{"id":3040,"date":"2026-07-01T15:52:39","date_gmt":"2026-07-01T12:52:39","guid":{"rendered":"https:\/\/shareai.now\/?p=3040"},"modified":"2026-07-01T15:52:40","modified_gmt":"2026-07-01T12:52:40","slug":"tam-zamaninda-baglam-yapay-zeka-ajanlari","status":"publish","type":"post","link":"https:\/\/shareai.now\/tr\/blog\/gelistiriciler\/tam-zamaninda-baglam-yapay-zeka-ajanlari\/","title":{"rendered":"Yapay Zeka Temsilcileri i\u00e7in Tam Zaman\u0131nda Ba\u011flam: \u0130stekleri Sade Tutun"},"content":{"rendered":"<p><strong>Yapay zeka ajanlar\u0131 i\u00e7in tam zaman\u0131nda ba\u011flam<\/strong> b\u00fcy\u00fck bir \u00fcretim etkisi olan basit bir fikirdir: aktif istemi sade tutun, ajan\u0131n ihtiya\u00e7 duyabilece\u011fi hafif referanslar\u0131 ta\u015f\u0131y\u0131n ve a\u011f\u0131r ba\u011flam\u0131 yaln\u0131zca bir ad\u0131m ger\u00e7ekten gerekti\u011finde y\u00fckleyin.<\/p>\n\n\n\n<p>Bu de\u011fi\u015fim \u00f6nemlidir \u00e7\u00fcnk\u00fc ajan \u00e7al\u0131\u015fmalar\u0131 d\u00f6ng\u00fclerdir. Bir el kitab\u0131, ara\u00e7 katalo\u011fu, veritaban\u0131 anl\u0131k g\u00f6r\u00fcnt\u00fcs\u00fc veya istemde bulunan uzun bir sonu\u00e7 bir kez \u00f6denmez. Planlama, ara\u00e7 \u00e7a\u011fr\u0131lar\u0131, yeniden denemeler ve nihai cevaplar boyunca tekrar tekrar g\u00f6nderilebilir. Sade ba\u011flam modeli odakl\u0131 tutar, maliyetleri anlamay\u0131 kolayla\u015ft\u0131r\u0131r ve ekiplerin her ad\u0131m\u0131 do\u011fru modele y\u00f6nlendirmesi i\u00e7in daha temiz bir yol sunar.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Tam Zaman\u0131nda Ba\u011flam Ne Anlama Geliyor<\/h2>\n\n\n\n<p>Tam zaman\u0131nda ba\u011flam, toplu \u00f6n y\u00fcklemeyi bir katalogla de\u011fi\u015ftirir. Model, g\u00f6r\u00fcn\u00fcmde kompakt i\u015faret\u00e7iler tutar: bir dosya yolu, bir ara\u00e7 ad\u0131, bir beceri a\u00e7\u0131klamas\u0131, saklanm\u0131\u015f bir sorgu, bir arama sonucu tan\u0131t\u0131c\u0131s\u0131 veya \u00f6nceki bir ad\u0131m\u0131n k\u0131sa bir \u00f6zeti. Ajan, y\u00fck\u00fc gerektiren bir g\u00f6reve ula\u015ft\u0131\u011f\u0131nda, \u00e7al\u0131\u015fma zaman\u0131 belirli i\u00e7eri\u011fi al\u0131r, kullan\u0131r ve ard\u0131ndan aktif pencereden \u00e7\u0131kmas\u0131na izin verir.<\/p>\n\n\n\n<p>En iyi zihinsel model bir i\u015f tezgah\u0131d\u0131r, bir depo de\u011fil. Ajan, bir sonraki ad\u0131m\u0131 se\u00e7mesine yard\u0131mc\u0131 olan ara\u00e7lar\u0131 ve referanslar\u0131 g\u00f6rmelidir. Ba\u015flang\u0131\u00e7tan itibaren istemde her k\u0131lavuz, her g\u00fcnl\u00fck sat\u0131r\u0131 ve her olas\u0131 \u015fema bulunmas\u0131na gerek yoktur.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Y\u00fckl\u00fc Kalmas\u0131 Gerekenler<\/h2>\n\n\n\n<p>Sade ba\u011flam, bo\u015f bir istem anlam\u0131na gelmez. Baz\u0131 bilgiler her zaman alakal\u0131 oldu\u011fu ve yeniden ke\u015ffedilmesi pahal\u0131 oldu\u011fu i\u00e7in sabit \u00f6n ekte yer almal\u0131d\u0131r.