Tech Station

From prompt to production.

Five technical tracks covering the skills engineers and architects need to build LLM-powered systems that actually work in production — not just in demos.

5 technical tracks·Ordered by recommended learning path
01 — Start here
AI Primer

The concepts every LLM practitioner needs before writing a single prompt.

19 guides
02 — Core skill
Prompt Engineering

Zero-shot to few-shot, chain-of-thought, and structured output patterns.

13 guides
03 — Architecture
RAG

Chunking, embeddings, vector search, and fixing hallucinations in production.

13 guides
04 — LLMOps
LLM Fine-Tuning & LLMOps

When to fine-tune vs. prompt, LoRA, QLoRA, evaluation, and deployment.

13 guides
05 — Advanced
Agentic AI

Planning loops, tool use, memory, and multi-agent coordination.

14 guides

Recommended reading paths

Curated sequences that weave across the five tech tracks — pick the outcome you're building toward.
Path 01

Ship a RAG Product for Your Own Data

The complete path for a production RAG feature — foundations, retrieval quality, prompt structure, evaluation, and monitoring.

  1. 01What Is RAG & Why It MattersRAG-01·6 min
  2. 02Word Embeddings & Vector SpaceAIP-06·5 min
  3. 03Chunking Strategies That Make or Break RAGRAG-04·6 min
  4. 04Building Your First RAG Pipeline (Concept)RAG-05·6 min
  5. 05Structured Output: Reliable JSON Every TimePE-07·4 min
  6. 06Re-Ranking: The Biggest Quality LeverRAG-08·6 min
  7. 07Why Your RAG Pipeline Keeps HallucinatingRAG-07·7 min
  8. 08Evaluating RAG SystemsRAG-12·7 min
  9. 09RAG in Production: Cost, Latency & MonitoringRAG-13·8 min
9 guides · 55 min end-to-endStart path →
Path 02

Decide Between Prompting, RAG, and Fine-Tuning

The architectural decision, done properly — cost, quality, maintenance, and the model context that decides the answer.

  1. 01Fine-Tuning vs RAG vs PromptingFT-01·8 min
  2. 02Why LLMs HallucinateAIP-18·6 min
  3. 03Context Windows & Tokens in PracticeAIP-17·5 min
  4. 04The 7 Prompt Patterns That Cover 90% of CasesPE-05·5 min
  5. 05What Is RAG & Why It MattersRAG-01·6 min
  6. 06How Fine-Tuning WorksFT-02·6 min
  7. 07Full Fine-Tuning vs LoRA & QLoRAFT-04·7 min
  8. 08Preparing a Fine-Tuning DatasetFT-03·7 min
  9. 09Evaluating a Fine-Tuned ModelFT-07·9 min
  10. 10Inference Economics: Tokens, Caching, Routing, DistillationBCR-06·9 min
10 guides · 68 min end-to-endStart path →
Path 03

Build an Agent That Ships to Production

From agent loop to observability, guardrails, and the governance stance production actually requires.

  1. 01What Is Agentic AI?AGT-01·9 min
  2. 02Inside the Agent LoopAGT-03·6 min
  3. 03Tool Use & Function CallingAGT-04·8 min
  4. 04Planning & Reasoning in AgentsAGT-06·9 min
  5. 05Building Your First AgentAGT-08·6 min
  6. 06Model Context Protocol (MCP)AGT-11·6 min
  7. 07Evaluating & Observing Agents in ProductionAGT-13·6 min
  8. 08Securing AI AgentsAGT-14·7 min
  9. 09Governing Agentic AI: New Risks When AI Takes ActionGOV-15·12 min
  10. 10Guardrails & Safety LayersFT-12·7 min
10 guides · 76 min end-to-endStart path →
Path 04

Cut Your LLM Cost & Latency

The prompt-side, serving-side, model-side, and vendor-side levers that move real cost and latency numbers.

  1. 01Context Windows & Tokens in PracticeAIP-17·5 min
  2. 02Inference Economics: Tokens, Caching, Routing, DistillationBCR-06·9 min
  3. 03Prompt Engineering in ProductionPE-13·5 min
  4. 04Cost Optimisation: Caching, Routing & Model SelectionFT-13·9 min
  5. 05Full Fine-Tuning vs LoRA & QLoRAFT-04·7 min
  6. 06RAG in Production: Cost, Latency & MonitoringRAG-13·8 min
  7. 07Monitoring LLMs: Cost, Latency, Drift & QualityFT-10·7 min
  8. 08Vendor Pricing Models and NegotiationBCR-14·10 min
8 guides · 60 min end-to-endStart path →

Latest technical guides

agentic aiSecuring AI Agents7 min · Subhraprompt engineeringPrompt Engineering in Production5 min · Subhraai primerCapabilities, Limits & Where This Is Heading6 min · SubhraragRAG in Production: Cost, Latency & Monitoring8 min · Subhrallm fine tuningCost Optimisation: Caching, Routing & Model Selection9 min · Subhra