Cursuri de pregatire Building Secure and Responsible LLM Applications
LLM application security is the discipline of designing, building, and maintaining safe, trustworthy, and policy-compliant systems using large language models.
This instructor-led, live training (online or onsite) is aimed at intermediate-level to advanced-level AI developers, architects, and product managers who wish to identify and mitigate risks associated with LLM-powered applications, including prompt injection, data leakage, and unfiltered output, while incorporating security controls like input validation, human-in-the-loop oversight, and output guardrails.
By the end of this training, participants will be able to:
- Understand the core vulnerabilities of LLM-based systems.
- Apply secure design principles to LLM app architecture.
- Use tools such as Guardrails AI and LangChain for validation, filtering, and safety.
- Integrate techniques like sandboxing, red teaming, and human-in-the-loop review into production-grade pipelines.
Format of the Course
- Interactive lecture and discussion.
- Lots of exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Schița de curs
Overview of LLM Architecture and Attack Surface
- How LLMs are built, deployed, and accessed via APIs
- Key components in LLM app stacks (e.g., prompts, agents, memory, APIs)
- Where and how security issues arise in real-world use
Prompt Injection and Jailbreak Attacks
- What is prompt injection and why it’s dangerous
- Direct and indirect prompt injection scenarios
- Jailbreaking techniques to bypass safety filters
- Detection and mitigation strategies
Data Leakage and Privacy Risks
- Accidental data exposure through responses
- PII leaks and model memory misuse
- Designing privacy-conscious prompts and retrieval-augmented generation (RAG)
LLM Output Filtering and Guarding
- Using Guardrails AI for content filtering and validation
- Defining output schemas and constraints
- Monitoring and logging unsafe outputs
Human-in-the-Loop and Workflow Approaches
- Where and when to introduce human oversight
- Approval queues, scoring thresholds, fallback handling
- Trust calibration and role of explainability
Secure LLM App Design Patterns
- Least privilege and sandboxing for API calls and agents
- Rate limiting, throttling, and abuse detection
- Robust chaining with LangChain and prompt isolation
Compliance, Logging, and Governance
- Ensuring auditability of LLM outputs
- Maintaining traceability and prompt/version control
- Aligning with internal security policies and regulatory needs
Summary and Next Steps
Cerințe
- An understanding of large language models and prompt-based interfaces
- Experience building LLM applications using Python
- Familiarity with API integrations and cloud-based deployments
Audience
- AI developers
- Application and solution architects
- Technical product managers working with LLM tools
14 ore
Cursurile publice necesita 5+ participanti
Cursuri de pregatire Building Secure and Responsible LLM Applications - Booking
Cursuri de pregatire Building Secure and Responsible LLM Applications - Enquiry
Building Secure and Responsible LLM Applications - Cerere de consultanta
Cerere de consultanta
Upcoming Courses
Cursuri înrudite
Advanced LangGraph: Optimization, Debugging, and Monitoring Complex Graphs
35 oreLangGraph is a framework for building stateful, multi-actor LLM applications as composable graphs with persistent state and control over execution.
This instructor-led, live training (online or onsite) is aimed at advanced-level AI platform engineers, DevOps for AI, and ML architects who wish to optimize, debug, monitor, and operate production-grade LangGraph systems.
By the end of this training, participants will be able to:
- Design and optimize complex LangGraph topologies for speed, cost, and scalability.
- Engineer reliability with retries, timeouts, idempotency, and checkpoint-based recovery.
- Debug and trace graph executions, inspect state, and systematically reproduce production issues.
- Instrument graphs with logs, metrics, and traces, deploy to production, and monitor SLAs and costs.
Format of the Course
- Interactive lecture and discussion.
- Lots of exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Citește mai mult...
Advanced Ollama Model Debugging & Evaluation
35 oreAdvanced Ollama Model Debugging & Evaluation is an in-depth course focused on diagnosing, testing, and measuring model behavior when running local or private Ollama deployments.
