Agentic AI Training in Belgrade

Ova edukacija uživo u Belgrade istražuje kako agentic AI transformiše organizacione radne tokove, strategije kadrova i dizajn poslova. Idealna za stručnjake srednjeg nivoa, pokriva autonomno donošenje odluka, spremnost preduzeća i okvire upravljanja kako bi se osigurala odgovorna i usklađena primena AI.

Ovaj bootstrap sa vodičem uživo u Belgrade nudi praktičan put za izgradnju autonomnih AI agenata u Pythonu. Učesnici završavaju pet progresivnih projekata koji pokrivaju obrasce dizajna, orkestraciju API-ja i tokove rada više agenata, prelazeći od teorije do raspoređivanja u realnom svetu.

Ovaj praktičan kurs u Belgrade vodi vas kroz razvrtavanje agencijskog AI na uređajima sa ograničenim resursima. Naučite kako da izgradite, optimizujete i upravljate laganim agentima za lokalno razmišljanje koristeći Python, TensorFlow Lite i PyTorch Mobile, poboljšavajući brzinu, privatnost i pouzdanost.

This live, instructor-led program in Belgrade introduces agentic AI, exploring prompt engineering, architectural patterns, and ethical usage. Learners acquire the skills to construct basic agent workflows with Python, integrate external tools, and apply safety measures to create autonomous systems that are effective, secure, and scalable.

This instructor-led, live training in Belgrade supports intermediate professionals in designing and scaling agentic AI for business automation. Participants learn to map workflows, integrate tools, and create practical use cases in customer service, supply chain, and marketing, ensuring tangible business impact.

This live training in Belgrade assists advanced professionals in designing and implementing multi-agent systems using Python. It addresses agent coordination, reinforcement learning, and distributed computing with frameworks such as Mesa and Ray, culminating in a hands-on capstone project.

This instructor-led training in Belgrade focuses on reinforcement learning and decision-making for agentic AI. Learners will implement DQN, PPO, and A3C using Python, model environments via OpenAI Gym, and apply these techniques to robotics and planning systems to achieve real-world adaptive behavior.

This live training in Belgrade empowers advanced professionals with the skills necessary to scale and operationalize agentic AI systems in production. Covering MLOps, observability, and cost control, it enables the design of resilient, observable, and cost-optimized pipelines for large-scale deployments.

This live, instructor-led training in Belgrade guides BI professionals in modernizing legacy systems with WrenAI. You will evaluate current environments, strategize migrations to conversational analytics, and steer change management initiatives to ensure seamless adoption and tangible business value.

This instructor-led training in Belgrade focuses on governance, identity management, and red-teaming for agentic AI systems. Advanced practitioners will learn to design secure deployments, enforce least-privilege access, and perform adversarial testing to mitigate real-world threats within production environments.

This instructor-led, live training in Belgrade focuses on practical Python implementation for autonomous AI agents. It explores modern SDKs like LangChain and AutoGen, enabling engineers to build, connect, and orchestrate complex agent workflows with confidence.

This instructor-led training in Belgrade guides finance professionals in utilizing WrenAI to model KPIs and build dashboards that are inherently compliance-aware. Participants will develop practical skills in data source integration, maintaining audit readiness, and generating risk management reports to support robust decision-making.

This live, instructor-led course in Belgrade focuses on practical Python techniques for developing autonomous agents. It covers essential components such as agent loops, tool integration, memory management, orchestration, and safety controls. The course is ideal for ML engineers aiming to deploy resilient, production-ready agents.

Ova obuka uživo koju vodi instruktor u okviru Belgrade oprema napredne stručnjake neophodnim veštinama za osiguranje kvaliteta u WrenAI. Učesnici će naučiti da procenjuju tačnost generisanja SQL iz prirodnog jezika, primenjuju podešavanje upita (prompt tuning) i implementiraju okvire za posmatranje. Idealno za obezbeđivanje pouzdanosti i usklađenosti na nivou preduzeća.

Otkrijte agentičku veštačku inteligenciju u zdravstvu uz ovu obuku koju vodi instruktor u Belgrade. Naučite kako da projektujete, evaluirate i upravljate tokovima rada agenata za kliničke primene. Učesnici će izgrađivati agente potpomognute pretragom, primenjivati mehanizme zaštite i savladati upravljanje putem praktičnih laboratorijskih radova i vežbi zasnovanih na scenarijima.

