> ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # The Agentic AI Hub > A software engineer's complete reference to AI, from foundations to agents. Version 1.1 · Last updated 2026-07-22 · License CC BY 4.0 · Published by daily.dev Every page below is available as LLM-friendly markdown via its `.md/` URL. For rendered HTML, omit `.md`. ## Part I. Foundations - [How LLMs Actually Work](https://daily.dev/agentic-ai-hub/how-llms-actually-work.md/): A large language model predicts the next token given the tokens so far, and that is essentially all it does. - [Core Concepts](https://daily.dev/agentic-ai-hub/core-concepts.md/): Quick definitions for the vocabulary you'll run into everywhere. Each one is short, and several get a fuller treatment later in the handbook. - [Prompting & Context Engineering](https://daily.dev/agentic-ai-hub/prompting-context-engineering.md/): 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. - [Safety, Alignment & Governance](https://daily.dev/agentic-ai-hub/safety-alignment-governance.md/): Building with AI means owning its failure modes. This section is deliberately neutral and tight, enough to reason about risk without ideology. ## Part II. Models, Labs & Benchmarks - [The Labs: Who's Who](https://daily.dev/agentic-ai-hub/the-labs-whos-who.md/): Snapshot as of July 19, 2026. Valuations and funding are dated and sourced. - [Frontier Model Comparison](https://daily.dev/agentic-ai-hub/frontier-model-comparison.md/): A dated snapshot of the current top-tier, closed ("frontier") models, meaning the API-only models from the major labs that set the capability bar. - [Open-Weight Models](https://daily.dev/agentic-ai-hub/open-weight-models.md/): The models you can download, self-host, and fine-tune. As of July 2026. Two things to know: (1) "open weight" ≠ open source. - [Specialized Models](https://daily.dev/agentic-ai-hub/specialized-models.md/): Beyond the general-purpose flagships, each modality and job has its own leaders, and the "best" one shifts constantly, so treat these as categories to shop in with current examples. - [Benchmarks & Leaderboards](https://daily.dev/agentic-ai-hub/benchmarks-leaderboards.md/): The single most useful mental model here is that benchmarks tell you what a model can do on someone else's task. - [Pricing & Cost Reference](https://daily.dev/agentic-ai-hub/pricing-cost-reference.md/): Pricing is a Frontier Model Comparison snapshot. This section is the durable part: how to reason about cost so you're not surprised by a bill. - [How to Choose a Model](https://daily.dev/agentic-ai-hub/how-to-choose-a-model.md/): The honest answer is to shortlist from benchmarks and reputation, then run a small eval on your actual task. ## Part III. Tools, Products & Agents - [Chat Assistants & Apps](https://daily.dev/agentic-ai-hub/chat-assistants-apps.md/): The consumer/prosumer chat apps are the front door to each lab's frontier model. - [Coding Tools & CLI Agents](https://daily.dev/agentic-ai-hub/coding-tools-cli-agents.md/): Two families here: IDE assistants (autocomplete + chat + in-editor agents living in your editor) and CLI/terminal agents (you talk to an agent in the shell. - [Agent Harnesses & Frameworks](https://daily.dev/agentic-ai-hub/agent-harnesses-frameworks.md/): Two very different things get called "agent tooling." - [No-Code & App Builders](https://daily.dev/agentic-ai-hub/no-code-app-builders.md/): Prompt-to-app tools turn a description into a running web app with UI, backend, and deploy. - [Voice & Real-Time Agents](https://daily.dev/agentic-ai-hub/voice-real-time-agents.md/): Real-time voice agents = STT (speech-to-text) → LLM → TTS (text-to-speech) stitched into a low-latency loop (or, increasingly, a single speech-to-speech model). - [Browser & Computer-Use Agents](https://daily.dev/agentic-ai-hub/browser-computer-use-agents.md/): These agents perceive a screen or DOM and act (click, type, scroll, navigate) to complete tasks a human would do in a browser or OS. - [Multimodal Creative Tools](https://daily.dev/agentic-ai-hub/multimodal-creative-tools.md/): Image, video, and audio generation. Quality is now high across the board. Choose by control, licensing, and API availability more than raw "wow." - [MCP & the Tool/Context Ecosystem](https://daily.dev/agentic-ai-hub/mcp-tool-context-ecosystem.md/): Models are only half the story. The other half is the plumbing that gives models hands: how an assistant reaches your files, databases, SaaS tools, and the web. ## Part IV. Building with AI: The Engineering Stack - [RAG & Retrieval](https://daily.dev/agentic-ai-hub/rag-retrieval.md/): Retrieval-Augmented Generation (RAG) is the practice of fetching relevant text (or other data) at query time and injecting it into the model's context so the model can answer from information it wasn't trained on. - [Vector Databases & Memory](https://daily.dev/agentic-ai-hub/vector-databases-memory.md/): A vector database