{"id":37280,"date":"2025-12-29T21:00:38","date_gmt":"2025-12-29T18:00:38","guid":{"rendered":"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/"},"modified":"2025-12-29T21:00:38","modified_gmt":"2025-12-29T18:00:38","slug":"azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek","status":"publish","type":"post","link":"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/","title":{"rendered":"Azure AI Foundry Projesi ile MAF Ajanlar\u0131: Gelece\u011fin Ak\u0131ll\u0131 Sistemlerini \u0130n\u015fa Etmek"},"content":{"rendered":"<h2>Azure AI Foundry Projesi ile MAF Ajanlar\u0131: Gelece\u011fin Ak\u0131ll\u0131 Sistemlerini \u0130n\u015fa Etmek<\/h2>\n<p>G\u00fcn\u00fcm\u00fcz\u00fcn h\u0131zla de\u011fi\u015fen dijital d\u00fcnyas\u0131nda, karma\u015f\u0131k problemleri \u00e7\u00f6zmek ve dinamik ortamlara adapte olabilen ak\u0131ll\u0131 sistemler geli\u015ftirmek b\u00fcy\u00fck \u00f6nem ta\u015f\u0131maktad\u0131r. Bu ba\u011flamda, \u00c7ok Ajanl\u0131 Sistemler (Multi-Agent Systems &#8211; MAF) ve Microsoft Azure&#8217;un yapay zeka geli\u015ftirme platformu Azure AI Foundry Projesi, yenilik\u00e7i \u00e7\u00f6z\u00fcmler sunan g\u00fc\u00e7l\u00fc bir ikili olu\u015fturmaktad\u0131r. Bu makalede, MAF ajanlar\u0131n\u0131n ne oldu\u011funu, Azure AI Foundry&#8217;nin yeteneklerini ve bu iki teknolojinin birle\u015ferek nas\u0131l \u00e7\u0131\u011f\u0131r a\u00e7\u0131c\u0131 uygulamalar geli\u015ftirebilece\u011fimizi detayl\u0131 bir \u015fekilde inceleyece\u011fiz.<\/p>\n<h3>MAF Ajanlar\u0131 Nedir?<\/h3>\n<p>\u00c7ok Ajanl\u0131 Sistemler (MAF), \u00f6zerk, etkile\u015fimli ve genellikle heterojen ajanlar\u0131n bir araya gelerek belirli bir amac\u0131 ger\u00e7ekle\u015ftirdi\u011fi da\u011f\u0131t\u0131k yapay zeka sistemleridir. Her ajan, kendi hedefleri, alg\u0131lar\u0131 ve eylemleri olan ba\u011f\u0131ms\u0131z bir varl\u0131kt\u0131r. Bu ajanlar, birbirleriyle i\u015fbirli\u011fi yaparak, rekabet ederek veya koordine olarak karma\u015f\u0131k g\u00f6revleri yerine getirirler.<\/p>\n<h4>\u00c7ok Ajanl\u0131 Sistemlere Giri\u015f<\/h4>\n<p>\u00c7ok ajanl\u0131 sistemler, bireysel ajanlar\u0131n s\u0131n\u0131rl\u0131 bilgi ve yeteneklere sahip olmas\u0131na ra\u011fmen, kolektif olarak daha b\u00fcy\u00fck ve karma\u015f\u0131k problemleri \u00e7\u00f6zebilme potansiyeli sunar. Bu sistemler, da\u011f\u0131t\u0131k problem \u00e7\u00f6zme, kaynak y\u00f6netimi, ak\u0131ll\u0131 otomasyon ve sim\u00fclasyon gibi bir\u00e7ok alanda uygulama alan\u0131 bulur.<\/p>\n<h4>MAF Ajanlar\u0131n\u0131n Temel \u00d6zellikleri<\/h4>\n<ul>\n<li><strong>\u00d6zerklik:<\/strong> Ajanlar, d\u0131\u015f m\u00fcdahaleye ihtiya\u00e7 duymadan kendi kararlar\u0131n\u0131 alabilir ve eylemlerini ger\u00e7ekle\u015ftirebilir.<\/li>\n<li><strong>Reaktiflik:<\/strong> \u00c7evrelerindeki de\u011fi\u015fikliklere tepki verebilir ve davran\u0131\u015flar\u0131n\u0131 buna g\u00f6re ayarlayabilirler.<\/li>\n<li><strong>Proaktiflik:<\/strong> Sadece tepki vermekle kalmaz, ayn\u0131 zamanda kendi hedeflerine ula\u015fmak i\u00e7in inisiyatif alabilirler.<\/li>\n<li><strong>Sosyal Yetenek:<\/strong> Di\u011fer ajanlarla ileti\u015fim kurabilir, i\u015fbirli\u011fi yapabilir ve m\u00fczakere edebilirler.<\/li>\n<li><strong>\u00d6\u011frenme:<\/strong> Deneyimlerinden ders \u00e7\u0131kararak zamanla performanslar\u0131n\u0131 iyile\u015ftirebilirler.<\/li>\n<\/ul>\n<h4>Geleneksel Yakla\u015f\u0131mlardan Farklar\u0131<\/h4>\n<p>Geleneksel tekil sistemler veya merkezi kontrol mekanizmalar\u0131, \u00f6zellikle dinamik ve belirsiz ortamlarda \u00f6l\u00e7eklenebilirlik, esneklik ve hata tolerans\u0131 konusunda zorluklar ya\u015fayabilir. MAF ajanlar\u0131 ise, bu zorluklar\u0131n \u00fcstesinden gelmek i\u00e7in da\u011f\u0131t\u0131k karar alma, paralel i\u015flem ve do\u011fal hata tolerans\u0131 gibi avantajlar sunar. Her ajan ba\u011f\u0131ms\u0131z \u00e7al\u0131\u015ft\u0131\u011f\u0131 i\u00e7in, bir ajan\u0131n ar\u0131zalanmas\u0131 t\u00fcm sistemin \u00e7\u00f6kmesine neden olmaz.<\/p>\n<h3>Azure AI Foundry Projesi Nedir?<\/h3>\n<p>Azure AI Foundry, Microsoft&#8217;un b\u00fcy\u00fck \u00f6l\u00e7ekli yapay zeka modelleri geli\u015ftirmek, e\u011fitmek, da\u011f\u0131tmak ve y\u00f6netmek i\u00e7in tasarlanm\u0131\u015f kapsaml\u0131 bir platformudur. Geni\u015f bir ara\u00e7 ve hizmet yelpazesi sunarak, geli\u015ftiricilerin ve veri bilimcilerinin en son yapay zeka teknolojilerini kullanarak yenilik\u00e7i \u00e7\u00f6z\u00fcmler \u00fcretmelerini sa\u011flar.