> Other kinds of messages take longer. Emails have to be manually read and sorted. Faxes have to be digitized and emailed. [...] By contrast, congressional staffers tally phone calls right away.
Golly. Is this a problem? Hasn't this been solved already? Do they want to solve it? How much do they want to solve it, in terms of United States Dollars?
This is now easy for many HNers to build, with the hard parts now done by free off-the-shelf components.
The customer could have those email tallies even faster than the phone staffer tallies, for the timely read on constituents that the 5calls.org Web page suggests.
And then they can manually or semi-manually review the emails later, for nuance and genuine responses. But they got the important tallies immediately, on their live dashboard and timely alerts.
(But keep those human staffers answering phone calls, since I'd guess that AI on phone there would alienate the very engaged voters who still make phone calls.)
Please no AI interpreting sentiment in emails, the error rate / hallucinations at that scale would be dangerous.
To be clear, not necessarily sentiment analysis of the email (the pre-LLM kind, like are they angry, aggressive, etc.); but sentiment tally about voting on the legislation, like a phone operator might do, which might only be identifying which bill/issue is being talked about, and whether "vote for" vs. "vote against".
The limitations of that is part of why I suggested that following up with review of the email by a human later, for nuance. The other part is so they know they're reaching a human at their representative's office, not just talking to a machine.
I don't know much about politics other than Sorkin-esque TV dramas, but the original Web page said that timely tallies could help a politician avoid being in the situation of having to walk back a stated position on something. So I'd guess that's one way a real-time tally could still be very valuable, and I think an LLM is up to the hard parts of it.