The ai-guru lessons, made for listening. Patterns, smells and refactorings for LLM systems and agents, explained the way a senior colleague would, without reading code aloud. https://ai-guru-academy.vercel.app/en/ en ai-guru false Decorative Multi-Agent is an AI code smell, a sign of trouble in LLM systems, in the Dispensables group. Five agents with job titles passing text to each other without splitting any real work. https://ai-guru-academy.vercel.app/en/smells/decorative-multi-agent/ https://ai-guru-academy.vercel.app/en/smells/decorative-multi-agent/ ai-guru-en-decorative-multi-agent Sat, 24 Oct 2026 00:00:00 GMT 500 false Collapse Agents is an AI refactoring for LLM systems, in the Moving control group. Merge agents that only pass text along into one agent with the right tools. https://ai-guru-academy.vercel.app/en/refactorings/collapse-agents/ https://ai-guru-academy.vercel.app/en/refactorings/collapse-agents/ ai-guru-en-collapse-agents Sat, 24 Oct 2026 00:00:00 GMT 517 false Tool Router is an AI design pattern for LLM apps and agents, in the Tools and action group. Pick a small subset of tools before calling the main model. https://ai-guru-academy.vercel.app/en/patterns/tool-router/ https://ai-guru-academy.vercel.app/en/patterns/tool-router/ ai-guru-en-tool-router Fri, 23 Oct 2026 00:00:00 GMT 471 false Mega Agent is an AI code smell, a sign of trouble in LLM systems, in the Bloaters group. One agent researches, writes, reviews, and publishes with the same context and the same tools. https://ai-guru-academy.vercel.app/en/smells/mega-agent/ https://ai-guru-academy.vercel.app/en/smells/mega-agent/ ai-guru-en-mega-agent Fri, 23 Oct 2026 00:00:00 GMT 469 false Extract Subagent is an AI refactoring for LLM systems, in the Moving control group. Give a large task its own agent with a clean context and only the tools it needs. https://ai-guru-academy.vercel.app/en/refactorings/extract-subagent/ https://ai-guru-academy.vercel.app/en/refactorings/extract-subagent/ ai-guru-en-extract-subagent Fri, 23 Oct 2026 00:00:00 GMT 520 false Subagent Delegation is an AI design pattern for LLM apps and agents, in the Agent behavior group. The main agent spawns subagents for focused tasks and receives only the conclusion. https://ai-guru-academy.vercel.app/en/patterns/subagent-delegation/ https://ai-guru-academy.vercel.app/en/patterns/subagent-delegation/ ai-guru-en-subagent-delegation Fri, 23 Oct 2026 00:00:00 GMT 547 false Orchestrator-Workers is an AI design pattern for LLM apps and agents, in the Composition group. One model decides subtasks on the fly and hands them to workers. https://ai-guru-academy.vercel.app/en/patterns/orchestrator-workers/ https://ai-guru-academy.vercel.app/en/patterns/orchestrator-workers/ ai-guru-en-orchestrator-workers Fri, 23 Oct 2026 00:00:00 GMT 509 false Internal knowledge base chat is a real-world case study of an LLM system, in the Data and documents group. Answer employee questions from wikis, policies, and manuals. https://ai-guru-academy.vercel.app/en/scenarios/internal-knowledge-chat/ https://ai-guru-academy.vercel.app/en/scenarios/internal-knowledge-chat/ ai-guru-en-internal-knowledge-chat Thu, 22 Oct 2026 00:00:00 GMT 539 false ReAct Loop is an AI design pattern for LLM apps and agents, in the Agent behavior group. Alternate reasoning, action, and observation until the task is done. https://ai-guru-academy.vercel.app/en/patterns/react-loop/ https://ai-guru-academy.vercel.app/en/patterns/react-loop/ ai-guru-en-react-loop Thu, 22 Oct 2026 00:00:00 GMT 571 false Unbounded Loop is an AI code smell, a sign of trouble in LLM systems, in the Control-flow abusers group. The agent can call tools forever; the only limit is the credit card. https://ai-guru-academy.vercel.app/en/smells/unbounded-loop/ https://ai-guru-academy.vercel.app/en/smells/unbounded-loop/ ai-guru-en-unbounded-loop Thu, 22 Oct 2026 00:00:00 GMT 466 false Add Loop Budget is an AI refactoring for LLM systems, in the Moving control group. Cap steps, time, and money for each run and define what happens at the limit. https://ai-guru-academy.vercel.app/en/refactorings/add-loop-budget/ https://ai-guru-academy.vercel.app/en/refactorings/add-loop-budget/ ai-guru-en-add-loop-budget Thu, 22 Oct 2026 00:00:00 GMT 480 false Stop Conditions is an AI design pattern for LLM apps and agents, in the Agent behavior group. Define clearly when the agent is done, has given up, or needs help. https://ai-guru-academy.vercel.app/en/patterns/stop-conditions/ https://ai-guru-academy.vercel.app/en/patterns/stop-conditions/ ai-guru-en-stop-conditions Thu, 22 Oct 2026 00:00:00 GMT 529 false Tool Sprawl is an AI code smell, a sign of trouble in LLM systems, in the Bloaters group. The agent has 40 similarly named tools and often picks the wrong one. https://ai-guru-academy.vercel.app/en/smells/tool-sprawl/ https://ai-guru-academy.vercel.app/en/smells/tool-sprawl/ ai-guru-en-tool-sprawl Thu, 22 Oct 2026 00:00:00 GMT 494 false Consolidate Tools is an AI refactoring for LLM systems, in the Simplifying tools group. Merge similar tools and remove the ones nobody uses. https://ai-guru-academy.vercel.app/en/refactorings/consolidate-tools/ https://ai-guru-academy.vercel.app/en/refactorings/consolidate-tools/ ai-guru-en-consolidate-tools Thu, 22 Oct 2026 00:00:00 GMT 522 false Context Rot is an AI code smell, a sign of trouble in LLM systems, in the Bloaters group. A long session drags old history that confuses the model and makes every turn pricier. https://ai-guru-academy.vercel.app/en/smells/context-rot/ https://ai-guru-academy.vercel.app/en/smells/context-rot/ ai-guru-en-context-rot Wed, 21 Oct 2026 00:00:00 GMT 478 false RAG for Small Data is an AI code smell, a sign of trouble in LLM systems, in the Dispensables group. A vector search pipeline for 20 pages that fit entirely in the context. https://ai-guru-academy.vercel.app/en/smells/rag-for-small-data/ https://ai-guru-academy.vercel.app/en/smells/rag-for-small-data/ ai-guru-en-rag-for-small-data Wed, 21 Oct 2026 00:00:00 GMT 453 false Replace RAG with Direct Context is an AI refactoring for LLM systems, in the Organizing data group. When the material fits in the window, send it whole and use prompt caching. https://ai-guru-academy.vercel.app/en/refactorings/replace-rag-with-direct-context/ https://ai-guru-academy.vercel.app/en/refactorings/replace-rag-with-direct-context/ ai-guru-en-replace-rag-with-direct-context Wed, 21 Oct 2026 00:00:00 GMT 460 false Contextual Chunking is an AI design pattern for LLM apps and agents, in the Context and knowledge group. Split documents along their structure and attach to each chunk the context it came from. https://ai-guru-academy.vercel.app/en/patterns/contextual-chunking/ https://ai-guru-academy.vercel.app/en/patterns/contextual-chunking/ ai-guru-en-contextual-chunking Wed, 21 Oct 2026 00:00:00 GMT 487 false Replace History with Summary is an AI refactoring for LLM systems, in the Organizing data group. Replace old turns with a summary and with facts stored outside the context. https://ai-guru-academy.vercel.app/en/refactorings/replace-history-with-summary/ https://ai-guru-academy.vercel.app/en/refactorings/replace-history-with-summary/ ai-guru-en-replace-history-with-summary Wed, 21 Oct 2026 00:00:00 GMT 524 false Context Compaction is an AI design pattern for LLM apps and agents, in the Context and knowledge group. Summarize or prune the context as it grows, keeping what matters. https://ai-guru-academy.vercel.app/en/patterns/context-compaction/ https://ai-guru-academy.vercel.app/en/patterns/context-compaction/ ai-guru-en-context-compaction Wed, 21 Oct 2026 00:00:00 GMT 500 false Free-Text Handoff is an AI code smell, a sign of trouble in LLM systems, in the Couplers group. One step hands loose text to the next, which has to guess the format. https://ai-guru-academy.vercel.app/en/smells/free-text-handoff/ https://ai-guru-academy.vercel.app/en/smells/free-text-handoff/ ai-guru-en-free-text-handoff Sat, 10 Oct 2026 00:00:00 GMT 446 false Replace Free Text with Structured Output is an AI refactoring for LLM systems, in the Organizing data group. Define a schema for the step's output and validate it before moving on. https://ai-guru-academy.vercel.app/en/refactorings/replace-free-text-with-structured-output/ https://ai-guru-academy.vercel.app/en/refactorings/replace-free-text-with-structured-output/ ai-guru-en-replace-free-text-with-structured-output Sat, 10 Oct 2026 00:00:00 GMT 512 false Replace LLM Call with Code is an AI refactoring for LLM systems, in the Simplifying tools group. Move calculation, formatting, and validation into a function the model calls. https://ai-guru-academy.vercel.app/en/refactorings/replace-llm-call-with-code/ https://ai-guru-academy.vercel.app/en/refactorings/replace-llm-call-with-code/ ai-guru-en-replace-llm-call-with-code Sat, 10 Oct 2026 00:00:00 GMT 480 false Golden Dataset is an AI design pattern for LLM apps and agents, in the Operations and quality group. Keep a curated set of inputs and expected answers that grows with real bugs. https://ai-guru-academy.vercel.app/en/patterns/golden-dataset/ https://ai-guru-academy.vercel.app/en/patterns/golden-dataset/ ai-guru-en-golden-dataset Sat, 10 Oct 2026 00:00:00 GMT 556 false Blind Retry is an AI code smell, a sign of trouble in LLM systems, in the Control-flow abusers group. Every error triggers another attempt, including errors that will never succeed. https://ai-guru-academy.vercel.app/en/smells/blind-retry/ https://ai-guru-academy.vercel.app/en/smells/blind-retry/ ai-guru-en-blind-retry Sat, 10 Oct 2026 00:00:00 GMT 411 false Classify Errors Before Retry is an AI refactoring for LLM systems, in the Safety and reliability group. Separate transient errors from permanent ones and retry only what can succeed. https://ai-guru-academy.vercel.app/en/refactorings/classify-errors-before-retry/ https://ai-guru-academy.vercel.app/en/refactorings/classify-errors-before-retry/ ai-guru-en-classify-errors-before-retry Sat, 10 Oct 2026 00:00:00 GMT 416 false Invoice and contract extraction is a real-world case study of an LLM system, in the Data and documents group. Read invoices and contracts in PDF and fill the ERP with no manual typing. https://ai-guru-academy.vercel.app/en/scenarios/nfe-contract-extraction/ https://ai-guru-academy.vercel.app/en/scenarios/nfe-contract-extraction/ ai-guru-en-nfe-contract-extraction Sat, 10 Oct 2026 00:00:00 GMT 486 false Natural language to SQL is a real-world case study of an LLM system, in the Data and documents group. Let business teams query the database without knowing SQL and without risk of damage. https://ai-guru-academy.vercel.app/en/scenarios/text-to-sql/ https://ai-guru-academy.vercel.app/en/scenarios/text-to-sql/ ai-guru-en-text-to-sql Sat, 10 Oct 2026 00:00:00 GMT 609 false Routing is an AI design pattern for LLM apps and agents, in the Composition group. Classify the input and send each kind down a specialized path. https://ai-guru-academy.vercel.app/en/patterns/routing/ https://ai-guru-academy.vercel.app/en/patterns/routing/ ai-guru-en-routing Fri, 09 Oct 2026 00:00:00 GMT 525 false How to read this catalog is an AI engineering fundamental for people who work with LLMs. The five pillars, how pages connect, and