<\/p>\n<h4>AI Geli\u015ftirme S\u00fcre\u00e7lerini H\u0131zland\u0131rma<\/h4>\n<p>Azure AI Foundry, model se\u00e7imi, veri haz\u0131rl\u0131\u011f\u0131, e\u011fitim, do\u011frulama, da\u011f\u0131t\u0131m ve izleme gibi yapay zeka ya\u015fam d\u00f6ng\u00fcs\u00fcn\u00fcn her a\u015famas\u0131n\u0131 basitle\u015ftirmeyi hedefler. \u00d6zellikle b\u00fcy\u00fck dil modelleri (LLM&#8217;ler) ve di\u011fer \u00fcretken yapay zeka modelleri i\u00e7in optimize edilmi\u015ftir, b\u00f6ylece ekipler karma\u015f\u0131k altyap\u0131 y\u00f6netimi yerine model geli\u015ftirmeye odaklanabilir.<\/p>\n<h4>Temel \u00d6zellikleri ve Yetenekleri<\/h4>\n<ul>\n<li><strong>Model Katalo\u011fu:<\/strong> \u00d6nceden e\u011fitilmi\u015f geni\u015f bir model yelpazesi (\u00f6rn. GPT, DALL-E) ve a\u00e7\u0131k kaynak modellerine eri\u015fim.<\/li>\n<li><strong>Veri Y\u00f6netimi:<\/strong> B\u00fcy\u00fck veri k\u00fcmelerinin g\u00fcvenli ve verimli bir \u015fekilde depolanmas\u0131, i\u015flenmesi ve etiketlenmesi i\u00e7in ara\u00e7lar.<\/li>\n<li><strong>E\u011fitim ve \u0130nce Ayar:<\/strong> Da\u011f\u0131t\u0131k e\u011fitim, GPU h\u0131zland\u0131rma ve model ince ayar (fine-tuning) yetenekleri.<\/li>\n<li><strong>Da\u011f\u0131t\u0131m ve \u00d6l\u00e7eklendirme:<\/strong> Modelleri kolayca da\u011f\u0131tma, API&#8217;ler arac\u0131l\u0131\u011f\u0131yla eri\u015filebilir k\u0131lma ve talep \u00fczerine \u00f6l\u00e7eklendirme.<\/li>\n<li><strong>G\u00fcvenlik ve Uyumluluk:<\/strong> Kurumsal d\u00fczeyde g\u00fcvenlik, eri\u015fim kontrol\u00fc ve end\u00fcstri standartlar\u0131na uyumluluk.<\/li>\n<li><strong>\u0130zleme ve Y\u00f6netim:<\/strong> Model performans\u0131n\u0131, maliyetleri ve kaynak kullan\u0131m\u0131n\u0131 izleme ara\u00e7lar\u0131.<\/li>\n<\/ul>\n<h4>Neden Azure AI Foundry?<\/h4>\n<p>Azure AI Foundry, geli\u015ftiricilere ve kurulu\u015flara, yapay zeka projelerini daha h\u0131zl\u0131, daha g\u00fcvenli ve daha \u00f6l\u00e7eklenebilir bir \u015fekilde hayata ge\u00e7irme imkan\u0131 sunar. Microsoft&#8217;un k\u00fcresel altyap\u0131s\u0131, g\u00fcvenlik standartlar\u0131 ve entegre hizmet ekosistemi sayesinde, karma\u015f\u0131k yapay zeka \u00e7\u00f6z\u00fcmlerini kolayca olu\u015fturabilir ve y\u00f6netebilirsiniz.<\/p>\n<h3>MAF Ajanlar\u0131n\u0131 Azure AI Foundry ile Entegre Etmenin Avantajlar\u0131<\/h3>\n<p>MAF ajanlar\u0131n\u0131n da\u011f\u0131t\u0131k problem \u00e7\u00f6zme yetenekleri ile Azure AI Foundry&#8217;nin g\u00fc\u00e7l\u00fc yapay zeka altyap\u0131s\u0131n\u0131n birle\u015fimi, ak\u0131ll\u0131 sistemler geli\u015ftirmede \u00f6nemli avantajlar sa\u011flar.<\/p>\n<h4>\u00d6l\u00e7eklenebilirlik ve Performans<\/h4>\n<p>Azure AI Foundry, MAF ajanlar\u0131n\u0131n ihtiya\u00e7 duydu\u011fu i\u015flem g\u00fcc\u00fcn\u00fc ve depolama alan\u0131n\u0131 dinamik olarak sa\u011flayabilir. Binlerce ajan\u0131n e\u015f zamanl\u0131 olarak \u00e7al\u0131\u015fmas\u0131, veri i\u015flemesi ve birbirleriyle etkile\u015fime girmesi gerekti\u011finde, Azure&#8217;un \u00f6l\u00e7eklenebilir kaynaklar\u0131 sorunsuz bir performans sunar. Bu, \u00f6zellikle y\u00fcksek talep g\u00f6ren veya b\u00fcy\u00fck veri k\u00fcmeleriyle \u00e7al\u0131\u015fan uygulamalar i\u00e7in kritik \u00f6neme sahiptir.<\/p>\n<h4>G\u00fcvenlik ve Y\u00f6netilebilirlik<\/h4>\n<p>Kurumsal d\u00fczeyde g\u00fcvenlik ve uyumluluk, Azure AI Foundry&#8217;nin temel ta\u015flar\u0131ndand\u0131r. MAF ajanlar\u0131, hassas verilerle veya kritik operasyonlarla etkile\u015fimde bulunabilir. Azure&#8217;un kimlik y\u00f6netimi, a\u011f g\u00fcvenli\u011fi ve veri \u015fifreleme \u00f6zellikleri, ajanlar\u0131n ve verilerin g\u00fcvende kalmas\u0131n\u0131 sa\u011flar. Ayr\u0131ca, merkezi y\u00f6netim ara\u00e7lar\u0131 sayesinde ajanlar\u0131n ya\u015fam d\u00f6ng\u00fcs\u00fc, performans\u0131 ve davran\u0131\u015flar\u0131 kolayca izlenebilir ve y\u00f6netilebilir.