[{"data":1,"prerenderedAt":314},["ShallowReactive",2],{"project-37180017":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":29,"sentiment":30,"stance_mix":31,"scored_comments":36,"aspects":37,"strip":45,"post_text":46,"what":47,"said":66,"maker_in_thread":167,"shape":179,"grid":182,"attempts":277,"same_week":278,"maker_shows":39,"maker_hidden":306,"reader_version":307,"card":308},"37180017","Poozle","open-source Plaid for LLMs","title","Show HN: Poozle – open-source Plaid for LLMs","https:\u002F\u002Fgithub.com\u002Fpoozlehq\u002Fpoozle","github.com","harshithmul",1692383274,2023,132,39,482,3109,16,"notable","ai","llm data integration","api",[24,25,26,27,28],"unified api","saas integration","llm context","oauth","etl","curious",-0.069,{"positive":32,"neutral":33,"mixed":34,"critical":35},3,10,0,7,20,{"idea":38,"execution":40,"design":42,"privacy":44},{"positive":39,"critical":34},2,{"positive":34,"critical":41},1,{"positive":34,"critical":43},5,{"positive":34,"critical":41},[32,32,32,34,34,34,34,32,34,41,34,32,34,34,43,34,43,34,32,34,43,34,32,34,41,34,32,32,32,34,41,34,41,34,34,41,34,41,34,41],"Hi HN, We’re Harshith, Manoj, and Manik\n\nPoozle (https:\u002F\u002Fgithub.com\u002Fpoozlehq\u002Fpoozle) provides a single API that helps businesses achieve accurate LLM responses by providing real-time customer data from different SAAS tools (e.g Notion, Salesforce, Jira, Shopify, Google Ads etc).\n\nWhy we built Poozle: As we were talking to more AI companies who need to integrate with their customers’ data we realised managing all SAAS tools data and keeping them up-to-date is a huge infra of ETL, Auth management, Webhooks and many more things before you take it to production.  It struck us – why not streamline ",{"problem":48,"audience":49,"pricing":48,"motivation":58,"time_to_build":48,"stack":62,"openness":63,"stage":64,"team_size":65},null,{"value":50,"source":51,"evidence":52},"AI companies and businesses integrating LLMs with customer SaaS data","maker",[53,55],{"id":54},"post",{"id":56,"by":11,"text":57},"37191083","We haven't gotten into finance integrations yet but would love to understand use case more and see what we can do. Happy to discuss more in our community Slack. Also what kind of…",{"value":59,"source":51,"evidence":60},"AI companies needed customer SaaS data and building the ETL, auth and webhooks was a huge effort",[61],{"id":54},[],"open_source","beta","team",{"praise":67,"objections":80,"requests":116,"questions":128,"alternatives":149},[68],{"value":69,"source":70,"evidence":71},"Timely and useful idea for LLM context","commenter",[72,76],{"id":73,"by":74,"text":75},"37190113","oldsj","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…",{"id":77,"by":78,"text":79},"37181122","retakeming","This looks neat. https:\u002F\u002Fgithub.com\u002FShishirPatil\u002Fgorilla feels like a project with certain similarities here. How would you compare yourselves to them?",[81,88,98,109],{"value":82,"source":70,"evidence":83},"Unclear what makes it specific to LLMs",[84],{"id":85,"by":86,"text":87},"37181968","haxton","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…",{"value":89,"source":70,"evidence":90},"Normalising entities across services loses fidelity and terminology differs",[91,95],{"id":92,"by":93,"text":94},"37181448","tuckerconnelly","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…",{"id":96,"by":93,"text":97},"37181636","Maybe 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…",{"value":99,"source":70,"evidence":100},"Name has an unfortunate slang meaning",[101,105],{"id":102,"by":103,"text":104},"37182118","eurleif","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…",{"id":106,"by":107,"text":108},"37182677","acqbu","Slangonym for vagina. According to The Big Book of Filth (1999) coinage and usage dates back to the late 19 th century.",{"value":110,"source":70,"evidence":111},"Cross-department data access may be a security risk",[112],{"id":113,"by":114,"text":115},"37190767","TZubiri","Pozzle just sounds like a violation of encapsulation\u002Fdepartmental permiters at best, and a security nightmare at worst.",[117,121],{"value":118,"source":70,"evidence":119},"Add personal finance integration like Plaid",[120],{"id":73,"by":74,"text":75},{"value":122,"source":70,"evidence":123},"Allow users to define their own schema",[124],{"id":125,"by":126,"text":127},"37182430","theskcd","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…",[129,138,142],{"value":130,"source":70,"evidence":131},"How does it compare to Nango, Merge and Gorilla",[132,133,134],{"id":85,"by":86,"text":87},{"id":77,"by":78,"text":79},{"id":135,"by":136,"text":137},"37180853","toomuchtodo","Very