This instructor-led, live training (online or onsite) is aimed at advanced-level AI engineers, ML Ops professionals, and QA practitioners who wish to ensure reliability, fidelity, and operational readiness of Ollama-based models in production.
By the end of this training, participants will be able to:
- Perform systematic debugging of Ollama-hosted models and reproduce failure modes reliably.
- Design and execute robust evaluation pipelines with quantitative and qualitative metrics.
- Implement observability (logs, traces, metrics) to monitor model health and drift.
- Automate testing, validation, and regression checks integrated into CI/CD pipelines.
Format of the Course
- Interactive lecture and discussion.
- Hands-on labs and debugging exercises using Ollama deployments.
- Case studies, group troubleshooting sessions, and automation workshops.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Citește mai mult...
Construirea de fluxuri de lucru AI private cu Ollama
14 oreAcest training cu instruire directă (online sau în mod prezențial) este destinat profesionistilor avansați care doresc să implementeze fluxuri de lucru bazate pe IA și sigure folosind Ollama.
La finalul acestui training, participanții vor putea:
- Instalați și configurați Ollama pentru procesarea AI privată.
- Integrați modelele IA în fluxuri de lucru enterprise sigure.
- Optimizați performanța AI menținând confidențialitatea datelor.
- Automatizați procesele de afaceri cu capacități AI locale.
- Asigurați conformitatea cu politiciile de securitate și guvernanță enterprise.
Citește mai mult...
Claude AI pentru Dezvoltatori: Construirea Aplicațiilor Potrivite de Inteligență Artificială
14 oreAceastă instruire live, cu instructor, în România (online sau la fața locului) se adresează dezvoltatorilor de software de nivel mediu și inginerilor AI care doresc să integreze Claude AI în aplicațiile lor, să construiască chatbots alimentați de AI și să îmbunătățească funcționalitatea software cu ajutorul automatizării bazate pe AI.
La sfârșitul acestui curs, participanții vor fi capabili să:
- Să utilizeze API-ul Claude AI pentru a integra inteligența artificială în aplicații.
- Să dezvolte chatbots și asistenți virtuali AI-driven.
- Să îmbunătățească aplicațiile cu ajutorul automatizării bazate pe AI și NLP.
- Să optimizeze și să ajusteze modelele Claude AI pentru diferite cazuri de utilizare.
Citește mai mult...
Claude AI pentru Automatizarea Fluxurilor de Lucru și Productivitate
14 oreAcest curs de formare live, condus de un instructor în România (online sau la fața locului) se adresează profesioniștilor de nivel începător care doresc să integreze Claude AI în fluxurile lor de lucru zilnice pentru a îmbunătăți eficiența și automatizarea.
Până la sfârșitul acestui training, participanții vor fi capabili să:
- Să utilizeze Claude AI pentru automatizarea sarcinilor repetitive și eficientizarea fluxurilor de lucru.
- Să îmbunătățească productivitatea personală și a echipei utilizând automatizarea bazată pe AI.
- Să integreze Claude AI cu instrumentele și platformele de afaceri existente.
- Să optimizeze luarea deciziilor și gestionarea sarcinilor bazate pe AI.
Citește mai mult...
Implementarea și Optimizarea LLM-urilor cu Ollama
14 oreAcest curs de formare live, condus de un instructor, în România (online sau la fața locului) se adresează profesioniștilor de nivel mediu care doresc să implementeze, să optimizeze și să integreze LLM-uri utilizând Ollama.
Până la sfârșitul acestei formări, participanții vor fi capabili să:
- Să configureze și să implementeze LLM-uri utilizând Ollama.
- Să optimizeze modelele AI pentru performanță și eficiență.
- Să utilizeze accelerarea GPU pentru îmbunătățirea vitezelor de inferență.
- Să integreze Ollama în fluxuri de lucru și aplicații.