<\/p>\n<h4>H\u0131zl\u0131 Geli\u015ftirme ve Da\u011f\u0131t\u0131m<\/h4>\n<p>Azure AI Foundry, MAF ajanlar\u0131n\u0131 tasarlama, e\u011fitme ve da\u011f\u0131tma s\u00fcrecini h\u0131zland\u0131r\u0131r. \u00d6nceden olu\u015fturulmu\u015f modeller, SDK&#8217;lar ve entegrasyon ara\u00e7lar\u0131 sayesinde geli\u015ftiriciler, s\u0131f\u0131rdan ba\u015flamak yerine mevcut bile\u015fenleri kullanarak ajanlar\u0131n\u0131 daha h\u0131zl\u0131 olu\u015fturabilirler. Otomatik da\u011f\u0131t\u0131m (CI\/CD) boru hatlar\u0131 ile ajanlar\u0131n \u00fcretim ortam\u0131na ge\u00e7i\u015fi kolayla\u015f\u0131r ve g\u00fcncellemeler sorunsuz bir \u015fekilde yap\u0131labilir.<\/p>\n<h3>Entegrasyon Mimarisi ve Bile\u015fenleri<\/h3>\n<p>MAF ajanlar\u0131n\u0131 Azure AI Foundry ile entegre etmek, genellikle \u00e7e\u015fitli Azure servislerinin bir kombinasyonunu kullanmay\u0131 gerektirir. Bu entegrasyon, ajanlar\u0131n \u00f6zerk \u00e7al\u0131\u015fmas\u0131n\u0131 sa\u011flarken, ayn\u0131 zamanda Azure&#8217;un g\u00fc\u00e7l\u00fc altyap\u0131s\u0131ndan faydalanmalar\u0131na olanak tan\u0131r.<\/p>\n<h4>Azure AI Foundry&#8217;de Ajan Da\u011f\u0131t\u0131m\u0131<\/h4>\n<p>MAF ajanlar\u0131, Azure AI Foundry \u00fczerinde \u00e7e\u015fitli \u015fekillerde da\u011f\u0131t\u0131labilir. K\u00fc\u00e7\u00fck, olay tabanl\u0131 ajanlar i\u00e7in Azure Functions veya Azure Container Apps kullan\u0131labilirken, daha karma\u015f\u0131k ve uzun \u00f6m\u00fcrl\u00fc ajanlar i\u00e7in Azure Kubernetes Service (AKS) ideal bir platform sunar. AKS, ajanlar\u0131n konteynerize edilmi\u015f hallerini y\u00f6neterek \u00f6l\u00e7eklenebilirlik, hata tolerans\u0131 ve kaynak izolasyonu sa\u011flar.<\/p>\n<pre><code class=\"language-yaml\">\napiVersion: apps\/v1\nkind: Deployment\nmetadata:\n  name: ma-agent-deployment\nspec:\n  replicas: 3\n  selector:\n    matchLabels:\n      app: ma-agent\n  template:\n    metadata:\n      labels:\n        app: ma-agent\n    spec:\n      containers:\n      - name: ma-agent-container\n        image: youracr.azurecr.io\/maf-agent:latest\n        ports:\n        - containerPort: 8080\n        env:\n        - name: AZURE_AI_FOUNDRY_ENDPOINT\n          value: \"https:\/\/your-ai-foundry.cognitiveservices.azure.com\/\"\n        - name: AZURE_AI_FOUNDRY_KEY\n          valueFrom:\n            secretKeyRef:\n              name: ai-foundry-secret\n              key: key\n<\/pre>\n<p><\/code><\/p>\n<h4>Veri Ak\u0131\u015f\u0131 ve \u0130leti\u015fim Mekanizmalar\u0131<\/h4>\n<p>Ajanlar aras\u0131 ileti\u015fim ve veri al\u0131\u015fveri\u015fi, Azure servisleri arac\u0131l\u0131\u011f\u0131yla sa\u011flanabilir. Azure Service Bus veya Azure Event Hubs, ajanlar\u0131n mesajla\u015fma ve olay tabanl\u0131 ileti\u015fim kurmas\u0131 i\u00e7in g\u00fcvenilir ve \u00f6l\u00e7eklenebilir \u00e7\u00f6z\u00fcmler sunar. Azure Storage (Blob, Table, Queue) ise ajanlar\u0131n durum bilgilerini, \u00f6\u011frenilmi\u015f modelleri veya i\u015flenen verileri depolamas\u0131 i\u00e7in kullan\u0131labilir. Azure Machine Learning, ajanlar\u0131n kullanaca\u011f\u0131 yapay zeka modellerini e\u011fitmek ve y\u00f6netmek i\u00e7in merkezi bir platform g\u00f6revi g\u00f6r\u00fcr.<\/p>\n<p><strong>\u00d6rnek \u0130leti\u015fim Ak\u0131\u015f\u0131:<\/strong><\/p>\n<ol>\n<li>Ajan A, bir olay alg\u0131lar ve Azure Event Hubs'a bir mesaj g\u00f6nderir.<\/li>\n<li>Ajan B, Event Hubs'tan bu mesaj\u0131 al\u0131r.<\/li>\n<li>Ajan B, Azure Machine Learning'deki bir modeli kullanarak kararlar al\u0131r.<\/li>\n<li>Karar sonucunu Azure Service Bus \u00fczerinden Ajan C'ye iletir.<\/li>\n<li>Ajan C, ald\u0131\u011f\u0131 karara g\u00f6re bir eylem ger\u00e7ekle\u015ftirir ve durumu Azure Cosmos DB'ye kaydeder.<\/li>\n<\/ol>\n<h4>Kullan\u0131lan Azure Servisleri<\/h4>\n<p>Entegrasyon i\u00e7in yayg\u0131n olarak kullan\u0131lan Azure servisleri:<\/p>\n<table>\n<thead>\n<tr>\n<th>Azure Servisi<\/th>\n<th>Kullan\u0131m Amac\u0131<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Azure Kubernetes Service (AKS)<\/td>\n<td>Ajanlar\u0131n konteynerize edilmi\u015f da\u011f\u0131t\u0131m\u0131 ve y\u00f6netimi.<\/td>\n<\/tr>\n<tr>\n<td>Azure Functions \/ Container Apps<\/td>\n<td>Olay tabanl\u0131, sunucusuz ajanlar veya mikro servisler.<\/td>\n<\/tr>\n<tr>\n<td>Azure Machine Learning<\/td>\n<td>Ajanlar\u0131n kullanaca\u011f\u0131 AI modellerinin e\u011fitimi, y\u00f6netimi ve da\u011f\u0131t\u0131m\u0131.<\/td>\n<\/tr>\n<tr>\n<td>Azure Event Hubs \/ Service Bus<\/td>\n<td>Ajanlar aras\u0131 mesajla\u015fma ve olay ak\u0131\u015f\u0131.<\/td>\n<\/tr>\n<tr>\n<td>Azure Cosmos DB \/ SQL Database<\/td>\n<td>Ajanlar\u0131n durum, konfig\u00fcrasyon ve \u00f6\u011frenme verilerinin depolanmas\u0131.