Poozle
AI
llm data integration
SHOW HN2023
132points
39comments
#482of 3,109 in 2023
Top 16%of 2023 by points
How HN took it
CuriousMostly questions and neutral comments
3 positive, 10 neutral or asking, 0 mixed, 7 critical, out of 20 comments about the project. Thread score -0.07.
Design: 0 for, 5 againstIdea: 2 for, 0 againstExecution: 0 for, 1 againstPrivacy: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Timely and useful idea for LLM context
From 2 comments
This looks excellent and very timely. We just started hand rolling our own ETL process with Python and Github Actions to ingest from various SaaS sources to a central DB for…
oldsj on HNThis looks neat. https://github.com/ShishirPatil/gorilla feels like a project with certain similarities here. How would you compare yourselves to them?
retakeming on HN
Objections
Unclear what makes it specific to LLMs
From 1 comment
Definitely a difficult problem you're taking on here, but I don't see anything specific to LLMs here? How or why are you marketing towards LLMs? How do you compare to the larger…
haxton on HN
Normalising entities across services loses fidelity and terminology differs
From 2 comments
This is a very difficult problem. How do you deal with losing data fidelity? If one service's entity has X field, but all the others don't, do you include it or not? How do you…
tuckerconnelly on HNMaybe ticket isn't a great example. Another general problem I've had with mappings is say, one service uses a one-to-one relationship, and another puts both entities into a…
tuckerconnelly on HN
Name has an unfortunate slang meaning
From 2 comments
Fwiw, while I haven't heard "poozle" very much as an American, I've heard it enough that my mind instantly went to the unfortunate definition when I saw it here. Meanwhile, I've…
eurleif on HNSlangonym for vagina. According to The Big Book of Filth (1999) coinage and usage dates back to the late 19 th century.
acqbu on HN
Cross-department data access may be a security risk
From 1 comment
Pozzle just sounds like a violation of encapsulation/departmental permiters at best, and a security nightmare at worst.
TZubiri on HN
Requests
Add personal finance integration like Plaid
From 1 comment
This looks excellent and very timely. We just started hand rolling our own ETL process with Python and Github Actions to ingest from various SaaS sources to a central DB for…
oldsj on HN
Allow users to define their own schema
From 1 comment
This sounds very useful, I wonder if you have given thought to users providing their own schema to query rather than using yours(I would assume a LLM or the likes should be able…
theskcd on HN
Questions
How does it compare to Nango, Merge and Gorilla
From 3 comments
Definitely a difficult problem you're taking on here, but I don't see anything specific to LLMs here? How or why are you marketing towards LLMs? How do you compare to the larger…
haxton on HNThis looks neat. https://github.com/ShishirPatil/gorilla feels like a project with certain similarities here. How would you compare yourselves to them?
retakeming on HNVery cool product! Have you consider relying on Gorilla for integrations? https://gorilla.cs.berkeley.edu/ https://github.com/ShishirPatil/gorilla https://arxiv.org/abs/2305.15334
toomuchtodo on HN
How is data staleness handled and does each user need to authorise
From 1 comment
Definitely a difficult problem you're taking on here, but I don't see anything specific to LLMs here? How or why are you marketing towards LLMs? How do you compare to the larger…
haxton on HN
How does it compare to building context in LangChain
From 1 comment
Hey, very cool work! How does your solution compare to directly building the context in a framework like LangChain? I’m an AI researcher, so am a little further from this area,…
hsikka on HN
Alternatives named
Nango
From 1 comment
Definitely a difficult problem you're taking on here, but I don't see anything specific to LLMs here? How or why are you marketing towards LLMs? How do you compare to the larger…
haxton on HN
Merge
From 1 comment
Definitely a difficult problem you're taking on here, but I don't see anything specific to LLMs here? How or why are you marketing towards LLMs? How do you compare to the larger…
haxton on HN
Gorilla
From 2 comments
This looks neat. https://github.com/ShishirPatil/gorilla feels like a project with certain similarities here. How would you compare yourselves to them?
retakeming on HNVery cool product! Have you consider relying on Gorilla for integrations? https://gorilla.cs.berkeley.edu/ https://github.com/ShishirPatil/gorilla https://arxiv.org/abs/2305.15334
toomuchtodo on HN
LangChain
From 1 comment
Hey, very cool work! How does your solution compare to directly building the context in a framework like LangChain? I’m an AI researcher, so am a little further from this area,…
hsikka on HN