- Monitorizarea și menținerea performanței modelelor AI în timp.
Citește mai mult...
Fine-Tuning și Personalizarea modelelor AI pe Ollama
14 oreAcest formator-guvernav, antrenament live în România (online sau pe locație) se adresează profesionistilor cu nivel avansat care doresc să îmbunătățească și să personalizeze modelele AI pe Ollama pentru o performanță mai bună și aplicații specific domeniu.
La sfârșitul acestui antrenament, participanții vor putea:
- Configura un mediu eficient pentru îmbunătățirea modelelor AI pe Ollama.
- Prepara seturi de date pentru îmbunătățirea supravegheată și învățarea prin recompense.
- Optimiza modelele AI pentru performanță, acuratețe și eficiență.
- Implementa modele personalizate în medii de producție.
- Evaluarea îmbunătățirilor modelului și asigurarea robustezii.
Citește mai mult...
Introducere în Claude AI: Conversational AI și Business Aplicații
14 oreAceastă instruire live, condusă de un instructor în România (online sau la fața locului) se adresează profesioniștilor din domeniul afacerilor de nivel începător, echipelor de asistență pentru clienți și pasionaților de tehnologie care doresc să înțeleagă elementele de bază ale Claude AI și să le valorifice pentru aplicații de afaceri.
Până la sfârșitul acestui curs, participanții vor fi capabili să:
- Să înțeleagă capacitățile și cazurile de utilizare ale Claude AI.
- Să configureze și să interacționeze eficient cu Claude AI.
- Să automatizeze fluxurile de lucru de afaceri cu ajutorul inteligenței artificiale conversaționale.
- Să îmbunătățească implicarea și asistența clienților utilizând soluții bazate pe AI.
Citește mai mult...
LangGraph Applications in Finance
35 oreLangGraph is a framework for building stateful, multi-actor LLM applications as composable graphs with persistent state and control over execution.
This instructor-led, live training (online or onsite) is aimed at intermediate-level to advanced-level professionals who wish to design, implement, and operate LangGraph-based finance solutions with proper governance, observability, and compliance.
By the end of this training, participants will be able to:
- Design finance-specific LangGraph workflows aligned to regulatory and audit requirements.
- Integrate financial data standards and ontologies into graph state and tooling.
- Implement reliability, safety, and human-in-the-loop controls for critical processes.
- Deploy, monitor, and optimize LangGraph systems for performance, cost, and SLAs.
Format of the Course
- Interactive lecture and discussion.
- Lots of exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Citește mai mult...
LangGraph Foundations: Graph-Based LLM Prompting and Chaining
14 oreLangGraph is a framework for building graph-structured LLM applications that support planning, branching, tool use, memory, and controllable execution.
This instructor-led, live training (online or onsite) is aimed at beginner-level developers, prompt engineers, and data practitioners who wish to design and build reliable, multi-step LLM workflows using LangGraph.
By the end of this training, participants will be able to:
- Explain core LangGraph concepts (nodes, edges, state) and when to use them.
- Build prompt chains that branch, call tools, and maintain memory.
- Integrate retrieval and external APIs into graph workflows.
- Test, debug, and evaluate LangGraph apps for reliability and safety.
Format of the Course
- Interactive lecture and facilitated discussion.
- Guided labs and code walkthroughs in a sandbox environment.
- Scenario-based exercises on design, testing, and evaluation.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Citește mai mult...
LangGraph in Healthcare: Workflow Orchestration for Regulated Environments
35 oreLangGraph enables stateful, multi-actor workflows powered by LLMs with precise control over execution paths and state persistence. In healthcare, these capabilities are crucial for compliance, interoperability, and building decision-support systems that align with medical workflows.
This instructor-led, live training (online or onsite) is aimed at intermediate-level to advanced-level professionals who wish to design, implement, and manage LangGraph-based healthcare solutions while addressing regulatory, ethical, and operational challenges.
