Role
Topic
Skill Level
Duration
- Architect
- Decision Maker
- Developer
- Security & Ops
- Architecture
- Data Modeling
- Gen AI
- Performance at Scale
- Query
- Aggregation
- Security
- Indexes
- Sharding
- Monitoring, Tuning, and Automation
- Search
- Foundational
- Intermediate
- Advanced
- < 60 minutes
- 60 minutes
- 75 minutes
- 90 minutes
Evaluating an Agentic Platform
How to evaluate whether an agentic AI platform can support secure, reliable production workloads. Use governance, security, observability, data architecture, scalability, and cost criteria to assess platform readiness and long-term flexibility.
Observability for AI Agents
How to instrument and observe production AI applications and agents, interpret runtime signals, debug silent failures, and build trust in systems that retrieve context, call tools, and execute multi step workflows.
Governance for AI Agents
How to establish guardrails for AI applications and agents, define policies for data access and tool use, manage risk across multi-step workflows, and build trust through transparent, compliant, and accountable systems.
Building an App with Code Agents and MongoDB
How to use MongoDB Agent Skills and the MongoDB MCP Server to build applications.
Retrieval Evaluation
How to evaluate embedding models for retrieval tasks. Master key metrics like NDCG@k, Recall@k, and MRR, work with golden datasets and benchmarks, and make confident model selection decisions.
Vector Search Performance
How to tune MongoDB vector search for production workloads, size indexes to fit RAM, choose between search nodes and coupled deployments, use sharding to scale, and apply filtering, quantization, and multi-tenancy to optimize performance and cost.
Memory for AI Applications with MongoDB
How to design and implement short- and long-term memory for AI applications using MongoDB, LangGraph, and Atlas Vector Search.