RAG tutorials
From first index to hybrid retrieval with evals — working code throughout.
Learn
Tutorials
Hands-on walkthroughs for RAG, agents, evaluation, and cloud deployment patterns.
- 20+hands-on tutorials
- 4tracks from RAG to deploys
- 100%runnable, tested code
The tutorials
What you'll build
Technical tutorials and deep dives for building production AI systems.
Agent patterns
Tool-calling, memory and multi-agent coordination built step by step.
Eval harnesses
Golden sets, LLM judges and CI gates wired up from scratch.
Cloud deploys
Shipping AI workloads to production infrastructure properly.
What's inside
Learn by shipping something real
Each tutorial ends with working software and the understanding to modify it — not a copy-pasted demo you can't extend.
Foundations track
RAG done properly, from zero
Ingestion, chunking, hybrid search, reranking and grounded generation — built incrementally with an eval harness from step one, so you see every improvement measured.
- Working pipeline at every checkpoint
- Eval scores tracked across the tutorial
- The production gaps flagged explicitly
Ingest→
Chunk→
Embed→
Index→
Retrieve
PDFConfluenceSharePointSQLTicketsEmail
Grounded answer…with citations [1] [2] and permissions applied
Agents track
From tool call to multi-agent system
A progression: single tool-calling agent, then memory, then guardrails, then a supervisor topology — each step motivated by a failure of the previous one.
- MCP tool integration hands-on
- State and approval-gate patterns
- When multi-agent earns its complexity
Shared stateHandoffsRetriesTraces
Production track
The parts demos skip
Tracing, cost attribution, CI eval gates and cloud deployment — the operational tutorials that turn a working prototype into something you'd put your name on.
- Observability wired in, not on
- Eval gates in a real CI pipeline
- Deploy patterns with rollback
Invoice exception workflowRunning
✓Extract invoice fields1.1s
✓Match against PO0.6s
Resolve mismatch with agentrunning
·Post to ERPqueued
Who it's for
Built for builders
Engineers new to AI
The foundations track, in order.
Teams standardizing
Shared patterns for onboarding.
Prototype graduates
The production track, urgently.
Eval skeptics
The harness tutorial converts.
Students and switchers
Portfolio projects with substance.
Architects
Hands-on grounding for design authority.
Delivery
Learn, then apply
Practical guides and tools from teams who ship production AI — so your next decision is grounded in real delivery experience.
- Actionable playbooks
- Architecture blueprints
- Cost & ROI frameworks
- Security checklists
-
1
Assess
Understand readiness, risks and opportunities.
-
2
Learn
Use playbooks, guides and architecture patterns.
-
3
Decide
Prioritize the right build path.
-
4
Execute
Partner with Skugal to ship confidently.
FAQ
Common questions
What stack do the tutorials use?
Python and TypeScript with mainstream tooling — patterns transfer across providers, and vendor-specific steps are marked.
Are they kept current?
Tested against current APIs quarterly; breaking changes get fixed or flagged.
Free?
Yes — tutorials are unashamedly how teams discover they like working with us.
Next step
Start building
Pick a track — working software by the end of the session.