This instructor-led, live training in Belgrade (online or onsite) is aimed at intermediate-level AI developers and automation specialists who wish to integrate agentic capabilities into AI-powered applications.

By the end of this training, participants will be able to:

• Understand the principles of agentic AI and autonomous decision-making.
• Implement goal-driven AI agents with self-optimization techniques.
• Integrate multi-agent collaboration for complex problem-solving.
• Enhance AI-human interaction through adaptive user experiences.
• Deploy agentic AI models in real-world applications.

Ova uživo obuka sa instruktorom u Belgrade pomaže profesionalcima iz operacija da savladaju WrenAI Spreadsheets i Metrics Library. Naučite da izgrađujete izveštaje potpomognute veštačkom inteligencijom, povežete podatke uživo i uskladite radne tokove kako biste ubrzali operativnu analitiku i efikasno poslovno izveštavanje.

Ovaj instrukcijski, uživo obukom u Belgrade (online ili na lokaciji) namenjen je profesionalima naprednog nivoa koji žele da razviju i optimizuju sisteme više agenata koristeći Agentic AI okvire.

Na kraju ove obuke, učesnici će moći da:

• Razumeju principe Agentic AI u okruženjima više agenata.
• Razviju AI agentove koji autonomno interaguju.
• Primene učenje sa jačanjem za adaptivno AI ponašanje.
• Optimizuju saradnju i takmičenje više agenata.
• Primene Agentic AI u robotici, igricama i preduzećkoj automatizaciji.

Ova uživa obuka uz instruktora u Belgrade opremi inženjere srednjeg nivoa znanja veštinama potrebnim za korišćenje WrenAI API-ja u praktičnim primenama. Učesnici će naučiti da generišu SQL kod iz prirodnog jezika, kreiraju i integrišu grafikone, kao i da integrišu API u backend sisteme i interne alate.

This instructor-led, live training in Belgrade (online or onsite) is designed for advanced-level professionals aiming to leverage Agentic AI for enterprise-scale automation and strategic AI adoption.

Upon completion of this training, participants will be able to:

• Understand the role of Agentic AI in enterprise applications.
• Integrate autonomous AI agents with enterprise systems.
• Optimize AI-driven workflows for scalability and efficiency.
• Ensure compliance, security, and governance in AI automation.
• Develop AI-driven business strategies for digital transformation.

This practical training in Belgrade leads data professionals through the process of implementing WrenAI Cloud, linking varied data sources, and structuring data for analytical purposes. Learners will gain the skills to transform raw information and construct interactive dashboards that provide practical, actionable business insights.

Ova obuka, vođena od strane instruktora, u Belgrade (online ili na licu mesta), namenjena je profesionalcima naprednog nivoa koji žele da iskoriste agentsku veštačku inteligenciju za donošjenje odluka u složenim poslovnim i tehničkim scenarijima.

Nakon završetka ove obuke, učesnici će moći da:

• Razumeju principe autonomog donošjenja odluka u veštačkoj inteligenciji.
• Dizajniraju i implementiraju agense veštačke inteligencije koji rade uz minimalno ljudsko mešanje.
• Integriraju agentsku veštačku inteligenciju u automatizovane tokove posla i poslovne sisteme.
• Optimizuju procese donošjenja odlaka na bazi veštačke inteligencije radi efikasnosti i skalabilnosti.
• Obezbeđuju usklađenost, bezbednost i etičke aspekte u autonomiji veštačke inteligencije.

In Belgrade, acquire the skills to construct robust semantic layers and refine text-to-SQL workflows using WrenAI OSS. Designed for advanced data and ML engineers, this course addresses prompt optimization, the deployment of safety controls, and the seamless embedding of these tools into pipelines and analytical workflows to ensure consistent performance.

This instructor-led, live training in Belgrade (online or onsite) targets AI engineers, machine learning researchers, and developers at an intermediate level who wish to construct and deploy Agentic AI systems for real-world use cases.

Upon completing this training, participants will be equipped to:

• Grasp the fundamental principles underlying Agentic AI systems.
• Develop AI agents capable of autonomous reasoning and execution.
• Connect Agentic AI with APIs and external service providers.
• Optimize interactions among multiple agents for handling complex tasks.
• Tackle ethical, security, and scalability issues inherent in Agentic AI.