<\/td>\n<\/tr>\n<tr>\n<td>Azure Monitor \/ Application Insights<\/td>\n<td>Ajan performans\u0131n\u0131n ve sistem sa\u011fl\u0131\u011f\u0131n\u0131n izlenmesi.<\/td>\n<\/tr>\n<tr>\n<td>Azure Key Vault<\/td>\n<td>Ajanlar\u0131n kimlik bilgileri ve s\u0131rlar\u0131n\u0131n g\u00fcvenli y\u00f6netimi.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h3>Uygulama Senaryolar\u0131 ve \u00d6rnekler<\/h3>\n<p>MAF ajanlar\u0131n\u0131n Azure AI Foundry ile birle\u015fimi, bir\u00e7ok sekt\u00f6rde yenilik\u00e7i ve ak\u0131ll\u0131 \u00e7\u00f6z\u00fcmlerin kap\u0131s\u0131n\u0131 aralamaktad\u0131r.<\/p>\n<h4>Ak\u0131ll\u0131 Otomasyon ve Karar Destek Sistemleri<\/h4>\n<p>\u00dcretim hatlar\u0131nda, lojistik operasyonlar\u0131nda veya finansal piyasalarda MAF ajanlar\u0131, karma\u015f\u0131k s\u00fcre\u00e7leri otomatikle\u015ftirerek insan m\u00fcdahalesini azaltabilir. Her ajan, belirli bir g\u00f6revi (\u00f6rn. envanter takibi, rota optimizasyonu, risk analizi) \u00fcstlenirken, Azure AI Foundry'deki modellerden ger\u00e7ek zamanl\u0131 tahminler ve \u00f6neriler alarak daha bilin\u00e7li kararlar verebilir. Bu, operasyonel verimlili\u011fi art\u0131r\u0131r ve maliyetleri d\u00fc\u015f\u00fcr\u00fcr.<\/p>\n<h4>Tahminsel Bak\u0131m ve Anomali Tespiti<\/h4>\n<p>End\u00fcstriyel makinelerdeki sens\u00f6r verilerini s\u00fcrekli olarak izleyen ajanlar, Azure AI Foundry'de e\u011fitilmi\u015f anomali tespit modellerini kullanarak potansiyel ar\u0131zalar\u0131 \u00f6nceden belirleyebilir. Her makine veya bile\u015fen i\u00e7in bir ajan atanabilir. Bu ajanlar, veri toplar, analiz eder ve anormallik tespit etti\u011finde ilgili bak\u0131m ajanlar\u0131n\u0131 veya insan operat\u00f6rleri uyar\u0131r. Bu sayede plans\u0131z duru\u015f s\u00fcreleri azal\u0131r ve ekipman \u00f6mr\u00fc uzar.<\/p>\n<h4>Ki\u015fiselle\u015ftirilmi\u015f M\u00fc\u015fteri Deneyimleri<\/h4>\n<p>Perakende, bankac\u0131l\u0131k veya sa\u011fl\u0131k sekt\u00f6r\u00fcnde, her m\u00fc\u015fteri i\u00e7in bir \"ki\u015fisel asistan\" ajan\u0131 atanabilir. Bu ajanlar, m\u00fc\u015fterinin ge\u00e7mi\u015f davran\u0131\u015flar\u0131n\u0131, tercihlerini ve mevcut ba\u011flam\u0131n\u0131 Azure AI Foundry'deki ki\u015fiselle\u015ftirme modelleriyle analiz ederek, onlara \u00f6zel \u00fcr\u00fcn \u00f6nerileri, hizmetler veya destek sunabilir. Ajanlar, do\u011fal dil i\u015fleme (NLP) yeteneklerini kullanarak m\u00fc\u015fteriyle etkile\u015fim kurabilir ve deneyimi s\u00fcrekli olarak iyile\u015ftirebilir.<\/p>\n<h3>Geli\u015ftirme S\u00fcreci ve Best Practices<\/h3>\n<p>MAF ajanlar\u0131n\u0131 Azure AI Foundry \u00fczerinde geli\u015ftirmek, belirli bir metodoloji ve en iyi uygulamalarla daha verimli hale getirilebilir.<\/p>\n<h4>Proje Kurulumu ve Ortam Haz\u0131rl\u0131\u011f\u0131<\/h4>\n<p>\u0130lk ad\u0131m, Azure aboneli\u011fi olu\u015fturmak ve gerekli kaynak gruplar\u0131n\u0131, depolama hesaplar\u0131n\u0131 ve Azure AI Foundry \u00e7al\u0131\u015fma alan\u0131n\u0131 yap\u0131land\u0131rmakt\u0131r. Geli\u015ftirme ortam\u0131 olarak Visual Studio Code veya Jupyter Notebooks gibi ara\u00e7lar kullan\u0131labilir. Gerekli SDK'lar\u0131n (\u00f6rn. Azure ML SDK, Azure Python SDK) kurulmas\u0131 ve kimlik do\u011frulama mekanizmalar\u0131n\u0131n (\u00f6rn. Azure AD, Service Principal) ayarlanmas\u0131 \u00f6nemlidir.<\/p>\n<pre><code class=\"language-bash\">\n# Azure CLI ile kaynak grubu ve AI Foundry \u00e7al\u0131\u015fma alan\u0131 olu\u015fturma\naz group create --name myAIFoundryResourceGroup --location eastus\naz ml workspace create --name myAIFoundryWorkspace --resource-group myAIFoundryResourceGroup\n<\/pre>\n<p><\/code><\/p>\n<h4>Ajan Tasar\u0131m\u0131 ve Uygulamas\u0131<\/h4>\n<p>Ajanlar\u0131n tasar\u0131m\u0131, sistemin genel hedeflerine ve ajanlar\u0131n \u00fcstlenece\u011fi rollere g\u00f6re yap\u0131lmal\u0131d\u0131r. Her ajan\u0131n sorumluluklar\u0131, ileti\u015fim protokolleri ve karar alma mekanizmalar\u0131 net bir \u015fekilde tan\u0131mlanmal\u0131d\u0131r. Python gibi diller, ajanlar\u0131n geli\u015ftirilmesi i\u00e7in pop\u00fcler bir se\u00e7imdir. Ajanlar\u0131n yapay zeka yetenekleri (\u00f6rn. s\u0131n\u0131fland\u0131rma, regresyon, LLM etkile\u015fimi) Azure AI Foundry'deki modeller arac\u0131l\u0131\u011f\u0131yla sa\u011flanmal\u0131d\u0131r.