Благодарим ви, че изпратихте вашето запитване! Един от членовете на нашия екип ще се свърже с вас скоро.
Благодарим ви, че направихте своята резервация! Един от членовете на нашия екип ще се свърже с вас скоро.
План на курса
Foundations of Secure Local AI
- What local and on-prem AI mean in regulated environments
- Cloud AI versus internal deployment for sensitive workloads
- Common enterprise use cases for private assistants and workflow support
- Core components of a secure local AI architecture
Ollama and Open Model Basics
- How Ollama fits into a local development stack
- Pulling, running, and managing models locally
- Choosing models based on size, quality, hardware, and license
- Matching model options to practical business tasks
Preparing the On-Prem Environment
- Host, workstation, and server preparation
- Installing and configuring Ollama for local inference
- Using containers and internal development tooling
- Verifying API access and basic operational readiness
Working with Local Models Effectively
- Running prompts and shaping outputs with system instructions
- Reusing templates for consistent enterprise tasks
- Managing model versions and internal artifacts
- Basic performance tuning for CPU and GPU deployments
Building Practical Agentic Workflows
- What makes a workflow agentic in a controlled setting
- Simple patterns for planning, tool use, and response loops
- Designing task-focused assistants for internal operations
- Adding human review, fallback logic, and error handling
Private Retrieval Workflows
- Retrieval-augmented generation basics for internal knowledge access
- Preparing documents for chunking, indexing, and search
- Connecting a local vector store to an Ollama-based application
- Improving relevance and answer quality with better retrieval patterns
Security, Governance, and Compliance Practices
- Data handling boundaries and privacy considerations
- Access control, logging, and audit support
- Prompt safety, output controls, and guardrails
- Governance checkpoints for regulated deployment and operation
Enterprise Integration Patterns
- Exposing local AI capabilities through internal APIs
- Integrating assistants with internal applications and services
- Supporting assistant, batch, and workflow automation use cases
- Keeping solutions inside controlled network boundaries
Evaluating Local AI Solutions
- Assessing quality, reliability, and consistency
- Testing against business, policy, and safety requirements
- Comparing model options for specific enterprise tasks
- Establishing a practical improvement cycle for internal teams
Hands-On Implementation Lab
- Building a private assistant with Ollama and an open model
- Adding retrieval over approved internal documents
- Introducing simple agentic actions and safety controls
- Reviewing deployment, operations, and governance checkpoints
Adoption Planning and Next Steps
- Reviewing key design and deployment decisions
- Identifying common pitfalls in regulated AI projects
- Planning pilot use cases and stakeholder alignment
- Defining a roadmap for secure local AI adoption
Изисквания
- Basic understanding of AI concepts and software development
- Familiarity with command line tools, containers, or local development environments
- Basic scripting or programming experience
Audience
- Developers and technical teams building private AI solutions on internal infrastructure
- Security, compliance, and platform professionals supporting AI in regulated environments
- Technical leaders in finance, healthcare, government, and defense evaluating on-prem AI adoption
21 Часове
