--- title: I'm new to all this. Where do I start? — The Agentic AI Hub | daily.dev description: Five chapters that get you fluent: how models actually work, the core vocabulary, prompting, and where the risks live. canonical: https://daily.dev/agentic-ai-hub/paths/where-do-i-start/ og:type: website og:url: https://daily.dev/agentic-ai-hub/paths/where-do-i-start/ og:title: I'm new to all this. Where do I start? — The Agentic AI Hub | daily.dev og:description: Five chapters that get you fluent: how models actually work, the core vocabulary, prompting, and where the risks live. og:image: https://daily.dev/assets/og/agentic-ai-hub.png?v=40e6ff69 og:site_name: daily.dev og:locale: en_US twitter:card: summary_large_image twitter:site: @dailydotdev twitter:creator: @dailydotdev twitter:title: I'm new to all this. Where do I start? — The Agentic AI Hub | daily.dev twitter:description: Five chapters that get you fluent: how models actually work, the core vocabulary, prompting, and where the risks live. twitter:image: https://daily.dev/assets/og/agentic-ai-hub.png?v=40e6ff69 --- [Skip to main content ](#main-content) # I'm new to all this. Where do I start? Five chapters that get you fluent: how models actually work, the core vocabulary, prompting, and where the risks live. [Start reading → ](/agentic-ai-hub/how-llms-actually-work/?path=where-do-i-start&i=0) [Check yourself first ↓ ](#quiz) 1. [ 1 How LLMs Actually Work A large language model predicts the next token given the tokens so far, and that is essentially all it does. › ](/agentic-ai-hub/how-llms-actually-work/?path=where-do-i-start&i=0) 2. [ 2 Core Concepts Quick definitions for the vocabulary you'll run into everywhere. Each one is short, and several get a fuller treatment later in the handbook. › ](/agentic-ai-hub/core-concepts/?path=where-do-i-start&i=1) 3. [ 3 Prompting & Context Engineering Prompting is the highest-leverage, lowest-cost skill in this whole handbook. Small changes in how you frame a request move quality more than most people expect. › ](/agentic-ai-hub/prompting-context-engineering/?path=where-do-i-start&i=2) 4. [ 4 Chat Assistants & Apps The consumer/prosumer chat apps are the front door to each lab's frontier model. › ](/agentic-ai-hub/chat-assistants-apps/?path=where-do-i-start&i=3) 5. [ 5 Safety, Alignment & Governance Building with AI means owning its failure modes. This section is deliberately neutral and tight, enough to reason about risk without ideology. › ](/agentic-ai-hub/safety-alignment-governance/?path=where-do-i-start&i=4) ## Check yourself. One question per step. Take it cold to find where to start, or after reading to see what stuck. Nobody's grading you. Best so far: Question 1 of 5 1. Step 1 Why can a chat model reference something you said earlier in the same conversation? A Its weights were updated by your messages B The interface re-sends the full transcript in context each turn C It stores your chats in persistent internal memory D It retrieves old messages from the provider's servers Weights are frozen at inference and the model is stateless between calls. It only "knows" the conversation because the accumulated transcript sits in the context window, re-read on every turn. [Covered in step 1 · How LLMs Actually Work → ](/agentic-ai-hub/how-llms-actually-work/?path=where-do-i-start&i=0) Next question → 2. Step 2 In a Mixture-of-Experts model, what mainly drives per-token inference cost and speed? A Total parameter count B Context window length C Active parameters used per forward pass D The size of the training corpus MoE decouples total capacity from per-token compute: only a subset of experts activates per token, so active parameters are what you actually pay for at inference. [Covered in step 2 · Core Concepts → ](/agentic-ai-hub/core-concepts/?path=where-do-i-start&i=1) Next question → 3. Step 3 The model almost does what you want, but the output format keeps drifting. Fastest fix? A Show two or three input→output examples B Describe the desired format in more detail C Switch to a larger model D Lower the temperature to zero Few-shot examples anchor format and style far more reliably than describing them in words. If you're writing paragraphs about the output shape, show examples instead. [Covered in step 3 · Prompting & Context Engineering → ](/agentic-ai-hub/prompting-context-engineering/?path=where-do-i-start&i=2) Next question → 4. Step 4 The chat