Saving links doesn't make you smarter. Learning from them does.
Problem
IwasthatpersonwithhundredsofsavedlinksI'dneveropenagain.Isavedarticles,videos,references.ButwhenIneededsomething,I'dendupsearchingforatitleIbarelyremembered,infoldersIbarelyorganized.ThetoolIusedorganizedwhatIsaved.Theproblemwasitdidn'thelpmelearnfromitorfinditwhenIactuallyneededit.
SoIbuiltCoisas.spacearoundonequestion:whatifthecontentyousavedcouldsurfaceitselfwhenyouneedit,withoutyouhavingtorememberitexisted?
The AI stack
Categorizationrunsongpt-4o-miniviaOpenRouterattemperature0.2.Ifoundthattemperaturethroughtesting:highertemperaturesintroducedcategorydrift,thesamelinkcategorizeddifferentlyonrepeatsaves.0.2givestheconsistencythatacategorizationfeatureneedstobetrusted.
Theconversationalretrievallayerusesthecategoryasascopedcontextsignal,aRAG-likeapproachfastenoughforconsumerUXandaccurateenoughtobeuseful.Itestedwithfulldocumentembeddinganditwasslowerthantheactualquerypatternsjustified.
Whencontextisthin,retrievalfallsbackthroughthreelevels:visiblecontentfromtheactivecategory(last3days),thenallcontentfromthatcategory,thenallcontentregardlessofcategory.Thefallbackstrategykeepsresponsesgroundedevenforuserswhojuststarted.
TheFocoTimematchingalgorithmusessemanticAI,so"LearnReact"surfaceslinksabouthooks,components,andJSX,includinglinksthatnevermentionReactinthetitle.ResultsarecachedinKVwithhash-basedinvalidation:whenanewlinkissaved,thehashchanges,cacheinvalidates,andthenextmatchrequestregenerates.
The design decisions
Streamingwasnon-negotiableforme.Anycategorizationthatrequiredwaitingwouldbreakthesavehabit.Theproductonlyworksifsavingfeelsinstant.Thelinkappearsimmediatelyinthegridwithapendingstate,categorizationcompletesinthebackground,statusprogressesfrompendingtoprocessedtoread.
Iscopedtheconversationalinterfacebycategoryonpurpose.Open-endedchatoverallsavedcontentproducedirrelevantanswersintesting,sonarrowingthecontextwasthedecisionthatmadethefeaturework.Whenusersswitchcategorieswhileachatisopen,aninlinewarningappearswithtwooptions:keepthecurrentcontextorre-groundtheconversationinthenewcategory.
The/resumircommandusesFibonacci-basedprogressivedisclosure:thefirstcallreturns5links.Userscanaskformore,andthesequenceexpandsto8,13,21,34.Usersdiscoverwhattheyhaveatthepacetheyneed.
The failure mode
Whenthemodelcan'tcategorizealinkconfidently(paywalledpages,ambiguouscontent,brokenURLs),thelinklandsinanUncategorizedstatewithamanualoverrideoption.Thelinkisalwaysthere,alwaysaccessible.TheAIisanadditivelayerontopofthedata,sowhenitfails,thelinkstaysavailable.
TheAIproviderlayerhasafallback:ifOpenRouterreturnsa402(creditsexhausted),thesystemautomaticallyroutestoOpenAIwitha1-hourretrywindow.ServicestatusistrackedinKV:provider,lasterror,failedattempts,lastsuccesstime.Usersneverseeaproviderswitch.
Contentextractionusessilentfailure:ifittimesoutat10seconds,thelinkstillworkswithitsmetadata.Iprioritizedresponsespeedhere,becausealinkinthegridalreadyservestheuser,evenwithoutthefullcontentextracted.
Row-levelsecurityisenforcedatthedatabaselevelandintheapplicationlayer.EveryuserdatatablehasRLSpoliciesboundtoauth.uid().Noapplicationbugcanleakoneuser'sdatatoanother.
What's next
IwanttoadddeepreadingviaFirecrawl,extractingactualcontentfromsavedlinksbeyondthemetadata.AndGmailOAuthtopullnewslettersandthreadsdirectlyintothelibrary,turningtheinboxintoalearningfeed.WhatI'mmostexcitedaboutisthereadinglayer,becausethat'swhatwillmaketheAIresponsesgenuinelyuseful,groundedinwhatyouactuallyread.
previous read
Resense →Resense is a product that uses AI to turn any data a team already has (CSVs, PDFs, text, images) into Synthetic Users, with RAG and embeddings. It also generates insights with weighted cause-and-effect connections. I used AI across the whole process, from research to testing.