https://benn.substack.com/p/we-dont-need-another-sql-chatbot)) I’m generally skeptical that these bots will [be that revolutionary](https://twitter.com/gaganbiyani/status/1659204770438213638) ([View Highlight](https://read.readwise.io/read/01h85crvr6ww8xfsq7126s1k5x)) > Then, just as they’d do for a junior analyst, the producer would send back feedback: This number looks off; this explanation doesn’t quite make sense; can you dig into this unexpected anomaly? The bot creates another draft, the exec gives more direction, and so on. ([View Highlight](https://read.readwise.io/read/01h85csr9n3n4ksg0hpvkr4pyy)) > Second, the back-and-forth could also help people *ask* better questions. We often don’t know what we want until we start looking for it. Just as it’s almost impossible to write a perfect product spec without testing an imperfect prototype first, it’s very hard to ask exactly the right question before seeing the answers to a few of the wrong questions. A smol analyst would encourage this sort of iterative exploration, which is good for both user and agent ([View Highlight](https://read.readwise.io/read/01h85cwppx8y0je83yn81w4pws)) > There is, however, at least one very big reason why a smol analyst wouldn’t be as useful as a smol developer. In software, *how* code works is in some sense irrelevant; all that matters is that it works. I can test my ad blocking Chrome extension without knowing a line of Javascript, or that Javascript exists at all. If the tool does what I want it to, it works, no matter how “bad” its codebase. > In data, black boxes don’t work. Computational process matters. You can’t validate a dashboard by testing that it produces a reasonable-looking chart; you have to make sure that the logic behind its calculations are correct. SQL is [declarative](https://en.wikipedia.org/wiki/Declarative_programming), but used for [imperative](https://en.wikipedia.org/wiki/Imperative_programming) ends—we need to know how it works, step by step. Software is the opposite ([View Highlight](https://read.readwise.io/read/01h85cxh25ys9q2dysnb3p7rc7))