This live session in Belgrade supports SaaS teams in integrating WrenAI's GenBI capabilities into their client-facing products through the Embedded API. You will master the configuration of white-label analytics, the design of secure multi-tenant architectures, and performance optimization strategies that ensure compliance in contemporary, scalable SaaS environments.

This instructor-led, live training in Belgrade (online or onsite) is designed for beginner-level professionals who want to grasp the fundamental principles of Agentic AI, its capabilities, and its potential impact on industries.

By the end of this training, participants will be able to:

• Understand the core principles of Agentic AI.
• Differentiate between traditional AI and autonomous AI agents.
• Explore real-world applications of Agentic AI in various industries.
• Assess the benefits and challenges of deploying autonomous AI systems.
• Analyze the ethical and security considerations of Agentic AI.

This instructor-led training in Belgrade provides product teams with the expertise to implement WrenAI for conversational analytics. Learners will master designing robust NL-to-SQL workflows, standardizing metrics, and integrating self-service BI dashboards directly into their routine product management activities.

This five-day course in Belgrade empowers finance professionals with skills in advanced analytics, AI-assisted Python, and agentic AI. Participants will learn to construct intelligent dashboards, optimize GL operations, and design autonomous workflows to enhance financial analysis, reporting, and strategic decision-making.

Ovaj jednodnevni kurs pruža softverskim inženjerima, tehničkim liderima i razvojnim timovima praktičan okvir za efikasno korišćenje AI kodirajućih agenata u realnim softverskim projektima. Umesto da se fokusira isključivo na tehnike promptovanja, kurs istražuje ekosistem agenata u celini, uključujući inženjering konteksta, ponovno upotrebljive tokove posla, integracije sa MCP-om (Model Context Protocol), petlje povratne informacije, bezbednost i organizacionu usvojenost.

AI agents are transitioning from research prototypes to autonomous production systems capable of operating across text, image, speech, and tool-driven workflows. This shift demands heightened engineering rigor, adversarial robustness, and regulatory accountability. Designed for advanced practitioners, this instructor-led training covers the complete agent lifecycle—from architecting single and multi-agent architectures to integrating multi-modal perception and orchestrating coordinated behaviors via modern frameworks. Through progressively complex Python labs, participants construct a production-grade multi-agent system, which they then stress-test using adversarial techniques and the Adversarial Robustness Toolbox. The curriculum concludes with alignment to NIST AI RMF, ISO/IEC 42001, EU AI Act, and GDPR standards, alongside secure deployment, monitoring, and incident response strategies, ensuring participants can deliver agents that are capable, defensible, and compliant.

This live, instructor-led session in Belgrade (online or onsite) is designed for beginner to intermediate developers and cloud practitioners who aim to utilize Alibaba Cloud for building AI agents that can automate tasks, answer queries, and interface with business systems.

By the conclusion of this training, participants will be able to understand the architecture of AI agents on Alibaba Cloud, construct a basic agent workflow, link an agent to enterprise knowledge bases and tools, and deploy and monitor the agent within a cloud environment.

This live, instructor-led training in Belgrade is tailored for intermediate-level developers seeking to design, build, and test AI agents utilizing the Claude API and the Agent SDK.

Upon completion, participants will be equipped to:

• Invoke the Messages API utilizing system prompts, structured outputs, and streaming capabilities
• Configure tools and execute a robust tool-use cycle
• Integrate agents with external systems via MCP servers
• Construct and operate agents using the Claude Agent SDK, incorporating permission management and subagents
• Optimize costs and latency through prompt caching and effective context management
• Evaluate, record, and monitor agent performance using a concise evaluation dataset

Claude Cowork preuzima celokupne zadatke, poput istraživanja, pripreme dokumenata i rada sa fajlovima, umesto da odgovara na jedan prompt odjednom. Ovaj kurs uči kako da se sastave kvalitetne zadatke, kako da se proverava plan i kako da se pregledaju rezultati. Učešnici preuzmu tri stvarna zadatka i podesavaju zadatka sa rasporedom izvođenja.

Ova obuka sa predavačem uživo u Belgrade namenjena je: radnicima znanja, asistentima, vodjama projekata i odeljenja koji žele da poveruju ceo zadatak Claude-u, umesto da komuniciraju korak po korak.

