LLM core use cases
An evolving catalog. #taxonomies
generating end-use# content
e.g. Marketing copy, sales pitches
parsing unstructured data
Documents to data e.g. invoices, receipts
(Vision models for getting text out of pdfs and images )
Classifying
Sentiment analysis
Poor man’s switch statement
Summarizing
Emails, meeting transcripts, customer feedback, long documents,
RAG - fact retrieval
- Knowledge base look up
- Look up data in other systems (order status, travel itinerary, customer record), but this is borderline AI Agents
Deep Research
This is actually agenting and summarizing.
Data analysis (uses python)
Writing assistant
Brainstorming / [rubber-ducking](RubberDuck)
Meta:
agenting
(loop of reasoning, tool calls, or completion)
- orchestration of sub-agents
- single-purpose LLM calls as tool call (“agents as tools?”)
Non-deterministic general purpose compute unit
- Poorly-specified integration orchestration
See also:
Kinds of AI
Image use cases
diffusion model use cases
Multimodal:
STT / TTS