cool product! Have you consider relying on Gorilla for integrations? https:\u002F\u002Fgorilla.cs.berkeley.edu\u002F https:\u002F\u002Fgithub.com\u002FShishirPatil\u002Fgorilla https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.15334",{"value":139,"source":70,"evidence":140},"How is data staleness handled and does each user need to authorise",[141],{"id":85,"by":86,"text":87},{"value":143,"source":70,"evidence":144},"How does it compare to building context in LangChain",[145],{"id":146,"by":147,"text":148},"37190488","hsikka","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,…",[150,154,158,163],{"value":151,"source":70,"evidence":152},"Nango",[153],{"id":85,"by":86,"text":87},{"value":155,"source":70,"evidence":156},"Merge",[157],{"id":85,"by":86,"text":87},{"value":159,"source":70,"evidence":160},"Gorilla",[161,162],{"id":77,"by":78,"text":79},{"id":135,"by":136,"text":137},{"value":164,"source":70,"evidence":165},"LangChain",[166],{"id":146,"by":147,"text":148},{"comments":168,"answered":35,"key":169},17,[170,173,176],{"id":171,"text":172},"37184959","Would love to understand if there is something missing.",{"id":174,"text":175},"37192607","How Plaid has provided all needs for Finance products by providing unified API we are bringing that to multiple verticals. And choosing LLMs as our primary ICP, the solution will…",{"id":177,"text":178},"37181504","Yeah, I think we have 2 things here. Take an example model a \"Ticket\". 1. Dealing with custom fields. We provide a way you can map the custom fields specific to the company into…",{"commenters":36,"max_depth":43,"maker_replies":168,"first_comment_mins":180,"lifespan_hours":181},61,26,[183,185,188,191,195,197,201,202,204,206,208,210,213,215,217,219,222,226,228,229,231,233,234,235,237,240,243,244,249,253,255,257,259,260,262,265,268,270,272,274],[85,34,32,184,86,34],"maker\u002Fneutral\u002Fidea",[186,34,32,184,187,34],"37182393","Manik_agg",[189,34,32,190,187,34],"37182598","maker\u002Fneutral\u002Fexecution",[192,34,34,193,194,34],"37184925","commenter\u002Fneutral\u002Fnone","willio58",[171,34,34,196,11,41],"maker\u002Fneutral\u002Fnone",[198,34,34,199,200,34],"37192546","commenter\u002Fneutral\u002Fidea","dudus",[174,34,34,199,11,41],[92,41,32,203,93,34],"project\u002Fneutral\u002Fexecution",[177,41,34,205,11,41],"project\u002Fneutral\u002Fdesign",[96,41,41,207,93,34],"project\u002Fcritical\u002Fexecution",[209,41,34,203,11,41],"37181820",[211,41,32,203,212,34],"37181859","SparkyMcUnicorn",[214,41,34,203,11,41],"37182065",[216,41,34,205,11,41],"37181583",[77,39,43,218,78,34],"project\u002Fpositive\u002Fidea",[220,39,34,221,11,41],"37181228","project\u002Fneutral\u002Fidea",[223,39,43,224,225,34],"37182790","maker\u002Fpositive\u002Fnone","jamesmcintyre",[227,39,34,196,11,41],"37182942",[125,32,32,205,126,34],[230,32,34,205,11,41],"37182612",[73,232,43,218,74,34],4,[56,232,34,196,11,41],[146,43,32,221,147,34],[236,43,34,221,11,41],"37191017",[113,238,41,239,114,34],6,"project\u002Fcritical\u002Fprivacy",[241,238,34,242,11,41],"37191048","maker\u002Fneutral\u002Fprivacy",[135,35,32,221,136,34],[245,246,32,247,248,34],"37180909",8,"project\u002Fneutral\u002Fnone","hdlothia",[250,251,32,205,252,34],"37181363",9,"smcleod",[254,251,34,205,11,41],"37181442",[102,251,41,256,103,34],"project\u002Fcritical\u002Fdesign",[258,251,34,205,11,41],"37182532",[106,251,41,256,107,34],[261,251,34,205,11,41],"37182802",[263,251,34,264,252,34],"37186007","commenter\u002Fneutral\u002Fdesign",[266,251,41,256,267,34],"37183403","mkl",[269,251,34,205,11,41],"37183609",[271,251,41,256,252,34],"37185977",[273,251,34,205,11,41],"37186029",[275,251,41,256,276,34],"37188623","fritzo",[],[279,284,288,293,297,301],{"id":280,"name":281,"points":282,"category":283},"37190743","flipreps",373,"creative",{"id":285,"name":286,"points":287,"category":283},"37194128","Just intonation keyboard",331,{"id":289,"name":290,"points":291,"category":292},"37188659","Rivet",327,"infrastructure",{"id":294,"name":295,"points":296,"category":283},"37188102","Avatartion",162,{"id":298,"name":299,"points":300,"category":292},"37224148","FlakeHub",154,{"id":302,"name":303,"points":304,"category":305},"37234887","Fast vector similarity",141,"data",false,"v2",{"id":309,"name":5,"line":6,"ai":306,"cat":20,"year":13,"points":14,"comments":15,"rec":29,"s":310,"top":18,"kw":311,"maker":11,"domain":10,"tier":19,"attempts":34,"strip":312,"url":9,"mix":313,"praise":69,"objection":82,"sub":21},37180017,-0.07,[24,25,26,27,28],"3330000301030050503050301033301010010101",[32,33,34,35],1793991072066]