{"content":{"markdown":"From “what is an API?” to production architecture: five levels for everyone who wants to build with AI — no-code builders, developers and tech leads. The guides use the development tools in our comparison and the models in our LLM database as examples, with diagrams, tables and code where it helps.","text":"From “what is an API?” to production architecture: five levels for everyone who wants to build with AI — no-code builders, developers and tech leads. The guides use the development tools in our comparison and the models in our LLM database as examples, with diagrams, tables and code where it helps.\n","words":51},"date":"2026-10-14","description":"Learn to build with AI in five levels: from APIs and tokens to RAG, agents and production systems. Clear guides with diagrams and LLM data.","json":"https://abxk.ai/en/ai-development/learn/index.json","kind":"section","language":"en","learning_path":{"category":"ai-development","levels":5},"modified":"2026-10-14","pages":[{"description":"AI development means three things: using AI to write code, building apps on top of a model, and training models. Learn the roles and where to start.","json":"https://abxk.ai/en/ai-development/learn/what-is-ai-development/index.json","kind":"page","title":"What Is AI Development? Using AI vs. Building with AI","url":"https://abxk.ai/en/ai-development/learn/what-is-ai-development/"},{"description":"The seven parts of an AI app in plain words, from interface and backend to model, data, guardrails and logs, and one support-bot request from start to finish.","json":"https://abxk.ai/en/ai-development/learn/how-an-ai-app-works/index.json","kind":"page","title":"How an AI App Works: Model, Prompt, Data, Interface","url":"https://abxk.ai/en/ai-development/learn/how-an-ai-app-works/"},{"description":"How apps talk to language models: what APIs and API keys are, how text becomes tokens, what fits into a context window and why you pay per token.","json":"https://abxk.ai/en/ai-development/learn/apis-tokens-and-context-windows/index.json","kind":"page","title":"APIs, Tokens and Context Windows Explained","url":"https://abxk.ai/en/ai-development/learn/apis-tokens-and-context-windows/"},{"description":"Compare no-code, low-code and code for building AI apps: speed, control, cost of change, scaling and lock-in, with examples and clear signals for when to switch.","json":"https://abxk.ai/en/ai-development/learn/no-code-low-code-or-code/index.json","kind":"page","title":"No-Code, Low-Code or Code: Three Ways to Build with AI","url":"https://abxk.ai/en/ai-development/learn/no-code-low-code-or-code/"},{"description":"Autocomplete, chat and agents: what AI coding assistants do well, which mistakes they typically make, and why you still review every change.","json":"https://abxk.ai/en/ai-development/learn/what-ai-coding-assistants-do/index.json","kind":"page","title":"What AI Coding Assistants Do (and Where They Fail)","url":"https://abxk.ai/en/ai-development/learn/what-ai-coding-assistants-do/"},{"description":"Create an API key, keep it safe, send your first request to a language model, read the response and handle errors — step by step, with Python code.","json":"https://abxk.ai/en/ai-development/learn/your-first-llm-api-call/index.json","kind":"page","title":"Your First LLM API Call, Step by Step","url":"https://abxk.ai/en/ai-development/learn/your-first-llm-api-call/"},{"description":"How to write prompts that work reliably inside code: message roles, delimiters, examples, JSON output, temperature and versioning, with templates.","json":"https://abxk.ai/en/ai-development/learn/prompt-design-for-developers/index.json","kind":"page","title":"Prompt Design for Developers: System Prompts and Structure","url":"https://abxk.ai/en/ai-development/learn/prompt-design-for-developers/"},{"description":"Build an FAQ assistant on a no-code platform, step by step: a one-page brief, clean knowledge files, clear instructions, tests, sharing and upkeep.","json":"https://abxk.ai/en/ai-development/learn/build-a-simple-ai-app-without-code/index.json","kind":"page","title":"Build a Simple AI App Without Code","url":"https://abxk.ai/en/ai-development/learn/build-a-simple-ai-app-without-code/"},{"description":"How to pick a language model for your app: weigh quality, speed, cost, context and openness, then test a shortlist on your own data.","json":"https://abxk.ai/en/ai-development/learn/choose-a-model-for-your-app/index.json","kind":"page","title":"Choose a Model for Your App: Quality, Speed, Cost, Openness","url":"https://abxk.ai/en/ai-development/learn/choose-a-model-for-your-app/"},{"description":"Put a small AI app online safely: a static page plus one serverless function, the API key in an environment variable, rate limits, HTTPS, logs and cost control.","json":"https://abxk.ai/en/ai-development/learn/deploy-a-small-ai-web-app/index.json","kind":"page","title":"Deploy a Small AI Web App","url":"https://abxk.ai/en/ai-development/learn/deploy-a-small-ai-web-app/"},{"description":"How embeddings turn text into coordinates of meaning, how similarity search works and what a vector database adds: index, filters and chunks.","json":"https://abxk.ai/en/ai-development/learn/embeddings-and-vector-databases/index.json","kind":"page","title":"Embeddings and Vector Databases Explained","url":"https://abxk.ai/en/ai-development/learn/embeddings-and-vector-databases/"},{"description":"How RAG works from ingest to cited answer: chunk, embed, retrieve, rerank, generate and evaluate — plus common failures and when you do not need RAG.","json":"https://abxk.ai/en/ai-development/learn/retrieval-augmented-generation-step-by-step/index.json","kind":"page","title":"Retrieval-Augmented