<\/p>\n\n\n\n<ul class=\"wp-block-list\"><li><strong>Temel talimatlar:<\/strong> rol, g\u00fcvenlik k\u0131s\u0131tlamalar\u0131, \u00e7\u0131kt\u0131 format\u0131 ve kullan\u0131c\u0131n\u0131n g\u00f6revi.<\/li><li><strong>Temel ara\u00e7 y\u00fczeyi:<\/strong> ajanlar\u0131n \u00e7o\u011fu \u00e7al\u0131\u015fmada var oldu\u011funu bilmesi gereken k\u00fc\u00e7\u00fck ara\u00e7 seti.<\/li><li><strong>Son durum:<\/strong> zaten al\u0131nm\u0131\u015f kararlar, a\u00e7\u0131k sorular ve mevcut g\u00f6rev s\u0131n\u0131r\u0131.<\/li><li><strong>Eri\u015fim kurallar\u0131:<\/strong> hangi verilerin, sistemlerin ve eylemlerin izinli oldu\u011funu.<\/li><li><strong>Y\u00f6nlendirme kurallar\u0131:<\/strong> uygulaman\u0131n ne zaman h\u0131zl\u0131 bir model, daha ucuz bir model veya daha g\u00fc\u00e7l\u00fc bir ak\u0131l y\u00fcr\u00fctme modeli kullanmas\u0131 gerekti\u011fini.<\/li><\/ul>\n\n\n\n<p>Geri kalanlar yerini hak etmelidir. Tam politika belgeleri, hacimli API sonu\u00e7lar\u0131, uzun transkriptler, b\u00fcy\u00fck tablolar ve nadiren kullan\u0131lan ara\u00e7 talimatlar\u0131, al\u0131nabilir y\u00fckler olarak daha iyi i\u015flenir.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Jeton \u0130sraf\u0131n\u0131n Genellikle Ba\u015flad\u0131\u011f\u0131 Yer<\/h2>\n\n\n\n<p>Jeton israf\u0131 genellikle makul bir kestirme yol ile ba\u015flar: \u201cModelin her \u015feye sahip olmas\u0131 i\u00e7in \u015fimdi y\u00fckle.\u201d Bu, k\u0131sa, tek d\u00f6n\u00fc\u015fl\u00fc g\u00f6revler i\u00e7in i\u015fe yarar. Ancak, her d\u00f6ng\u00fc ad\u0131m\u0131 ayn\u0131 sabit ba\u011flam\u0131 s\u00fcr\u00fckledi\u011fi i\u00e7in ajan i\u015f ak\u0131\u015flar\u0131nda pahal\u0131 hale gelir.<\/p>\n\n\n\n<p>Yayg\u0131n \u00f6rnekler aras\u0131nda, ajan yaln\u0131zca mevcut bileti ihtiya\u00e7 duydu\u011funda tam m\u00fc\u015fteri ge\u00e7mi\u015flerini \u00f6nceden y\u00fcklemek, her ara\u00e7 sonucunu bir sonraki isteme yap\u0131\u015ft\u0131rmak, kullan\u0131lmayan ara\u00e7 a\u00e7\u0131klamalar\u0131n\u0131 g\u00f6r\u00fcn\u00fcr tutmak veya bir g\u00f6rev yaln\u0131zca bir u\u00e7 noktaya ihtiya\u00e7 duydu\u011funda t\u00fcm belgeleri g\u00f6ndermek yer al\u0131r. Maliyet yaln\u0131zca jetonlarla s\u0131n\u0131rl\u0131 de\u011fildir. \u0130lgisiz ba\u011flam, ger\u00e7ekten \u00f6nemli olan istemin b\u00f6l\u00fcmleriyle rekabet eder.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">JIT Ba\u011flam\u0131 Model Y\u00f6nlendirme ile E\u015fle\u015ftirin<\/h2>\n\n\n\n<p>Tam zaman\u0131nda ba\u011flam ve model y\u00f6nlendirme, ayn\u0131 \u00fcretim probleminin farkl\u0131 y\u00f6nlerini \u00e7\u00f6zer. JIT ba\u011flam\u0131, isteme neyin girece\u011fine karar verir. Y\u00f6nlendirme, hangi modelin ad\u0131m\u0131 ele almas\u0131 gerekti\u011fine karar verir.