<\/p>\n<p><strong>Basit Bir Ajan Karar Mant\u0131\u011f\u0131 (Pseudocode):<\/strong><\/p>\n<pre><code class=\"language-python\">\nclass SensorAgent:\n    def __init__(self, agent_id, ai_foundry_client):\n        self.id = agent_id\n        self.ai_client = ai_foundry_client\n\n    def perceive_environment(self, sensor_data):\n        # Sens\u00f6r verilerini i\u015fleme\n        processed_data = self.preprocess(sensor_data)\n        return processed_data\n\n    def make_decision(self, processed_data):\n        # Azure AI Foundry'deki bir modelden tahmin alma\n        prediction = self.ai_client.invoke_model(\"anomaly_detector\", processed_data)\n        if prediction['is_anomaly']:\n            return \"ALERT_MAINTENANCE_AGENT\"\n        else:\n            return \"CONTINUE_MONITORING\"\n\n    def execute_action(self, decision):\n        if decision == \"ALERT_MAINTENANCE_AGENT\":\n            # Azure Service Bus \u00fczerinden bak\u0131m ajan\u0131n\u0131 bilgilendir\n            self.send_message_to_service_bus(\"maintenance_topic\", {\"agent_id\": self.id, \"anomaly_details\": ...})\n        elif decision == \"CONTINUE_MONITORING\":\n            # Durumu logla\n            self.log_status(\"Monitoring normal.\")\n\n# Ana d\u00f6ng\u00fc\n# agent = SensorAgent(\"sensor_001\", azure_ai_foundry_client)\n# while True:\n#     data = get_sensor_data()\n#     processed = agent.perceive_environment(data)\n#     decision = agent.make_decision(processed)\n#     agent.execute_action(decision)\n<\/pre>\n<p><\/code><\/p>\n<h4>Test, Da\u011f\u0131t\u0131m ve \u0130zleme<\/h4>\n<p>Ajanlar\u0131n ve t\u00fcm sistemin i\u015flevselli\u011fini, performans\u0131n\u0131 ve g\u00fcvenilirli\u011fini sa\u011flamak i\u00e7in kapsaml\u0131 testler yap\u0131lmal\u0131d\u0131r. Birim testleri, entegrasyon testleri ve sistem testleri bu s\u00fcrecin par\u00e7as\u0131d\u0131r. Ajanlar konteynerize edildikten sonra Azure Container Registry'ye itilmeli ve AKS veya Azure Container Apps \u00fczerinde da\u011f\u0131t\u0131lmal\u0131d\u0131r. Azure Monitor ve Application Insights, ajanlar\u0131n \u00e7al\u0131\u015fma zaman\u0131 performans\u0131n\u0131, hatalar\u0131n\u0131 ve etkile\u015fimlerini izlemek i\u00e7in kritik ara\u00e7lard\u0131r. Bu izleme verileri, sistemin s\u00fcrekli iyile\u015ftirilmesi i\u00e7in geri bildirim sa\u011flar.<\/p>\n<h3>Gelecek ve Potansiyel<\/h3>\n<p>MAF ajanlar\u0131 ve Azure AI Foundry entegrasyonu, yapay zeka alan\u0131nda gelecekteki bir\u00e7ok yenili\u011fin temelini olu\u015fturma potansiyeline sahiptir.<\/p>\n<h4>Geli\u015fen Trendler ve Yenilikler<\/h4>\n<p>\u00dcretken yapay zeka (Generative AI) modellerinin MAF ajanlar\u0131yla birle\u015fimi, ajanlar\u0131n daha karma\u015f\u0131k ve yarat\u0131c\u0131 g\u00f6revleri yerine getirmesini sa\u011flayabilir. \u00d6rne\u011fin, bir tasar\u0131m ajan\u0131, Azure AI Foundry'deki bir \u00fcretken modelden yeni tasar\u0131m fikirleri \u00fcretebilir. Otonom ajanlar, daha karma\u015f\u0131k ortamlarda insan benzeri karar verme yetenekleri sergileyebilir. Federasyon \u00f6\u011frenimi gibi da\u011f\u0131t\u0131k \u00f6\u011frenme yakla\u015f\u0131mlar\u0131, ajanlar\u0131n hassas verileri payla\u015fmadan kolektif olarak \u00f6\u011frenmesini sa\u011flayabilir.<\/p>\n<h4>Sekt\u00f6rel Etkiler ve D\u00f6n\u00fc\u015f\u00fcm<\/h4>\n<p>Bu entegrasyon, sa\u011fl\u0131k, finans, \u00fcretim, perakende ve savunma gibi bir\u00e7ok sekt\u00f6rde devrim niteli\u011finde d\u00f6n\u00fc\u015f\u00fcmler yaratabilir. Daha ak\u0131ll\u0131, daha \u00f6zerk ve daha adapte olabilen sistemler, i\u015fletmelerin verimlili\u011fini art\u0131r\u0131rken, yeni i\u015f modelleri ve hizmetler ortaya \u00e7\u0131karacakt\u0131r. \u00d6zellikle ger\u00e7ek zamanl\u0131 karar verme ve dinamik adaptasyon gerektiren alanlarda b\u00fcy\u00fck fark yaratacakt\u0131r.<\/p>\n<h4>Microsoft'un Vizyonu<\/h4>\n<p>Microsoft, Azure AI Foundry ile yapay zekay\u0131 demokratikle\u015ftirmeyi ve geli\u015ftiricilerin en son teknolojilere kolayca eri\u015fmesini sa\u011flamay\u0131 hedeflemektedir. MAF ajanlar\u0131 gibi geli\u015fmi\u015f yapay zeka paradigmalar\u0131n\u0131n bu platform \u00fczerinde desteklenmesi, Microsoft'un ak\u0131ll\u0131 bulut ve ak\u0131ll\u0131 u\u00e7 vizyonunun \u00f6nemli bir par\u00e7as\u0131d\u0131r. Bu, gelecekte daha fazla entegrasyon ve geli\u015ftirme arac\u0131 sunulaca\u011f\u0131 anlam\u0131na gelmektedir.