By the end of this training, participants will be able to:
- Design healthcare-specific LangGraph workflows with compliance and auditability in mind.
- Integrate LangGraph applications with medical ontologies and standards (FHIR, SNOMED CT, ICD).
- Apply best practices for reliability, traceability, and explainability in sensitive environments.
- Deploy, monitor, and validate LangGraph applications in healthcare production settings.
Format of the Course
- Interactive lecture and discussion.
- Hands-on exercises with real-world case studies.
- Implementation practice in a live-lab environment.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Citește mai mult...
LangGraph for Legal Applications
35 oreLangGraph is a framework for building stateful, multi-actor LLM applications as composable graphs with persistent state and precise control over execution.
This instructor-led, live training (online or onsite) is aimed at intermediate-level to advanced-level professionals who wish to design, implement, and operate LangGraph-based legal solutions with the necessary compliance, traceability, and governance controls.
By the end of this training, participants will be able to:
- Design legal-specific LangGraph workflows that preserve auditability and compliance.
- Integrate legal ontologies and document standards into graph state and processing.
- Implement guardrails, human-in-the-loop approvals, and traceable decision paths.
- Deploy, monitor, and maintain LangGraph services in production with observability and cost controls.
Format of the Course
- Interactive lecture and discussion.
- Lots of exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Citește mai mult...
Building Dynamic Workflows with LangGraph and LLM Agents
14 oreLangGraph is a framework for composing graph-structured LLM workflows that support branching, tool use, memory, and controllable execution.
This instructor-led, live training (online or onsite) is aimed at intermediate-level engineers and product teams who wish to combine LangGraph’s graph logic with LLM agent loops to build dynamic, context-aware applications such as customer support agents, decision trees, and information retrieval systems.
By the end of this training, participants will be able to:
- Design graph-based workflows that coordinate LLM agents, tools, and memory.
- Implement conditional routing, retries, and fallbacks for robust execution.
- Integrate retrieval, APIs, and structured outputs into agent loops.
- Evaluate, monitor, and harden agent behavior for reliability and safety.
Format of the Course
- Interactive lecture and facilitated discussion.
- Guided labs and code walkthroughs in a sandbox environment.
- Scenario-based design exercises and peer reviews.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Citește mai mult...
LangGraph for Marketing Automation
14 oreLangGraph is a graph-based orchestration framework that enables conditional, multi-step LLM and tool workflows, ideal for automating and personalizing content pipelines.
This instructor-led, live training (online or onsite) is aimed at intermediate-level marketers, content strategists, and automation developers who wish to implement dynamic, branching email campaigns and content generation pipelines using LangGraph.
By the end of this training, participants will be able to:
- Design graph-structured content and email workflows with conditional logic.
- Integrate LLMs, APIs, and data sources for automated personalization.
- Manage state, memory, and context across multi-step campaigns.
- Evaluate, monitor, and optimize workflow performance and delivery outcomes.
Format of the Course
- Interactive lectures and group discussions.
- Hands-on labs implementing email workflows and content pipelines.
- Scenario-based exercises on personalization, segmentation, and branching logic.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Citește mai mult...
Noțiuni introductive cu Ollama: Rularea modelelor AI locale
7 oreAcest training în direcția instructorului (online sau la sediu) este destinat profesionistilor cu nivel de începător care doresc să instaleze, să configureze și să folosească Ollama pentru a rula modele AI locale pe mașinile lor.
La sfârșitul acestui training, participanții vor fi capabili să:
- Înțeleg fundamentele și capacitățile lui Ollama.
- Configurați Ollama pentru a rula modele AI locale.
- Implementați și interacționați cu modelele LLM folosind Ollama.
- Optimizați performanța și utilizarea resurselor pentru sarcini de AI.
- Explorați cazuri de utilizare ale dezvoltării locale AI în diferite industrii.
Citește mai mult...