<\/p>\n\n\n\n<p>\u0130nce bir istem, y\u00f6nlendirmeyi kolayla\u015ft\u0131r\u0131r. Bir ad\u0131m yaln\u0131zca k\u00fc\u00e7\u00fck bir arama ve yap\u0131land\u0131r\u0131lm\u0131\u015f bir cevap gerektiriyorsa, premium bir ak\u0131l y\u00fcr\u00fctme modeline ihtiya\u00e7 duymayabilir. Daha sonraki bir ad\u0131m karma\u015f\u0131k bir s\u00f6zle\u015fme, kod taban\u0131 dilimi veya \u00e7oklu belge kar\u015f\u0131la\u015ft\u0131rmas\u0131 y\u00fckl\u00fcyorsa, y\u00f6nlendirici yaln\u0131zca o ad\u0131m i\u00e7in daha g\u00fc\u00e7l\u00fc bir modele ge\u00e7ebilir. Uygulama, her iste\u011fi en zor istek gibi ele almaktan ka\u00e7\u0131n\u0131r.<\/p>\n\n\n\n<p>Yap\u0131c\u0131lar i\u00e7in, bu, istem tasar\u0131m\u0131n\u0131n \u00fcr\u00fcn ekonomisine d\u00f6n\u00fc\u015ft\u00fc\u011f\u00fc yerdir. Bir yapay zeka \u00f6zelli\u011finin maliyeti, \u00f6zelli\u011fin ne kadar ba\u011flam g\u00f6nderdi\u011fi, ajan d\u00f6ng\u00fclerinin bunu ne s\u0131kl\u0131kla tekrarlad\u0131\u011f\u0131, her ad\u0131m\u0131 hangi modelin ele ald\u0131\u011f\u0131 ve tercih edilen yolun kullan\u0131lamad\u0131\u011f\u0131nda yedekleme davran\u0131\u015f\u0131n\u0131n nas\u0131l oldu\u011fu ile \u015fekillenir.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Pratik Bir JIT Ba\u011flam Kontrol Listesi<\/h2>\n\n\n\n<ul class=\"wp-block-list\"><li>Her ajan \u00e7al\u0131\u015fmas\u0131n\u0131 kompakt, sabit bir talimat \u00f6n ekiyle ba\u015flat\u0131n.<\/li><li>B\u00fcy\u00fck kaynaklar\u0131, a\u00e7\u0131k isimler, sahipler, boyutlar ve \u00f6zetlerle tan\u0131mlanan tutama\u00e7lar olarak temsil edin.<\/li><li>Ara\u00e7 a\u00e7\u0131klamalar\u0131n\u0131 k\u0131sa ve g\u00f6reve \u00f6zel tutun.<\/li><li>Hacimli ara\u00e7 sonu\u00e7lar\u0131n\u0131 d\u0131\u015far\u0131 aktar\u0131n ve \u00f6nce \u00f6zl\u00fc \u00f6nizlemeler d\u00f6nd\u00fcr\u00fcn.<\/li><li>Bir ad\u0131m\u0131n buna ihtiyac\u0131 oldu\u011funda yaln\u0131zca kaynak verileri al\u0131n.<\/li><li>Tamamlanan \u00e7al\u0131\u015fmay\u0131 bayat istem ge\u00e7mi\u015fine d\u00f6n\u00fc\u015fmeden \u00f6nce \u00f6zetleyin.<\/li><li>Her i\u015f ak\u0131\u015f\u0131 i\u00e7in giri\u015f belirte\u00e7lerini, \u00e7\u0131k\u0131\u015f belirte\u00e7lerini, yeniden denemeleri ve rota de\u011fi\u015fikliklerini takip edin.<\/li><li>Bir ad\u0131m\u0131n daha g\u00fc\u00e7l\u00fc bir modele y\u00fckseltilmesi gerekti\u011fi zaman\u0131 tan\u0131mlay\u0131n.<\/li><li>Kullan\u0131c\u0131lara her ekibin ba\u011flam kurallar\u0131n\u0131 elle olu\u015fturmas\u0131n\u0131 zorlamak yerine onaylanm\u0131\u015f yollar sa\u011flay\u0131n.<\/li><li>Ba\u011flam y\u00fcklerini yaln\u0131zca maliyetler artt\u0131ktan sonra de\u011fil, s\u00fcr\u00fcm QA'n\u0131n bir par\u00e7as\u0131 olarak g\u00f6zden ge\u00e7irin.