I'm doing research to sort through all antidotal or hyperbolic statements about how AI is actually impacting day-to-day code writing.
The link is to the survey driving research. It's just 4 questions and does not ask for your email.
Personally, I've been finding I'm 2-3x more efficient as I lean into the tooling. But I've seen many say it's not impactful at all and have seen some say it's >10x!
So does the CSV have multiple languages within it? Why a CSV verse various documents in a directory (like Google Drive?).
Just curious, I'm working on AskJack.io and the multiple users, find anything, no matter the context, is exactly what we're doing. But we haven't tried to tackle languages yet.
"So does the CSV have multiple languages within it?"
For context, it's for Indonesia. So you do have urban areas and expats who can mostly speak English. But English isn't taught in school. Arabic, Chinese, Dutch are popular too.
Bahasa Indonesia is the formal version, but most will be more familiar with the various languages. Most states will have their own dialects, at least 5 major dialects. The difference is not like American/English, but closer to Scots/English.
The challenge is that many people are comfortable with writing in their own dialect, even if they can read others. So we can't possibly use all the languages that could be input, but it's fine if it outputs in a somewhat different dialect. For the most part, sentence structures are similar and "bua" and "buah" are still recognizable to people with different dialects, likely to AI as well. But programmatic algorithms wouldn't handle something like "buwa" properly.
To answer the question, the CSV will mostly just have informal Bahasa Indonesia. English questions will miss sometimes, so we've added English as well for the ones that miss. More data is more effective.
"Why a CSV verse various documents in a directory (like Google Drive?)"
Could be anything really, but we tend to have a loose format for data & notes, and then have a script that strips out or combines from other sheets into something that's cleaner to read and search. PDF, XLS, etc is hard to get consistent. But something like JSON, XML, YAML are still acceptable as long as we can script it.
AskJack seems to be a bit low code though. We can build our own and have reasons to have more control over certain bits. So a B2B solution over the RAG part would be nice.
I've started interviewing SaaS founders (from bootstrapped to VC-backed) about lessons learned building and operating SaaS companies. The is the first one, Ash did a fantastic job, dropping some true gems.
I’m building https://Interweaveapp.com a customer product feedback loop application to help startups and product managers manage the full lifecycle of feedback.
Feedback turns into insights, which turn into ideas, which turn into shipped product. Interweave helps collection of feedback (interviews, surveys, bug reports, and idea boards), helps you synthesis that, helps you prioritize work, and connects back to users when you ship something they're linked to.
Can you elaborate a bit on the 'insight' and 'idea' artifacts? What do those look like? Are they tied in any way to metrics for validation (and perhaps invalidation if something changes at some future time)?
At this point in my career I can literally build anything that can be built. I have 100s of ideas. Why do I tech cofound with you for 25% equity vs just building my own idea for 100%?
Currently we're in an open space and the moment I can convince the CEO we'll do away with it. Collaboration that matters for my team happens in two places: our morning meetings and in HipChat. Otherwise lots of distractions, sure it can be fun at times, but at what cost?
We're focused on solo owners and other busy local service based companies.
We're using OpenAI's newest real time voice API, which has been surprisingly responsive.