<\/p>\n<h3>Sonu\u00e7<\/h3>\n<p>MAF ajanlar\u0131 ve Azure AI Foundry Projesi'nin birle\u015fimi, da\u011f\u0131t\u0131k, \u00f6zerk ve ak\u0131ll\u0131 sistemler olu\u015fturmak i\u00e7in g\u00fc\u00e7l\u00fc ve \u00f6l\u00e7eklenebilir bir platform sunmaktad\u0131r. Ajanlar\u0131n esnekli\u011fi ve adaptasyon yetene\u011fi ile Azure'un bulut altyap\u0131s\u0131n\u0131n ve yapay zeka hizmetlerinin g\u00fcc\u00fc bir araya geldi\u011finde, i\u015fletmeler ve geli\u015ftiriciler karma\u015f\u0131k sorunlara yenilik\u00e7i \u00e7\u00f6z\u00fcmler \u00fcretebilir, operasyonel verimlili\u011fi art\u0131rabilir ve gelece\u011fin ak\u0131ll\u0131 uygulamalar\u0131n\u0131 bug\u00fcnden in\u015fa edebilirler. Bu sinerji, yapay zekan\u0131n potansiyelini tam anlam\u0131yla ortaya \u00e7\u0131kararak dijital d\u00f6n\u00fc\u015f\u00fcmde yeni bir d\u00f6nemi ba\u015flatmaktad\u0131r.<\/p>\n<h3>SSS (S\u0131k Sorulan Sorular)<\/h3>\n<dl>\n<dt>MAF Ajanlar\u0131 nedir?<\/dt>\n<dd>MAF Ajanlar\u0131 (Multi-Agent Systems), \u00f6zerk, etkile\u015fimli ve genellikle heterojen ajanlar\u0131n bir araya gelerek belirli bir amac\u0131 ger\u00e7ekle\u015ftirdi\u011fi da\u011f\u0131t\u0131k yapay zeka sistemleridir. Her ajan kendi kararlar\u0131n\u0131 alabilir ve \u00e7evresiyle etkile\u015fime ge\u00e7ebilir.<\/dd>\n<dt>Azure AI Foundry ne i\u015fe yarar?<\/dt>\n<dd>Azure AI Foundry, Microsoft'un b\u00fcy\u00fck \u00f6l\u00e7ekli yapay zeka modelleri geli\u015ftirmek, e\u011fitmek, da\u011f\u0131tmak ve y\u00f6netmek i\u00e7in tasarlanm\u0131\u015f kapsaml\u0131 bir platformudur. \u00d6zellikle \u00fcretken yapay zeka ve b\u00fcy\u00fck dil modelleri i\u00e7in optimize edilmi\u015ftir.<\/dd>\n<dt>Bu entegrasyonun temel faydas\u0131 nedir?<\/dt>\n<dd>Temel faydas\u0131, MAF ajanlar\u0131n\u0131n da\u011f\u0131t\u0131k problem \u00e7\u00f6zme yeteneklerini Azure AI Foundry'nin \u00f6l\u00e7eklenebilir, g\u00fcvenli ve y\u00f6netilebilir yapay zeka altyap\u0131s\u0131yla birle\u015ftirmektir. Bu sayede daha h\u0131zl\u0131 geli\u015ftirme, y\u00fcksek performans ve kurumsal d\u00fczeyde g\u00fcvenilirlik sa\u011flan\u0131r.<\/dd>\n<dt>Hangi Azure servisleri kullan\u0131l\u0131r?<\/dt>\n<dd>Entegrasyon i\u00e7in Azure Kubernetes Service (AKS), Azure Functions, Azure Machine Learning, Azure Event Hubs, Azure Service Bus, Azure Cosmos DB ve Azure Monitor gibi \u00e7e\u015fitli Azure servisleri kullan\u0131labilir.<\/dd>\n<dt>Geli\u015ftirme i\u00e7in hangi diller\/frameworkler tercih edilir?<\/dt>\n<dd>Ajanlar\u0131n geli\u015ftirilmesi i\u00e7in genellikle Python tercih edilir. Azure AI Foundry ile etkile\u015fim i\u00e7in Azure ML SDK ve Azure Python SDK gibi k\u00fct\u00fcphaneler kullan\u0131l\u0131r. Konteynerizasyon i\u00e7in Docker, orkestrasyon i\u00e7in Kubernetes (AKS) yayg\u0131n olarak kullan\u0131l\u0131r.<\/dd>\n<\/dl>\n","protected":false},"excerpt":{"rendered":"G\u00fcn\u00fcm\u00fcz\u00fcn h\u0131zla de\u011fi\u015fen dijital d\u00fcnyas\u0131nda, karma\u015f\u0131k problemleri \u00e7\u00f6zmek ve dinamik ortamlara adapte olabilen ak\u0131ll\u0131 sistemler geli\u015ftirmek b\u00fc&#8230;","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"csco_page_header_type":"","csco_page_load_nextpost":"","csco_page_subscribe_form":"","csco_page_contact_form":"","footnotes":""},"categories":[1405],"tags":[],"class_list":{"0":"post-37280","1":"post","2":"type-post","3":"status-publish","4":"format-standard","6":"category-azure","7":"cs-entry","8":"cs-video-wrap"},"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v20.5 (Yoast SEO v25.3.1) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Azure AI Foundry Projesi ile MAF Ajanlar\u0131: Gelece\u011fin Ak\u0131ll\u0131 Sistemlerini \u0130n\u015fa Etmek - Kodlar\u0131n Gizemli D\u00fcnyas\u0131<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/\" \/>\n<meta property=\"og:locale\" content=\"tr_TR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Azure AI Foundry Projesi ile MAF Ajanlar\u0131: Gelece\u011fin Ak\u0131ll\u0131 Sistemlerini \u0130n\u015fa Etmek\" \/>\n<meta property=\"og:description\" content=\"G\u00fcn\u00fcm\u00fcz\u00fcn h\u0131zla de\u011fi\u015fen dijital d\u00fcnyas\u0131nda, karma\u015f\u0131k problemleri \u00e7\u00f6zmek ve dinamik ortamlara adapte olabilen ak\u0131ll\u0131 sistemler geli\u015ftirmek b\u00fc...