<\/li><\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">ShareAI'nin Uygun Oldu\u011fu Yer<\/h2>\n\n\n\n<p>ShareAI, insan g\u00fcc\u00fcyle \u00e7al\u0131\u015fan bir AI pazar\u0131 ve API'dir. Geli\u015ftiriciler, 150+ modele eri\u015fmek, model se\u00e7eneklerini kar\u015f\u0131la\u015ft\u0131rmak, istekleri y\u00f6nlendirmek, yedekleme kullanmak ve belirte\u00e7 ba\u015f\u0131na \u00f6deme yapmak i\u00e7in tek bir API kullan\u0131r. Bu, uygulaman\u0131n modelleri kas\u0131tl\u0131 olarak se\u00e7mesini isteyen ekipler i\u00e7in her i\u015f ak\u0131\u015f\u0131n\u0131 tek bir model yoluna sabitlemek yerine kullan\u0131\u015fl\u0131 bir katman haline getirir.<\/p>\n\n\n\n<p>ShareAI bir uygulama olu\u015fturucu veya ajan \u00e7er\u00e7evesi de\u011fildir. Geli\u015ftirici, \u00fcr\u00fcn deneyimini, ba\u011flam stratejisini, veri politikas\u0131n\u0131 ve ajan tasar\u0131m\u0131n\u0131 y\u00f6netir. ShareAI, bu deneyimin arkas\u0131ndaki model eri\u015fim katman\u0131na yard\u0131mc\u0131 olur: model se\u00e7imi, pazar g\u00f6r\u00fcn\u00fcrl\u00fc\u011f\u00fc, y\u00f6nlendirme, yedekleme ve kullan\u0131m tabanl\u0131 ekonomi.<\/p>\n\n\n\n<p>Ajan \u00fcr\u00fcnleri i\u00e7in pratik hareket, \u00f6l\u00e7\u00fcl\u00fc yollarla ince ba\u011flam\u0131 e\u015fle\u015ftirmektir. \u0130stemleri daha k\u00fc\u00e7\u00fck tutun, her ad\u0131m\u0131 uygun modele g\u00f6nderin ve AI kullan\u0131m\u0131n\u0131 fiyatland\u0131rma, g\u00fcvenilirlik ve m\u00fc\u015fteri deneyiminin birlikte iyile\u015febilece\u011fi kadar g\u00f6r\u00fcn\u00fcr hale getirin. <a href=\"https:\/\/shareai.now\/docs\/api\/using-the-api\/getting-started-with-shareai-api\/?utm_source=blog&amp;utm_medium=content&amp;utm_campaign=just-in-time-context-ai-agents\">ShareAI API<\/a> ile ba\u015flay\u0131n ve mevcut modelleri kar\u015f\u0131la\u015ft\u0131r\u0131n. <a href=\"https:\/\/shareai.now\/models\/?utm_source=blog&amp;utm_medium=content&amp;utm_campaign=just-in-time-context-ai-agents\">ShareAI Modelleri<\/a>.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">SSS<\/h2>\n\n\n\n<h3 class=\"wp-block-heading\">AI ajanlar\u0131 i\u00e7in tam zaman\u0131nda ba\u011flam nedir?<\/h3>\n\n\n<p>Bu, bir ajan\u0131n istemde kompakt referanslar tuttu\u011fu ve yaln\u0131zca bir g\u00f6rev ad\u0131m\u0131n\u0131n bunlara ihtiyac\u0131 oldu\u011funda daha b\u00fcy\u00fck dosyalar\u0131, ara\u00e7 \u00e7\u0131kt\u0131lar\u0131, talimatlar\u0131 veya kay\u0131tlar\u0131 y\u00fckledi\u011fi bir ba\u011flam stratejisidir.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">JIT ba\u011flam\u0131 geleneksel RAG'den nas\u0131l farkl\u0131d\u0131r?<\/h3>\n\n\n<p>Geleneksel alma genellikle model yan\u0131t vermeden \u00f6nce muhtemelen ilgili par\u00e7alar\u0131 y\u00fckler. JIT ba\u011flam\u0131, ajan\u0131n g\u00f6rev birden fazla ad\u0131mda geli\u015fti\u011finde yararl\u0131 olan belirli y\u00fckleri \u00e7al\u0131\u015ft\u0131rma s\u0131ras\u0131nda ke\u015ffetmesine ve almas\u0131na olanak tan\u0131r.