Generation (RAG), Step by Step","url":"https://abxk.ai/en/ai-development/learn/retrieval-augmented-generation-step-by-step/"},{"description":"Get reliable JSON from a language model and let it call your functions safely: schemas, validation, retries, tool descriptions and the checks you need.","json":"https://abxk.ai/en/ai-development/learn/structured-output-and-function-calling/index.json","kind":"page","title":"Structured Output and Function Calling","url":"https://abxk.ai/en/ai-development/learn/structured-output-and-function-calling/"},{"description":"Why unit tests are not enough for AI features: build an eval set, pick metrics from exact match to an AI judge, and catch regressions in CI.","json":"https://abxk.ai/en/ai-development/learn/test-ai-features-with-evals/index.json","kind":"page","title":"Test AI Features with Evals","url":"https://abxk.ai/en/ai-development/learn/test-ai-features-with-evals/"},{"description":"Plan, generate, review, test, commit: a workflow for AI-assisted coding with small diffs, tests first, secret and dependency checks and a review checklist.","json":"https://abxk.ai/en/ai-development/learn/ai-assisted-coding-workflow/index.json","kind":"page","title":"An AI-Assisted Coding Workflow That Stays Safe","url":"https://abxk.ai/en/ai-development/learn/ai-assisted-coding-workflow/"},{"description":"How an AI agent works inside: the plan-act-observe loop, tools, memory, stop rules and human approval, plus what METR data shows about agent autonomy.","json":"https://abxk.ai/en/ai-development/learn/build-ai-agents-tools-loops-memory/index.json","kind":"page","title":"Build AI Agents: Tools, Loops and Memory","url":"https://abxk.ai/en/ai-development/learn/build-ai-agents-tools-loops-memory/"},{"description":"How AI apps get web data responsibly: official APIs first, polite scraping, robots.txt, terms of service, GDPR, legitimate proxy use and change monitoring.","json":"https://abxk.ai/en/ai-development/learn/web-data-for-ai-apps/index.json","kind":"page","title":"Web Data for AI Apps: Scraping, APIs and the Rules","url":"https://abxk.ai/en/ai-development/learn/web-data-for-ai-apps/"},{"description":"When an AI project needs its own GPUs, how to estimate GPU memory from model size, and how to choose between on-demand, reserved, spot and serverless compute.","json":"https://abxk.ai/en/ai-development/learn/gpu-infrastructure-for-ai/index.json","kind":"page","title":"GPU Infrastructure for AI: When to Rent Compute","url":"https://abxk.ai/en/ai-development/learn/gpu-infrastructure-for-ai/"},{"description":"What prompting, RAG and fine-tuning each change, what data and upkeep they need, how to combine them — and a decision table with practical examples.","json":"https://abxk.ai/en/ai-development/learn/fine-tuning-vs-rag-vs-prompting/index.json","kind":"page","title":"Fine-Tuning vs. RAG vs. Prompting: A Decision Guide","url":"https://abxk.ai/en/ai-development/learn/fine-tuning-vs-rag-vs-prompting/"},{"description":"What to log for every LLM request, where privacy sets limits, how traces reveal multi-step chains, which numbers to alert on and how to catch quality drift.","json":"https://abxk.ai/en/ai-development/learn/observability-for-llm-apps/index.json","kind":"page","title":"Observability for LLM Apps: Logs, Traces, Costs, Quality","url":"https://abxk.ai/en/ai-development/learn/observability-for-llm-apps/"},{"description":"How LLM apps stay fast, safe and available in production: a gateway, three kinds of caches, fallbacks, rate limits, guardrails, versions and SLOs.","json":"https://abxk.ai/en/ai-development/learn/production-llm-architecture/index.json","kind":"page","title":"Production LLM Architecture: Gateways, Caching, Fallbacks","url":"https://abxk.ai/en/ai-development/learn/production-llm-architecture/"},{"description":"When it pays to run open-weight LLMs yourself: licenses, serving software, GPU memory sizing, operations and the quality gap to closed models in our data.","json":"https://abxk.ai/en/ai-development/learn/self-host-open-weight-models/index.json","kind":"page","title":"Self-Hosting Open-Weight Models","url":"https://abxk.ai/en/ai-development/learn/self-host-open-weight-models/"},{"description":"When several AI agents beat one: orchestrator-worker, pipeline, review and shared-memory patterns, error compounding, cost, tracing and human checkpoints.","json":"https://abxk.ai/en/ai-development/learn/multi-agent-systems/index.json","kind":"page","title":"Multi-Agent Systems: Patterns and Pitfalls","url":"https://abxk.ai/en/ai-development/learn/multi-agent-systems/"},{"description":"What SWE-bench Verified, Aider Polyglot and Terminal-Bench measure, how they score, where they mislead and how to test models on your own code.","json":"https://abxk.ai/en/ai-development/learn/coding-benchmarks-explained/index.json","kind":"page","title":"Coding Benchmarks Explained: SWE-bench, Aider, Terminal-Bench","url":"https://abxk.ai/en/ai-development/learn/coding-benchmarks-explained/"},{"description":"Lower the cost and response time of an LLM app without losing quality: token budgets, caching, batching, model routing, streaming and cost per successful task.","json":"https://abxk.ai/en/ai-development/learn/optimize-llm-cost-and-latency/index.json","kind":"page","title":"Optimize LLM Cost and Latency at Scale","url":"https://abxk.ai/en/ai-development/learn/optimize-llm-cost-and-latency/"}],"section":"ai-development","seo_title":"Learn AI Development: From Beginner to Expert","title":"Learn AI Development","translations":[{"json":"https://abxk.ai/de/ai-development/learn/index.json","language":"de","url":"https://abxk.ai/de/ai-development/learn/"}],"url":"https://abxk.ai/en/ai-development/learn/"}