The most important design decision in an email classifier isn't the model — it's the label set, and...
The most important design decision in an email classifier isn't the model — it's the label set, and here's the one I keep coming back to:
You triage email into one of four categories:
URGENT — production incidents, executive requests; reply within 1 hour
ACTION — code reviews, meeting follow-ups; reply same day
FYI — informational, no response needed
My classifier calls an LLM on every single email. The LLM is not allowed to classify the email. That...
Every shared support inbox eventually becomes a triage problem: 80 unread messages, no agreement on...
In today's fast-paced world, managing email alerts can be a daunting task
AI tech is revolutionizing the way we handle emails by categorizing them according to their urgency
In AI monitoring systems, not every decision belongs to the LLM. Some decisions should stay deterministic.
I've been using LLMs to classify GitHub pull requests into changelog categories. The goal:...