where to start for your role. https://ai-guru-academy.vercel.app/en/fundamentals/how-to-read-this-catalog/ https://ai-guru-academy.vercel.app/en/fundamentals/how-to-read-this-catalog/ ai-guru-en-how-to-read-this-catalog Fri, 09 Oct 2026 00:00:00 GMT 463 false The prompt as an interface is an AI engineering fundamental for people who work with LLMs. Treat the prompt like an API contract: input, output, version, and test. https://ai-guru-academy.vercel.app/en/fundamentals/prompt-as-interface/ https://ai-guru-academy.vercel.app/en/fundamentals/prompt-as-interface/ ai-guru-en-prompt-as-interface Fri, 09 Oct 2026 00:00:00 GMT 451 false Tools and function calling is an AI engineering fundamental for people who work with LLMs. How the model asks your code to act and who decides what happens next. https://ai-guru-academy.vercel.app/en/fundamentals/tools-and-function-calling/ https://ai-guru-academy.vercel.app/en/fundamentals/tools-and-function-calling/ ai-guru-en-tools-and-function-calling Fri, 09 Oct 2026 00:00:00 GMT 468 false Tool Use is an AI design pattern for LLM apps and agents, in the Tools and action group. Give the model well described functions to fetch data and take action. https://ai-guru-academy.vercel.app/en/patterns/tool-use/ https://ai-guru-academy.vercel.app/en/patterns/tool-use/ ai-guru-en-tool-use Fri, 09 Oct 2026 00:00:00 GMT 492 false Prompt Bloat is an AI code smell, a sign of trouble in LLM systems, in the Bloaters group. The system prompt is past 3k tokens and every fixed bug became one more paragraph. https://ai-guru-academy.vercel.app/en/smells/prompt-bloat/ https://ai-guru-academy.vercel.app/en/smells/prompt-bloat/ ai-guru-en-prompt-bloat Fri, 09 Oct 2026 00:00:00 GMT 485 false Agent Where a Chain Would Do is an AI code smell, a sign of trouble in LLM systems, in the Control-flow abusers group. The path never changes, yet an autonomous agent decides the order on every run. https://ai-guru-academy.vercel.app/en/smells/agent-where-chain-would-do/ https://ai-guru-academy.vercel.app/en/smells/agent-where-chain-would-do/ ai-guru-en-agent-where-chain-would-do Fri, 09 Oct 2026 00:00:00 GMT 469 false Support bot with human escalation is a real-world case study of an LLM system, in the Customer service group. A WhatsApp bot that answers questions, looks up orders, and knows when to call a human. https://ai-guru-academy.vercel.app/en/scenarios/support-bot-escalation/ https://ai-guru-academy.vercel.app/en/scenarios/support-bot-escalation/ ai-guru-en-support-bot-escalation Fri, 09 Oct 2026 00:00:00 GMT 586 false LLM Doing Deterministic Work is an AI code smell, a sign of trouble in LLM systems, in the Dispensables group. The model calculates taxes, formats dates, or validates IDs, things a function does without error. https://ai-guru-academy.vercel.app/en/smells/llm-doing-deterministic-work/ https://ai-guru-academy.vercel.app/en/smells/llm-doing-deterministic-work/ ai-guru-en-llm-doing-deterministic-work Fri, 09 Oct 2026 00:00:00 GMT 493 false What an eval is is an AI engineering fundamental for people who work with LLMs. Tests for systems that never answer the same way twice, from unit case to benchmark. https://ai-guru-academy.vercel.app/en/fundamentals/what-is-an-eval/ https://ai-guru-academy.vercel.app/en/fundamentals/what-is-an-eval/ ai-guru-en-what-is-an-eval Fri, 09 Oct 2026 00:00:00 GMT 512 false Untested Prompt is an AI code smell, a sign of trouble in LLM systems, in the Change preventers group. The prompt changes in production with no test set to prove it did not get worse. https://ai-guru-academy.vercel.app/en/smells/untested-prompt/ https://ai-guru-academy.vercel.app/en/smells/untested-prompt/ ai-guru-en-untested-prompt Fri, 09 Oct 2026 00:00:00 GMT 448 false Add Eval