Na kraju ove obuke, učesnici će biti u mogućnosti da:

• razumeju razliku između dijaloga i delegiranog rada u Cowork-u
• sastave zadatke sa jasnim ciljem, materijalima, ograničenjima i kriterijumima za prihvatanje
• izrađuju dokumente, elektronske tabele i prezentacije iz određene mape
• delegiraju istraživanje od postavljanja pitanja do završenog izveštaja
• koriste pluginove, veštine i konektore u Cowork-u
• definišu tačke odobravanja, rezervne kopije i bezbedan pristup mapama

Format kursa

• Trajanje: 1 dan (7 sati)
• Interaktivna obuka sa trenerom, diskusija i praktične vežbe na osnovu sopstvenih slučajeva upotrebe učesnika
• Rezultat, 1. dan: Svaki učesnik je poverio tri stvarna zadatka Cowork-u, pregledao rezultate i podesio zadatak sa rasporedom izvođenja.

Opcije prilagođavanja kursa

• Da biste zatražili prilagođenu obuku za ovaj kurs, molimo vas da se javite nama radi koordinacije.

Agenti omogućavaju timovima da na kontrolisan način odgovaraju na pitanja iz oblasti znanja i podržavaju procese dokumenata. Ovaj dvodnevni kurs obuhvata Agent Builder prvog dana i Copilot Studio sa koracima odobravanja i testnim slučajevima drugog dana. Polaznici odlaze sa testiranim agentom znanja i nacrtom za Studio agenta.

Ova obuka koju vodi trener, uživo Belgrade, namenjena je: Ključnim korisnicima, AI šampionima i vodijama odeljenja koji žele da izgrade sopstvene Copilot agente za pitanja iz oblasti znanja i procese dokumenata.

Na kraju ove obuke, polaznici će moći da:

• Odrede kada je Copilot Chat dovoljan, a kada agent ima smisla
• Izgrade agenta znanja u Agent Builder-u sa publikom, izvorima znanja i ograničenjima
• Razumeju strukturu agenta u Copilot Studio i kreiraju prvi agent
• Razgrade procese dokumenata na pregledne korake sa ljudskim odobravanjem
• Testiraju agente pomoću testnih slučajeva i kriterijuma prihvatanja
• klasifikuju uloge, dozvole, licence i operacije

Format kursa

• Trajanje: 2 dana (po 7 sati)
• Interaktivna obuka sa trenerom, diskusije i praktične vežbe na osnovu sopstvenih slučajeva upotrebe polaznika
• Rezultat, 1. dan: Svaki polaznik ima testiranog agenta znanja i mapu alata za sopstvene radne slučajeve.
• Rezultat, 2. dan: Svaki polaznik ima nacrt Studio agenta sa odobravanjem, dva testirana procesna slučaja i mapu puta za sopstvene slučajeve upotrebe.

Opcije prilagođavanja kursa

• Zahtev za prilagođenu obuku za ovaj kurs, molimo kontaktirajte nas za koordinaciju.

An AI assistant integrated with corporate documentation can effectively answer questions about policies, manuals, and processes while accurately citing the source material. This course walks through the process of document preparation, platform selection, codeless agent construction, and performance measurement via a question catalog. Participants will also develop a maintenance plan.

This live, instructor-led training in Belgrade is designed for teams, knowledge owners, and key users who wish to provide answers derived from their own documents, policies, and manuals.

By the conclusion of this training, participants will be able to:

• Understand how AI generates answers from documents (a simple explanation of RAG) and recognize its limitations
• Prepare documents to ensure the accuracy of AI responses
• Select the appropriate platform for a knowledge agent
• Build and share a knowledge agent without writing code
• Verify answers using a question catalog and source references
• Define operational maintenance, roles, and content currency

Course Format

• Duration: 1 day (7 hours)
• Interactive training involving a trainer, discussions, and hands-on exercises focused on participants' own use cases
• Outcome, Day 1: Each participant will have a shared knowledge agent based on their documents, a measured hit rate, and a maintenance plan.

Course Customization Options

• To request a customized training for this course, please contact us to make arrangements.

Langdock integriše više AI modela, asistenata, znanje preduzeća i tokove poslovanja u jednu platformu za kompaniju. Ovaj kurs pokriva svakodnevnu upotrebu u četu, izgradnju i deljenje asistenata, povezivanje izvora znanja i postavljanje toka poslovanja sa ljudskim odobrenjem. Takođe, obrađuju se pravila za podatke, uloge i uvodjenje.

