Meta tags:
description=Join for content on designing, building, and shipping AI software. Learn AI engineering, end-to-end, from idea to production. Every Tuesday. Click to read Decoding AI Magazine, a Substack publication with tens of thousands of subscribers.;
author=Paul Iusztin;

Headings (most frequently used words):

start, here, your, map, to, decoding, ai, recent, posts, foundations, case, studies, projects, guests, newsletter,

Text of the page (most frequently used words):
the (32), paul (21), iusztin (21), and (19), from (16), your (13), agentic (12), 2025 (11), agents (11), production (11), engineering (11), mar (10), rag (9), all (8), real (7), view (7), that (7), for (6), what (6), why (6), guide (6), how (6), agent (6), systems (6), notes (6), subscribe (5), llm (5), months (5), most (5), feb (5), course (5), one (5), world (4), shipping (4), products (4), tutorials (4), fail (4), you (4), decoding (4), building (4), behind (4), anca (4), ioana (4), muscalagiu (4), with (4), mcp (4), code (4), engineer (4), apr (4), weekly (4), substack (3), 2026 (3), access (3), guides (3), poc (3), purgatory (3), highlights (3), learn (3), roadmap (3), scratch (3), newsletter (3), multi (3), without (3), web (3), build (3), github (3), louis (3), françois (3), bouchard (3), content (3), ship (3), day (3), karpathy (3), named (3), built (3), model (3), write (3), explore (3), its (3), context (3), javascript (2), home (2), app (2), start (2), series (2), evals (2), foundations (2), paolo (2), perrone (2), jan (2), zero (2), skip (2), realistic (2), mastering (2), new (2), chat (2), 139 (2), priya (2), senior (2), architect (2), learned (2), way (2), alejandro (2), aboy (2), actually (2), works (2), after (2), trial (2), error (2), scenes (2), observability (2), lucian (2), lature (2), two (2), tier (2), orchestration (2), keeps (2), debuggable (2), scaling (2), 120 (2), losing (2), control (2), jun (2), aug (2), reviewer (2), slack (2), asana (2), enterprise (2), designing (2), 409 (2), critical (2), mistakes (2), silently (2), destroy (2), inside (2), workflow (2), article (2), hrs (2), ago (2), deep (2), research (2), over (2), transcripts (2), grounded (2), years (2), curated (2), thinking (2), not (2), public (2), system (2), pattern (2), lets (2), instead (2), retrieving (2), pipeline (2), overkill (2), handbook (2), latest (2), end (2), magazine (2), this, site, requires, run, correctly, please, unblock, scripts, turn, great, culture, get, collection, notice, terms, privacy, dec, finale, controlling, output, vertical, november, updates, dai, thank, supporting, google, already, recommending, alongside, coursera, deeplearning, oxford, spent, shmulik, cohen, superhero, nov, secret, sauce, balancing, diversity, quality, precision, underrated, science, samplers, guests, 161, may, theory, api, deployments, llmops, pro, juan, ovalle, query, rich, visual, pdfs, under, king, modal, colpali, 125, integrated, scales, within, organization, breaks, old, architectures, 127, hands, unifying, through, like, sep, burning, time, money, sanity, getting, architecture, right, projects, case, studies, complete, evaluating, retrieval, augmented, generation, has, exactly, failure, modes, more, less, vibe, checking, trusted, wish, had, mental, prevents, overengineering, next, transform, into, operating, harness, full, catalog, become, ready, portfolio, email, reveal, courses, master, art, large, language, models, concept, books, linkedin, pauliusztin, also, see, recent, posts, reasoning, fine, memory, isn, join, software, idea, every, tuesday, 304, jul, skill, 191, hugo, bowne, anderson, stop, 159, 943, second, brain, assistant, popular, read, command, center, here, map, about, archive, contact, perks, roadmaps, sign,

