Comments URL: https://news.ycombinator.com/item?id=40663687

Points: 9

# Comments: 3

1. Business analysts can spend up to weeks per month updating existing month-end Excel reports with new data.

2. Python automations can reduce the updating process to a matter of minutes.

3. BUT actually understanding the Excel file & writing the Python automation code can take several months.

4. Tools like ChatGPT are hugely useful when given a specific translation task — eg: convert the formula =SUM(A1, B1) to Python — but get completely lost on more complicated translations.

So I'm trying to build an AI-powered tool that can automatically convert Excel workbooks to Python. The key to doing so is 1) using plain old programming to parse the Excel file and build a translation plan (finding all of the unique tables in the Excel file, identifying repeated logic, determining the correct order to output the code), and 2) to prompt an LLM to execute each piece of that translation plan one at a time.

If you spend hours per month automating Excel files and want to be an early adopter, sign up here https://naterush1997.typeform.com/to/SIKccZHc

Comments URL: https://news.ycombinator.com/item?id=40298877

Points: 2

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=37080735

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=36259882

Points: 1

# Comments: 0

This nails one of the biggest issues that we're trying to help Mito users with -- code that meets __changing__ requirements. ie: the input data column headers change.

The best approach we have right now is giving users flexibility to parametrize their script (ie: tell the script the right column header or reference columns by position instead of name)

It turns out that teams that have moved their data to Snowflake tend to avoid these issues primarily because the schema of their data changes much less frequently.

> Bridging the Abstraction Gap Between End-User Programmers and Code-Generating Large Language Models

I love the idea of giving users feedback on how to get better at prompting the LLM. I think the key to using this approach within Mito is giving users guidance at the right time -- sometimes shorter prompts get the job done, and they're always easier to write :)

A really sweet integration of this approach could be: when the LLM generated code errors or when we notice that the user undoes their previous prompt, we offer the user help in converting non-working prompts into ones that follow best practices of breaking complex tasks down into small steps.

> On the Design of AI-powered Code Assistants for Notebooks - uses Mito as part of their case study

Andrew McNutt, one of the authors presented this paper here: https://www.youtube.com/watch?v=g0prh8mE3bI Their different classifications of notebook code-gen tools has actually been super helpful in my own thinking. Thanks for the help, Andrew if you're a HNer

I've personally never seen a Mito users with a detailed enough spec of their report that an LLM would be able to use it to check compliance -- but maybe if we built the functionality users would create them...

I created Mito, a spreadsheet the lives inside of Jupyter. We've seen a ton of our users using Jupyter and ChatGPT playground side by side.

We're also experimenting with bringing chatgpt into Jupyter through the Mito spreadsheet. (https://blog.trymito.io/5-lessons-learned-from-adding-chatgp...)

Looking forward to trying this out.

[1]https://jupyterlab.readthedocs.io/en/stable/user/rtc.html

Comments URL: https://news.ycombinator.com/item?id=35214628

Points: 5

# Comments: 0

Mito doesn't have real time collaboration though. That is, not until Jupyter real time collaboration becomes more popular (https://jupyterlab.readthedocs.io/en/stable/user/rtc.html)

> In a typical scenario, the customer success team who is in charge of this activity has to work back and forth with the customer. The customer has to resolve manual (unintended) errors.

+ 100. This is even the case when analysts are working with datasets that are created by their colleagues at the same company. Since most companies don't have clear standards for column header labelling, etc. getting a new dataset and incorporating it into an existing workflow requires collaboration with others from inside your company.

Once you generate the code, you could copy it into your pipeline so that you pull the code from the last.fim api, preprocess it with the Python code that Mito generated, and then dump it into the LiteDB.