Teams7 updates



The old Yankees
Intake AgentSP
Stepan Pershko Final
May 11, 09:46 PM
FINAL!
VK
May 12, 01:04 AM
?
SP
Stepan Pershko
May 11, 09:46 PM
we have submitted :)
?
SP
Stepan Pershko
May 11, 06:53 PM
Agent Driven Recommendations
VK
Viktar Kushch

May 11, 07:17 PM
VK
Viktar Kushch
If not UI - please plan provide side by side runs of one and another
May 11, 07:17 PM
?
SP
Stepan Pershko
May 11, 06:38 PM
DON Helper to help you to proceed with correct pricebooks if they were not clear/correct for your request
VK
Viktar Kushch

May 11, 07:16 PM
?
SP
Stepan Pershko
May 7, 04:20 PM
We decided to review users interaction with price books recommendations.
Currently, the whole search is based on FTS + semantic mix which lacks context: vectors rely only on item description, UOM, currency, and price. In general, search is missing critical context like category, previous user requests history, additional data we can bring to our search engine while interacting with the user.
The goal is bringing our users a useful tool they can use themselves while creating new requests - an agent which asks additional data needed for recommendations, which will adjust to their search requests as used & decrease load from support teams.
We're exploring whether to show low-confidence results or keep interacting with the user until we are ready to recommend, letting users refine search queries interactively with an agent. Key questions include which data to embed for the search, how to handle noisy user input, and whether to analyze previous request history for better suggestions. Still no clue how to proceed if there are no strong recommendations exist, we're deciding between fallback options or prompting users for clarification.
AT
Andrey Timonin

May 7, 07:10 PM
AL
Aliaksandr Layuk

May 8, 03:06 PM
?







Please add short pitch and link to the Git