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">JIT ba\u011flam\u0131 AI maliyetlerini azalt\u0131r m\u0131?<\/h3>\n\n\n<p>Yapabilir. Arac\u0131 d\u00f6ng\u00fcleri aktif ba\u011flam\u0131 bir\u00e7ok kez yeniden g\u00f6nderir, bu nedenle kullan\u0131lmayan y\u00fckleri kald\u0131rmak, tekrarlanan giri\u015f jetonlar\u0131n\u0131 azaltabilir. Ger\u00e7ek tasarruflar i\u015f ak\u0131\u015f\u0131 uzunlu\u011funa, model se\u00e7imine, tekrar denemelere ve \u00e7\u0131kt\u0131 boyutuna ba\u011fl\u0131d\u0131r.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">JIT ba\u011flam\u0131 model kalitesini art\u0131rabilir mi?<\/h3>\n\n\n<p>Genellikle evet. Daha temiz bir istem, \u00f6nemli talimatlara ve yeni g\u00f6rev verilerine daha fazla yer a\u00e7ar. Ayr\u0131ca, alakas\u0131z ba\u011flam\u0131n modeli dikkati da\u011f\u0131tma olas\u0131l\u0131\u011f\u0131n\u0131 azalt\u0131r.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Tam zaman\u0131nda y\u00fcklenmemesi gerekenler nelerdir?<\/h3>\n\n\n<p>Temel talimatlar, g\u00fcvenlik kurallar\u0131, temel ara\u00e7 a\u00e7\u0131klamalar\u0131, eri\u015fim s\u0131n\u0131rlar\u0131 ve mevcut g\u00f6rev durumu genellikle sabit istemde yer al\u0131r \u00e7\u00fcnk\u00fc arac\u0131 bunlara t\u00fcm \u00e7al\u0131\u015fma boyunca ihtiya\u00e7 duyar.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">JIT ba\u011flam\u0131 model y\u00f6nlendirmesini nas\u0131l etkiler?<\/h3>\n\n\n<p>Y\u00f6nlendirmeyi daha hassas hale getirir. Basit ad\u0131mlar daha ucuz veya daha h\u0131zl\u0131 modeller kullanabilirken, karma\u015f\u0131k ba\u011flam y\u00fckleyen ad\u0131mlar yaln\u0131zca gerekti\u011finde daha g\u00fc\u00e7l\u00fc modellere y\u00f6nlendirilebilir.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">JIT ba\u011flam\u0131 m\u00fc\u015fteri destek ajanlar\u0131 i\u00e7in faydal\u0131 m\u0131?<\/h3>\n\n\n<p>Evet. Bir destek ajan\u0131, bileti, politika ipu\u00e7lar\u0131n\u0131 ve son konu\u015fma durumunu ba\u015flatabilir, ard\u0131ndan i\u015f ak\u0131\u015f\u0131 gerektirdi\u011finde tam m\u00fc\u015fteri kayd\u0131n\u0131 veya politika b\u00f6l\u00fcm\u00fcn\u00fc alabilir.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">JIT ba\u011flam\u0131 kodlama ajanlar\u0131 i\u00e7in faydal\u0131 m\u0131?<\/h3>\n\n\n<p>Evet. Kodlama ajanlar\u0131 proje talimatlar\u0131n\u0131 ve dosya referanslar\u0131n\u0131 g\u00f6r\u00fcn\u00fcr tutabilir, ard\u0131ndan bir ad\u0131m gerektirdi\u011finde belirli dosyalar\u0131, testleri veya g\u00fcnl\u00fckleri okuyabilir, t\u00fcm depoyu \u00f6nceden y\u00fcklemek yerine.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">ShareAI ajan ba\u011flam\u0131m\u0131 y\u00f6netiyor mu?<\/h3>\n\n\n<p>Hay\u0131r. Builder uygulama mant\u0131\u011f\u0131n\u0131, istemleri, alma i\u015flemini ve ba\u011flam stratejisini kontrol eder. ShareAI, model eri\u015fimi, y\u00f6nlendirme, yedekleme ve jeton ba\u015f\u0131na \u00f6deme kullan\u0131m\u0131 i\u00e7in model pazar\u0131n\u0131 ve API katman\u0131n\u0131 sa\u011flar.