\" \/>\n<meta property=\"og:url\" content=\"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/\" \/>\n<meta property=\"og:site_name\" content=\"Kodlar\u0131n Gizemli D\u00fcnyas\u0131\" \/>\n<meta property=\"article:published_time\" content=\"2025-12-29T18:00:38+00:00\" \/>\n<meta name=\"author\" content=\"Fatih Soysal\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Yazan:\" \/>\n\t<meta name=\"twitter:data1\" content=\"Fatih Soysal\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tahmini okuma s\u00fcresi\" \/>\n\t<meta name=\"twitter:data2\" content=\"14 dakika\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/\"},\"author\":{\"name\":\"Fatih Soysal\",\"@id\":\"https:\/\/fatihsoysal.com\/blog\/#\/schema\/person\/002a254750921dcfd568a99e48240dd1\"},\"headline\":\"Azure AI Foundry Projesi ile MAF Ajanlar\u0131: Gelece\u011fin Ak\u0131ll\u0131 Sistemlerini \u0130n\u015fa Etmek\",\"datePublished\":\"2025-12-29T18:00:38+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/\"},\"wordCount\":2554,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/fatihsoysal.com\/blog\/#\/schema\/person\/002a254750921dcfd568a99e48240dd1\"},\"articleSection\":[\"Azure\"],\"inLanguage\":\"tr\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/#respond\"]}],\"copyrightYear\":\"2025\",\"copyrightHolder\":{\"@id\":\"https:\/\/fatihsoysal.com\/blog\/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/\",\"url\":\"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/\",\"name\":\"Azure AI Foundry Projesi ile MAF Ajanlar\u0131: Gelece\u011fin Ak\u0131ll\u0131 Sistemlerini \u0130n\u015fa Etmek - Kodlar\u0131n Gizemli D\u00fcnyas\u0131\",\"isPartOf\":{\"@id\":\"https:\/\/fatihsoysal.com\/blog\/#website\"},\"datePublished\":\"2025-12-29T18:00:38+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/#breadcrumb\"},\"inLanguage\":\"tr\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Anasayfa\",\"item\":\"https:\/\/fatihsoysal.com\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Azure AI Foundry Projesi ile MAF Ajanlar\u0131: Gelece\u011fin Ak\u0131ll\u0131 Sistemlerini \u0130n\u015fa Etmek\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/fatihsoysal.com\/blog\/#website\",\"url\":\"https:\/\/fatihsoysal.com\/blog\/\",\"name\":\"Fatihsoysal.com\",\"description\":\"Blog - Yaz\u0131l\u0131m D\u00fcnyas\u0131 Tecr\u00fcbelerim\",\"publisher\":{\"@id\":\"https:\/\/fatihsoysal.com\/blog\/#\/schema\/person\/002a254750921dcfd568a99e48240dd1\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/fatihsoysal.com\/blog\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"tr\"},{\"@type\":[\"Person\",\"Organization\"],\"@id\":\"https:\/\/fatihsoysal.com\/blog\/#\/schema\/person\/002a254750921dcfd568a99e48240dd1\",\"name\":\"Fatih Soysal\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"tr\",\"@id\":\"https:\/\/fatihsoysal.com\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/fatihsoysal.com\/blog\/wp-content\/uploads\/2024\/04\/cropped-replicate-prediction-3kgg1hgjn5rgp0cf0p5tr0jw7w-1.png\",\"contentUrl\":\"https:\/\/fatihsoysal.com\/blog\/wp-content\/uploads\/2024\/04\/cropped-replicate-prediction-3kgg1hgjn5rgp0cf0p5tr0jw7w-1.png\",\"width\":512,\"height\":512,\"caption\":\"Fatih Soysal\"},\"logo\":{\"@id\":\"https:\/\/fatihsoysal.com\/blog\/#\/schema\/person\/image\/\"},\"description\":\"Kullan\u0131m ve kodlama m\u00fckemmeliyetini odak alan uygulamalar olu\u015fturma deneyimine sahip, profesyonel olarak 15+ y\u0131l \u00fczeri deneyime sahip bir yaz\u0131l\u0131m m\u00fchendisi.\",\"url\":\"https:\/\/fatihsoysal.com\/blog\/author\/fatihsoysal\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Azure AI Foundry Projesi ile MAF Ajanlar\u0131: Gelece\u011fin Ak\u0131ll\u0131 Sistemlerini \u0130n\u015fa Etmek - Kodlar\u0131n Gizemli D\u00fcnyas\u0131","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/","og_locale":"tr_TR","og_type":"article","og_title":"Azure AI Foundry Projesi ile MAF Ajanlar\u0131: Gelece\u011fin Ak\u0131ll\u0131 Sistemlerini \u0130n\u015fa Etmek","og_description":"G\u00fcn\u00fcm\u00fcz\u00fcn h\u0131zla de\u011fi\u015fen dijital d\u00fcnyas\u0131nda, karma\u015f\u0131k problemleri \u00e7\u00f6zmek ve dinamik ortamlara adapte olabilen ak\u0131ll\u0131 sistemler geli\u015ftirmek b\u00fc...","og_url":"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/","og_site_name":"Kodlar\u0131n Gizemli D\u00fcnyas\u0131","article_published_time":"2025-12-29T18:00:38+00:00","author":"Fatih