VEL ORENDISVel Orendis

Agents with tools in production

Function calling to multi-agent systems, with safeguards and evaluation.

20 lessons, about 3.5 h. Anything you already know, you can prove and skip.

0 of 20 lessonsquests defended, 1 open now

Start with What the Model Cannot Know
  1. The request path and where time goesFoundations, 10 min
    Opens later
  2. Throughput, utilisation and queueingFoundations, 10 min
    Opens later
  3. APIs: resources, idempotency, paginationQueues and streams, 10 min
    Opens later
  4. Background jobs, retries and rate limitsQueues and streams, 10 min
    Opens later
  5. What the Model Cannot KnowWorking with LLMs, 8 min
    Open
  6. Calling a model: messages, tokens and costWorking with LLMs, 10 min
    Opens later
  7. Prompts that ground answersWorking with LLMs, 10 min
    Opens later
  8. Structured output and validationWorking with LLMs, 10 min
    Opens later
  9. The RAG pipelineSearch and RAG, 10 min
    Opens later
  10. Lexical search and BM25Search and RAG, 12 min
    Opens later
  11. Ground truth for searchRetrieval quality, 10 min
    Opens later
  12. Function callingAgents, 12 min
    Opens later
  13. The agent loop and its budgetsAgents, 12 min
    Opens later
  14. When not to use an agentAgents, 8 min
    Opens later
  15. MCP: tools over a protocolAgents, 12 min
    Opens later
  16. Multi-agent systems and orchestrationAgents, 12 min
    Opens later
  17. Safeguards: guardrails, injection, permissionsAgents, 12 min
    Opens later
  18. Evaluating agentsAgents, 12 min
    Opens later
  19. Offline and online evaluationEvaluation and monitoring, 8 min
    Opens later
  20. LLM as a judgeEvaluation and monitoring, 12 min
    Opens later