Before Changing the Prompt is an AI refactoring for LLM systems, in the Operations group. Build a test set and measure the current version before any tweak. https://ai-guru-academy.vercel.app/en/refactorings/add-eval-before-prompt-change/ https://ai-guru-academy.vercel.app/en/refactorings/add-eval-before-prompt-change/ ai-guru-en-add-eval-before-prompt-change Fri, 09 Oct 2026 00:00:00 GMT 466 false Eval Harness is an AI design pattern for LLM apps and agents, in the Operations and quality group. Run test cases automatically on every prompt, model, or code change. https://ai-guru-academy.vercel.app/en/patterns/eval-harness/ https://ai-guru-academy.vercel.app/en/patterns/eval-harness/ ai-guru-en-eval-harness Fri, 09 Oct 2026 00:00:00 GMT 520 false LLMs for engineers is an AI engineering fundamental for people who work with LLMs. The model as a probabilistic function: what goes in, what comes out, and what it never promises. https://ai-guru-academy.vercel.app/en/fundamentals/llm-for-engineers/ https://ai-guru-academy.vercel.app/en/fundamentals/llm-for-engineers/ ai-guru-en-llm-for-engineers Thu, 08 Oct 2026 00:00:00 GMT 515 false Tokens and the context window is an AI engineering fundamental for people who work with LLMs. Why everything costs tokens, why the middle of the context fades, and how to measure it. https://ai-guru-academy.vercel.app/en/fundamentals/tokens-and-context-window/ https://ai-guru-academy.vercel.app/en/fundamentals/tokens-and-context-window/ ai-guru-en-tokens-and-context-window Thu, 08 Oct 2026 00:00:00 GMT 488 false Sampling and temperature is an AI engineering fundamental for people who work with LLMs. Where answer variation comes from and when you want more or less of it. https://ai-guru-academy.vercel.app/en/fundamentals/sampling-and-temperature/ https://ai-guru-academy.vercel.app/en/fundamentals/sampling-and-temperature/ ai-guru-en-sampling-and-temperature Thu, 08 Oct 2026 00:00:00 GMT 468 false Chains, agents, and workflows is an AI engineering fundamental for people who work with LLMs. The difference between code choosing the path and the model choosing the path. https://ai-guru-academy.vercel.app/en/fundamentals/chains-agents-workflows/ https://ai-guru-academy.vercel.app/en/fundamentals/chains-agents-workflows/ ai-guru-en-chains-agents-workflows Thu, 08 Oct 2026 00:00:00 GMT 477 false Prompt Chaining is an AI design pattern for LLM apps and agents, in the Composition group. Split the task into fixed steps where each output feeds the next input. https://ai-guru-academy.vercel.app/en/patterns/prompt-chaining/ https://ai-guru-academy.vercel.app/en/patterns/prompt-chaining/ ai-guru-en-prompt-chaining Thu, 08 Oct 2026 00:00:00 GMT 561 false Structured Output is an AI design pattern for LLM apps and agents, in the Composition group. Require the model to answer in a schema and validate the response. https://ai-guru-academy.vercel.app/en/patterns/structured-output/ https://ai-guru-academy.vercel.app/en/patterns/structured-output/ ai-guru-en-structured-output Thu, 08 Oct 2026 00:00:00 GMT 489 false Embeddings is an AI engineering fundamental for people who work with LLMs. Text turned into vectors: what similarity captures and where it misleads. https://ai-guru-academy.vercel.app/en/fundamentals/embeddings/ https://ai-guru-academy.vercel.app/en/fundamentals/embeddings/ ai-guru-en-embeddings Thu, 08 Oct 2026 00:00:00 GMT 490 false Retrieval-Augmented Generation (RAG) is an AI design pattern for LLM apps and agents, in the Context and knowledge group. Fetch relevant passages and hand them to the model along with the question. https://ai-guru-academy.vercel.app/en/patterns/rag/ https://ai-guru-academy.vercel.app/en/patterns/rag/ ai-guru-en-rag Thu, 08 Oct 2026 00:00:00 GMT 541 false