apps are converging in quality. How should you pick one in 2026? A The largest context window wins B Benchmark deltas, since raw IQ differs most C Always the cheapest paid tier D Ecosystem fit and surface features like connectors and agent modes The assistants now differ less in raw intelligence than in surface features and ecosystem lock-in (docs, cloud, IDE), so those should drive the choice, not benchmark gaps. [Covered in step 4 · Chat Assistants & Apps → ](/agentic-ai-hub/chat-assistants-apps/?path=where-do-i-start&i=3) Next question → 5. Step 5 Why is prompt injection the top security risk for agents that read untrusted content? A Models can't reliably tell trusted instructions from untrusted data in context B Untrusted content can permanently corrupt the model's weights C It only affects models that skipped RLHF training D Attackers need direct access to your system prompt To the model, everything in the window is just tokens, so instructions hidden in a web page or email can be followed as if they came from you. That's why OWASP ranks it the number-one LLM risk. [Covered in step 5 · Safety, Alignment & Governance → ](/agentic-ai-hub/safety-alignment-governance/?path=where-do-i-start&i=4) See results → of 5 * [ 1 How LLMs Actually Work → ](/agentic-ai-hub/how-llms-actually-work/?path=where-do-i-start&i=0) * [ 2 Core Concepts → ](/agentic-ai-hub/core-concepts/?path=where-do-i-start&i=1) * [ 3 Prompting & Context Engineering → ](/agentic-ai-hub/prompting-context-engineering/?path=where-do-i-start&i=2) * [ 4 Chat Assistants & Apps → ](/agentic-ai-hub/chat-assistants-apps/?path=where-do-i-start&i=3) * [ 5 Safety, Alignment & Governance → ](/agentic-ai-hub/safety-alignment-governance/?path=where-do-i-start&i=4) Try again [Where to next → ](#path-next-title) ## Where to next. More guided paths through the handbook. Pick the next question worth answering. [ Which model should I actually use? → ](/agentic-ai-hub/paths/which-model/)[ How do I build my own agent? → ](/agentic-ai-hub/paths/build-your-own-agent/)[ Can I trust what agents produce? → ](/agentic-ai-hub/paths/trust-agent-output/) [All reading paths → ](/agentic-ai-hub/#paths-start-here) [Browse every chapter ](/agentic-ai-hub/#pages) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/og-image.png?v=a830cdf1","width":1200,"height":630},"sameAs":["https://twitter.com/dailydotdev","https://www.linkedin.com/company/dailydotdev","https://github.com/dailydotdev","https://www.instagram.com/dailydotdev"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","description":"Free, personalized developer news aggregator. Stay on top of software development news, AI coding tools, and web dev - curated daily from trusted sources.","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}},{"@type":"WebPage","@id":"https://daily.dev/agentic-ai-hub/paths/where-do-i-start/","url":"https://daily.dev/agentic-ai-hub/paths/where-do-i-start/","name":"I'm new to all this. Where do I start? | The Agentic AI Hub","description":"Five chapters that get you fluent: how models actually work, the core vocabulary, prompting, and where the risks live.","inLanguage":"en-US","isPartOf":{"@id":"https://daily.dev/#website"}},{"@type":"ItemList","numberOfItems":5,"itemListElement":[{"@type":"ListItem","position":1,"url":"https://daily.dev/agentic-ai-hub/how-llms-actually-work/","name":"How LLMs Actually Work"},{"@type":"ListItem","position":2,"url":"https://daily.dev/agentic-ai-hub/core-concepts/","name":"Core Concepts"},{"@type":"ListItem","position":3,"url":"https://daily.dev/agentic-ai-hub/prompting-context-engineering/","name":"Prompting & Context Engineering"},{"@type":"ListItem","position":4,"url":"https://daily.dev/agentic-ai-hub/chat-assistants-apps/","name":"Chat Assistants & Apps"},{"@type":"ListItem","position":5,"url":"https://daily.dev/agentic-ai-hub/safety-alignment-governance/","name":"Safety, Alignment & Governance"}],"@id":"https://daily.dev/agentic-ai-hub/paths/where-do-i-start/#steps"},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev/"},{"@type":"ListItem","position":2,"name":"The Agentic AI Hub","item":"https://daily.dev/agentic-ai-hub/"},{"@type":"ListItem","position":3,"name":"New to AI?","item":"https://daily.dev/agentic-ai-hub/#paths-start-here"},{"@type":"ListItem","position":4,"name":"I'm new to all this. Where do I start?","item":"https://daily.dev/agentic-ai-hub/paths/where-do-i-start/"}]}]} ```