stores embeddings and serves approximate nearest-neighbor (ANN) search, which finds the closest vectors to a query vector quickly using index structures like HNSW (graph-based, the most common) or IVF/IVF-PQ (cluster + quantize, memory-efficient at scale). - [Fine-Tuning & Post-Training](https://daily.dev/agentic-ai-hub/fine-tuning-post-training.md/): Reach for the cheapest tool that works, in this order: - [Dataset Engineering](https://daily.dev/agentic-ai-hub/dataset-engineering.md/): Data quality, not model choice, is usually the ceiling on a fine-tune. - [Inference, Serving & Optimization](https://daily.dev/agentic-ai-hub/inference-serving-optimization.md/): TTFT (Time To First Token). Latency until the first token appears. Dominated by the prefill (prompt-processing) phase and prompt length. - [AI Hardware & Accelerators](https://daily.dev/agentic-ai-hub/ai-hardware-accelerators.md/): The 2026 picture is that NVIDIA still dominates training and general inference. - [APIs, Inference Platforms & Gateways](https://daily.dev/agentic-ai-hub/apis-inference-platforms-gateways.md/): Four rough tiers, each with different trade-offs on model access, speed, price, and control. - [Local & Self-Hosting Stack](https://daily.dev/agentic-ai-hub/local-self-hosting-stack.md/): Running models on your own machine or servers. - [LLMOps: Evals, Observability & Guardrails](https://daily.dev/agentic-ai-hub/llmops-evals-observability-guardrails.md/): Shipping LLM features without evals and observability is flying blind: outputs are non-deterministic, quality is subjective, and regressions are silent. ## Part V. Working with AI: Techniques, Workflows & Adoption - [Levels of AI Adoption](https://daily.dev/agentic-ai-hub/levels-of-ai-adoption.md/): Before you can improve how your team works with agents, you need a shared way to say where you are. - [Agentic Engineering: Core Ideas](https://daily.dev/agentic-ai-hub/agentic-engineering-core-ideas.md/): "Agentic coding" is an overloaded term. - [Orchestration Patterns](https://daily.dev/agentic-ai-hub/orchestration-patterns.md/): Once one agent works, the obvious move is to run several. This is where the biggest gains and the biggest self-inflicted wounds both live. - [Context, Skills & Memory](https://daily.dev/agentic-ai-hub/context-skills-memory.md/): Agents are only as good as what they know when they start, and by default they start knowing nothing about your repo, your conventions, or last week's decisions. - [Verification & Testing for Agents](https://daily.dev/agentic-ai-hub/verification-testing-for-agents.md/): If generation is cheap and verification is the bottleneck, then verification infrastructure is your leverage. - [Human Factors & the Agent-Era Career](https://daily.dev/agentic-ai-hub/human-factors-agent-era-career.md/): The techniques above make you faster. This chapter is about what they can quietly cost you, and how not to pay it. ## Part VI. Ecosystem & Staying Current - [People to Follow (X/Twitter)](https://daily.dev/agentic-ai-hub/people-to-follow.md/): X/Twitter is where much of AI moves in real time. Papers get discussed hours before the press notices, and model launches often break here first. - [Newsletters](https://daily.dev/agentic-ai-hub/newsletters.md/): Email survives because it's async and curated. Tagged by focus and cadence. - [Blogs & Publications](https://daily.dev/agentic-ai-hub/blogs-publications.md/): OpenAI Blog: openai.com/news. Launches and research. The announcement of record. - [Podcasts & YouTube](https://daily.dev/agentic-ai-hub/podcasts-youtube.md/): Latent Space (swyx & Alessio): latent.space/podcast. Best for: the AI-engineering discipline. - [Communities](https://daily.dev/agentic-ai-hub/communities.md/): Where real-time, tacit knowledge lives, the kind that never makes it into a blog post. - [Key Papers & Reading List](https://daily.dev/agentic-ai-hub/key-papers-reading-list.md/): A chronological spine of the field. The ones tagged Start here or Landmark are the priority reads; the rest fill in context. - [Platforms](https://daily.dev/agentic-ai-hub/platforms.md/): The infrastructure you'll actually live in. - [Events & Conferences](https://daily.dev/agentic-ai-hub/events-conferences.md/): 🔄 Dates and formats change yearly. Always confirm on the official site. - [Learning Paths, Courses & Books](https://daily.dev/agentic-ai-hub/learning-paths-courses-books.md/): Organized beginner → advanced. Pick a lane and go deep. Breadth comes with time. ## Part VII. Appendices - [AI Adoption Stats & Trends](https://daily.dev/agentic-ai-hub/ai-adoption-stats-trends.md/): 🔄 Fast-moving section. All figures are dated and sourced; surveys are annual and market forecasts get revised, so check the live sources for the latest. - [Glossary of Key Terms](https://daily.dev/agentic-ai-hub/glossary.md/): A jargon-buster for the terms used throughout this handbook. Where a full section exists, terms link to it.