Ova uživo obuka sa trenerom u Belgrade namenjena je: Odjelima i ključnim korisnicima u kompanijama koje koriste ili uvode Langdock kao centralnu AI platformu.

Nakon završetka ove obuke, učesnici će moći da:

• Poverljivo upravljaju Langdockom, uključujući čet, modele, asistente, znanje i tokove poslovanja
• Izaberu prikladni model za svaku zadatak
• Gradite asistente sa uputstvima i znanjem kompanije i delite ih u timu
• Povežete SharePoint, OneDrive i druge izvore kao bazu znanja
• Podesite jednostavan tok poslovanja sa ljudskim odobrenjem
• Definišete pravila za podatke, uloge i odobrenja u kompaniji

Format kursa

• Trajanje: 2 dana (po 7 sati), dostupno i kao 4 poludana online
• Interaktivna obuka sa trenerom, diskusija i praktične vežbe na sopstvenim slučajevima učesnika
• Rezultat, Dan 1: Svaki učesnik ima šablon, mapu znanja i deljeni asistent za sopstveno područje.
• Rezultat, Dan 2: Svaki učesnik ima funkcionalan tok poslovanja sa odobrenjem, povezan izvor znanja i plan za naredna 30 do 60 dana.

Opcije prilagodbe kursa

• Zahtev za prilagođenu obuku za ovaj kurs, molimo kontaktirajte nas kako bismo dogovorili.

This live, instructor-led training in Belgrade (online or onsite) is designed for professionals from beginner to intermediate levels aiming to automate a real-world process and build their first AI agent using Make in one day.

By the conclusion of this training, participants will be able to:

• Create Make scenarios linked to common business applications.
• Incorporate AI models and initial agents into scenarios.
• Execute scenarios with robust error handling and monitoring capabilities.

Ova obuka koja se odvija uživo uz instruktora u Belgrade (online ili na lokaciji klijenta) namenjena je poslovnim stručnjacima srednjeg nivoa koji žele da grade automatizovane radne tokove i AI agente u n8n-u bez pisanja koda.

Krajem ove obuke, učesnici će biti u mogućnosti da:

• Kreiraju n8n radne tokove povezane sa svakodnevnim poslovnim aplikacijama.
• Dodaju AI modele i agente koji rade na podacima kompanije.
• Izvršavaju radne tokove u svakodnevnim operacijama uz obradu grešaka, odobrenja i praćenje.

Ova trener-vodjena, uživo obuka u Belgrade namenjena je profesionalima srednjeg nivoa koji žele da automatizuju poslovne procese i izgrade svog prvog AI agenta koristeći Make.

Krajem ove obuke, učesnici će moći da:

• Dizajniraju no-code radne tokove u Make-u koristeći okidače i webhooke.
• Povežu AI agenta sa svojim podacima unutar toka.
• Automatizuju stvarni proces od početka do kraja, uključujući obradu grešaka i praćenje.

A personal AI agent can streamline email sorting, schedule appointments, prepare briefings, and execute routines like a morning overview. This one-day course illustrates how to configure the agent with a personal context, connectors, and explicit rules for approval and data protection. Participants will leave with a functional agent and two established routines.

This instructor-led, live training in Belgrade is designed for professionals, assistants, project managers, and self-employed individuals who wish to implement a personal AI agent for their work.

By the end of the session, participants will be able to:

• Understand the capabilities and limitations of a personal AI agent
• Build a personal context using profiles, instructions, and notes
• Organize email and calendar tasks with AI while maintaining control
• Prepare for appointments and conversations via automatic briefings
• Create routines, such as a morning overview and weekly review
• Set approvals, data protection standards, and limits for the agent

Course Format

• Duration: 1 day (7 hours)
• Interactive training with an instructor, including discussions and hands-on exercises based on participants' own use cases
• Day 1 Outcome: Each participant will have a set-up personal agent with a profile, connected mailbox and calendar, and two running routines.

Customization Options

• To request customized training for this course, please contact us.

This instructor-led, live training in Belgrade targets managers, assistants, and knowledge workers.

Upon completing this training, participants will be able to:

• Organize email and calendar activities with AI assistance
• Conduct meeting preparation and research more efficiently
• Establish a personal assistant aligned with specific preferences
• Ensure the protection of personal and company data