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">ShareAI, JIT ba\u011flam kullanan ajan \u00fcr\u00fcnleri i\u00e7in ne zaman iyi bir se\u00e7enektir?<\/h3>\n\n\n<p>ShareAI, bir Builder'\u0131n bir\u00e7ok model i\u00e7in tek bir API istemesi, farkl\u0131 ajan ad\u0131mlar\u0131n\u0131 farkl\u0131 model se\u00e7eneklerine y\u00f6nlendirme yetene\u011fi ve ger\u00e7ek jeton t\u00fcketimine temiz bir \u015fekilde uyum sa\u011flayan kullan\u0131m ekonomisi istedi\u011finde iyi bir se\u00e7enektir.<\/p>","protected":false},"excerpt":{"rendered":"<p>AI ajanlar\u0131 i\u00e7in tam zaman\u0131nda ba\u011flam, ara\u00e7lar\u0131, dosyalar\u0131 ve talimatlar\u0131 yaln\u0131zca g\u00f6rev ihtiya\u00e7 duydu\u011funda y\u00fckleyerek istemleri daha k\u00fc\u00e7\u00fck tutar. \u0130\u015fte bunu y\u00f6nlendirme ve kullan\u0131m g\u00f6r\u00fcn\u00fcrl\u00fc\u011f\u00fc ile e\u015fle\u015ftirmenin yolu.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"cta-title":"Integrate One API","cta-description":"Access 150+ models with smart routing and failover.","cta-button-text":"View Docs","cta-button-link":"https:\/\/shareai.now\/documentation\/?utm_source=blog&utm_medium=content&utm_campaign=just-in-time-context-ai-agents","rank_math_title":"Just-in-Time Context for AI Agents: Keep Prompts Lean","rank_math_description":"Just-in-time context for AI agents keeps prompts lean, reduces token waste, and helps production teams route model workloads more intentionally.","rank_math_focus_keyword":"just-in-time context for AI agents","footnotes":""},"categories":[4,6],"tags":[99,168,167,51,148],"class_list":["post-3040","post","type-post","status-publish","format-standard","hentry","category-developers","category-insights","tag-ai-agents","tag-context-engineering","tag-just-in-time-context","tag-model-routing","tag-shareai-builder"],"_links":{"self":[{"href":"https:\/\/shareai.now\/tr\/api\/wp\/v2\/posts\/3040","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/shareai.now\/tr\/api\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/shareai.now\/tr\/api\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/shareai.now\/tr\/api\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/shareai.now\/tr\/api\/wp\/v2\/comments?post=3040"}],"version-history":[{"count":1,"href":"https:\/\/shareai.now\/tr\/api\/wp\/v2\/posts\/3040\/revisions"}],"predecessor-version":[{"id":3092,"href":"https:\/\/shareai.now\/tr\/api\/wp\/v2\/posts\/3040\/revisions\/3092"}],"wp:attachment":[{"href":"https:\/\/shareai.now\/tr\/api\/wp\/v2\/media?parent=3040"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/shareai.now\/tr\/api\/wp\/v2\/categories?post=3040"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/shareai.now\/tr\/api\/wp\/v2\/tags?post=3040"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}