Catalog · Nexora

Agentic AI intermediate

RAG Systems in Production

The gap between a RAG demo and a RAG product is chunking strategy, retrieval evaluation and latency budgets. Covers document parsing, chunk boundary design, hybrid retrieval, cross-encoder re-ranking, and caching layers that keep p95 sane.

DO Daniel Okafor 4.9

$89.00

13 hours

→

Agentic AI

Agentic AI intermediate

Building Production Agents with LangGraph

Design agents as explicit state machines instead of prompt spaghetti. You will build a typed graph with conditional edges, add checkpointing so runs are replayable, implement retry and refinement loops, and ship an agent that degrades gracefully when a model call fails. Ends with a production deployment that handles concurrency, idempotency and observability.

PR Priya Raghavan 4.9

$89.00

14 hours

→

Agentic AI

Agentic AI advanced

Evaluation-Driven LLM Development

Shipping an LLM feature without an eval suite is shipping a rumour. Build golden datasets from production traffic, write graders that correlate with human judgement, and wire regression gates into CI so a prompt change cannot quietly degrade quality.

MA Marta Alves 4.8

$99.00

12 hours

→

Agentic AI

Agentic AI intermediate

Agentic RAG: Retrieval That Reasons

Naive RAG retrieves once and hopes. Agentic RAG grades what it retrieved, rewrites the query when results are thin, and decides when it has enough context. Covers relevance grading, query rewriting loops, hybrid dense plus keyword retrieval, reciprocal rank fusion and LLM-as-judge re-ranking, with honest evaluation of when each technique actually helps.

DO Daniel Okafor 4.8

$79.00

10 hours

→

Agentic AI

Agentic AI advanced

Multi-Agent Systems: Coordination Patterns

When one agent is not enough: supervisor architectures, hierarchical delegation, shared scratchpads and message-passing protocols. You will implement a research team that plans, splits work, critiques its own output and reconciles conflicting findings, then measure whether the added complexity beat a single well-prompted agent.

PR Priya Raghavan 4.7

$129.00

16 hours

→

Agentic AI

Agentic AI intermediate

LLM Observability with LangSmith

You cannot debug what you cannot see. Instrument agent runs with distributed tracing, attach custom metadata and tags so runs are filterable, build evaluation datasets from production traffic, and set up regression tests that catch quality drops before users do. Includes selective tracing so your traces stay signal, not noise.

MA Marta Alves 4.6

$59.00

6 hours

→

Agentic AI

Agentic AI beginner

Prompt Engineering for Structured Output

Getting reliable JSON out of a language model is an engineering problem, not a prompting trick. Schema-first prompt design, defensive parsing, repair loops, grammar constraints and validation with Pydantic. You will build a pipeline that survives the model wrapping its answer in prose or a code fence.

MA Marta Alves 4.5

$39.00

5 hours

→