Text of the page (random words):
decoding ai magazine paul iusztin substack subscribe sign in home notes chat llm engineer s handbook agentic ai engineering course roadmaps perks contact me archive about start here your map to decoding ai the ai engineering command center read the latest most popular view all build your second brain ai assistant feb 6 2025 paul iusztin 943 36 159 stop building ai agents jun 26 2025 hugo bowne anderson 191 13 25 context engineering 2025 s 1 skill in ai jul 22 2025 paul iusztin 304 16 35 agentic ai engineering guide mar 19 paul iusztin and louis françois bouchard 409 16 68 decoding ai magazine join for content on designing building and shipping ai software learn ai engineering end to end from idea to production every tuesday subscribe the latest from paul iusztin karpathy named it i built one on my notes anca ioana muscalagiu your agent s reasoning is fine its memory isn t recent posts view all karpathy named it i built one on my notes a deep research agent over my notes highlights and transcripts grounded in years of curated thinking not the public web 5 hrs ago paul iusztin 13 3 how to ship a weekly article in one day inside the agentic ai workflow behind my weekly newsletter course and content apr 15 paul iusztin 38 12 6 your rag pipeline is overkill the pattern that lets your model write code to explore its context instead of retrieving it apr 7 paul iusztin 59 7 9 see all also on pauliusztin ai github linkedin x books llm engineer s handbook master the art of engineering large language models from concept to production courses agentic ai engineering guide a 6 day email course to reveal the 6 critical mistakes that silently destroy agentic systems agentic ai engineering become an agentic ai engineer with a production ready portfolio explore full catalog write real code ship real ai products access real world guides from the poc purgatory to shipping ai products subscribe foundations view all your rag pipeline is overkill the pattern that lets your model write code to explore its context instead of retrieving it apr 7 paul iusztin 59 7 9 agentic harness engineering building systems that transform the llm into the new operating system mar 31 paul iusztin 76 12 13 from 12 agents to 1 the mental model that prevents you from overengineering your next ai system mar 26 paul iusztin and louis françois bouchard 45 2 10 the ai evals roadmap i wish i had from vibe checking to trusted agents in production mar 24 paul iusztin 67 6 9 why rag has exactly 6 failure modes no more no less a complete guide for evaluating your retrieval augmented generation systems mar 17 paul iusztin 36 6 4 case studies view all karpathy named it i built one on my notes a deep research agent over my notes highlights and transcripts grounded in years of curated thinking not the public web 5 hrs ago paul iusztin 13 3 how to ship a weekly article in one day inside the agentic ai workflow behind my weekly newsletter course and content apr 15 paul iusztin 38 12 6 agentic ai engineering guide the 6 critical mistakes that silently destroy agentic systems mar 19 paul iusztin and louis françois bouchard 409 16 68 scaling to 120 ai agents without losing control how two tier orchestration keeps multi agent systems debuggable mar 5 lucian lature 52 3 6 behind the scenes of ai observability in production what actually works after 6 months of trial and error feb 3 alejandro aboy 31 5 7 projects view all getting agent architecture right designing real world ai agents with mcp without burning your time money and sanity sep 6 2025 anca ioana muscalagiu 80 10 9 build with mcp like a real engineer hands on code for an enterprise ai pr reviewer by unifying github slack and asana through mcp aug 30 2025 anca ioana muscalagiu 127 6 14 why mcp breaks old enterprise ai architectures build from scratch an ai pr reviewer integrated with github slack and asana that scales within your organization aug 19 2025 anca ioana muscalagiu 125 11 12 the king of multi modal rag colpali query your rich visual pdfs under a rag web app jun 5 2025 juan ovalle 90 18 from 0 to pro ai agents roadmap theory to api deployments and llmops may 31 2025 paul iusztin 161 3 28 access real world guides from the poc purgatory to shipping ai products subscribe guests view all why most rag tutorials fail you how a senior architect learned rag from scratch the production way mar 12 priya 139 17 13 scaling to 120 ai agents without losing control how two tier orchestration keeps multi agent systems debuggable mar 5 lucian lature 52 3 6 behind the scenes of ai observability in production what actually works after 6 months of trial and error feb 3 alejandro aboy 31 5 7 the realistic guide to mastering ai agents in 2026 from zero to production in 6 9 months what to learn what to skip and why most tutorials fail jan 6 paolo perrone 89 6 12 the underrated science of llm samplers the secret sauce for balancing diversity quality and precision nov 25 2025 shmulik cohen ai superhero 46 8 9 newsletter view all why most rag tutorials fail you how a senior architect learned rag from scratch the production way mar 12 priya 139 17 13 i spent 9 months building an agentic ai engineering course google is already recommending it alongside coursera deeplearning ai and oxford feb 26 paul iusztin 20 2 2 thank you for supporting decoding ai roadmap updates and the new dai chat feb 19 paul iusztin 1 the realistic guide to mastering ai agents in 2026 from zero to production in 6 9 months what to learn what to skip and why most tutorials fail jan 6 paolo perrone 89 6 12 november highlights from foundations to production ai ai agents series finale controlling llm output vertical ai agents the evals series dec 18 2025 paul iusztin 13 6 1 access real world guides from the poc purgatory to shipping ai products subscribe 2026 paul iusztin privacy terms collection notice start your substack get the app substack is the home for great culture this site requires javascript to run correctly please turn on javascript or unblock scripts