Soysal","twitter_card":"summary_large_image","twitter_misc":{"Yazan:":"Fatih Soysal","Tahmini okuma s\u00fcresi":"14 dakika"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/#article","isPartOf":{"@id":"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/"},"author":{"name":"Fatih Soysal","@id":"https:\/\/fatihsoysal.com\/blog\/#\/schema\/person\/002a254750921dcfd568a99e48240dd1"},"headline":"Azure AI Foundry Projesi ile MAF Ajanlar\u0131: Gelece\u011fin Ak\u0131ll\u0131 Sistemlerini \u0130n\u015fa Etmek","datePublished":"2025-12-29T18:00:38+00:00","mainEntityOfPage":{"@id":"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/"},"wordCount":2554,"commentCount":0,"publisher":{"@id":"https:\/\/fatihsoysal.com\/blog\/#\/schema\/person\/002a254750921dcfd568a99e48240dd1"},"articleSection":["Azure"],"inLanguage":"tr","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/#respond"]}],"copyrightYear":"2025","copyrightHolder":{"@id":"https:\/\/fatihsoysal.com\/blog\/#organization"}},{"@type":"WebPage","@id":"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/","url":"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/","name":"Azure AI Foundry Projesi ile MAF Ajanlar\u0131: Gelece\u011fin Ak\u0131ll\u0131 Sistemlerini \u0130n\u015fa Etmek - Kodlar\u0131n Gizemli D\u00fcnyas\u0131","isPartOf":{"@id":"https:\/\/fatihsoysal.com\/blog\/#website"},"datePublished":"2025-12-29T18:00:38+00:00","breadcrumb":{"@id":"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/#breadcrumb"},"inLanguage":"tr","potentialAction":[{"@type":"ReadAction","target":["https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/fatihsoysal.com\/blog\/azure-ai-foundry-projesi-ile-maf-ajanlari-gelecegin-akilli-sistemlerini-insa-etmek\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Anasayfa","item":"https:\/\/fatihsoysal.com\/blog\/"},{"@type":"ListItem","position":2,"name":"Azure AI Foundry Projesi ile MAF Ajanlar\u0131: Gelece\u011fin Ak\u0131ll\u0131 Sistemlerini \u0130n\u015fa Etmek"}]},{"@type":"WebSite","@id":"https:\/\/fatihsoysal.com\/blog\/#website","url":"https:\/\/fatihsoysal.com\/blog\/","name":"Fatihsoysal.com","description":"Blog - Yaz\u0131l\u0131m D\u00fcnyas\u0131 Tecr\u00fcbelerim","publisher":{"@id":"https:\/\/fatihsoysal.com\/blog\/#\/schema\/person\/002a254750921dcfd568a99e48240dd1"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/fatihsoysal.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"tr"},{"@type":["Person","Organization"],"@id":"https:\/\/fatihsoysal.com\/blog\/#\/schema\/person\/002a254750921dcfd568a99e48240dd1","name":"Fatih Soysal","image":{"@type":"ImageObject","inLanguage":"tr","@id":"https:\/\/fatihsoysal.com\/blog\/#\/schema\/person\/image\/","url":"https:\/\/fatihsoysal.com\/blog\/wp-content\/uploads\/2024\/04\/cropped-replicate-prediction-3kgg1hgjn5rgp0cf0p5tr0jw7w-1.png","contentUrl":"https:\/\/fatihsoysal.com\/blog\/wp-content\/uploads\/2024\/04\/cropped-replicate-prediction-3kgg1hgjn5rgp0cf0p5tr0jw7w-1.png","width":512,"height":512,"caption":"Fatih Soysal"},"logo":{"@id":"https:\/\/fatihsoysal.com\/blog\/#\/schema\/person\/image\/"},"description":"Kullan\u0131m ve kodlama m\u00fckemmeliyetini odak alan uygulamalar olu\u015fturma deneyimine sahip, profesyonel olarak 15+ y\u0131l \u00fczeri deneyime sahip bir yaz\u0131l\u0131m m\u00fchendisi.","url":"https:\/\/fatihsoysal.com\/blog\/author\/fatihsoysal\/"}]}},"yoast_meta":{"yoast_wpseo_title":"","yoast_wpseo_metadesc":"","yoast_wpseo_canonical":""},"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/fatihsoysal.com\/blog\/wp-json\/wp\/v2\/posts\/37280","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/fatihsoysal.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/fatihsoysal.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/fatihsoysal.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/fatihsoysal.com\/blog\/wp-json\/wp\/v2\/comments?post=37280"}],"version-history":[{"count":0,"href":"https:\/\/fatihsoysal.com\/blog\/wp-json\/wp\/v2\/posts\/37280\/revisions"}],"wp:attachment":[{"href":"https:\/\/fatihsoysal.com\/blog\/wp-json\/wp\/v2\/media?parent=37280"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/fatihsoysal.com\/blog\/wp-json\/wp\/v2\/categories?post=37280"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/fatihsoysal.com\/blog\/wp-json\/wp\/v2\/tags?post=37280"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}