--- title: "Library" url: "https://talirezun.com/library" markdown: "https://talirezun.com/library.md" works: 77 updated: "2026-10-21T16:50:11.703Z" --- # Library Everything Tali Režun has published: essays and manuals from From Lab to Life, research papers, and the archive. Each work links to its page, its Markdown twin and the editions where it can be read. Search: https://talirezun.com/library?q= · Machine-readable index (JSON): https://talirezun.com/library/search-index.json ## From Lab to Life ### Essay - [The Right Context, Not All of It](https://talirezun.com/library/right-context-not-all-of-it.md) (2026-09-30): Written deliberately as a lesson rather than a product story, taught through The Curator v3.80.0. - [The Context Engine](https://talirezun.com/library/the-context-engine.md) (2026-09-20): Three kinds of context, three write rules, and a project that outlives the session, the harness, the model and the machine - [Every Product Needs a Home](https://talirezun.com/library/every-product-needs-a-home.md) (2026-09-16): Building a modern website in the age of AI agents: a manual, told through the new website of The Curator - [Where Your Context Lives](https://talirezun.com/library/where-your-context-lives.md) (2026-09-03): The Curator ships as a native Mac app (v3.45.0). Covers the three layers (personal wiki, Shared Brain, agent working state), the menu-bar widget, bring-your-own-key across three providers at about €5 a month, and plain-markdown portability. - [The Handoff Writes Itself](https://talirezun.com/library/the-handoff-writes-itself.md) (2026-08-30): The confession piece about two years of hand-written handoff files. The flaw: the most degraded model writes the most important document. - [Field Notes](https://talirezun.com/library/field-notes-corpus.md) (2026-08-24): I turned fifty-plus articles into a corpus you can question, download, and hand to your own AI. - [The Mixed Fleet](https://talirezun.com/library/the-mixed-fleet.md) (2026-08-17): Can a frontier orchestrator on a subscription delegate to local open-weight models? - [I Could Tell You My AI Has Never Lied. I'm Not Going To.](https://talirezun.com/library/not-claiming-my-ai-never-lied.md) (2026-08-06): Seven months, two generations, one production rebuild — and five things I learned that I did not expect to learn. - [Lumina: An AI Agent Your Business Can Stand Behind](https://talirezun.com/library/lumina-agent-you-can-stand-behind.md) (2026-07-31): The behind-the-scenes rebuild of Lumina from Gen-1 to an enterprise-grade Gen-2. - [From 0 to Dev in One Day: What a Real Coding Harness Actually Looks Like](https://talirezun.com/library/zero-to-dev-in-one-day.md) (2026-07-20): A summer manual for the curious non-developer who keeps seeing people build apps out of thin air and wondering: could I actually do that? - [Six Months After I Shipped Lumina; Here's What Actually Happened](https://talirezun.com/library/six-months-after-lumina.md) (2026-07-10): Running Lumina with real customers six months after launch. A Ljubljana massage studio hit a forgotten 2,000-character personality limit mid-conversation; the systemic fix raised the limit fourfold and added live counters. - [The Fight for Intelligence](https://talirezun.com/library/the-fight-for-intelligence.md) (2026-07-08): Putting the Organisation of Tomorrow to Work; Use Cases, Vendor Independence, and the Brain Behind the Framework - [Second Brain to Shared Brain: Building a Neural Network of Your Own Knowledge](https://talirezun.com/library/second-brain-to-shared-brain.md) (2026-07-03): A follow-up seven weeks after the Shared Brain launch. The author's own wiki has 3,305 nodes and 15,095 edges at v3.0.6. - [Anthropic Shipped Two Models This Week. I Only Wanted One Back.](https://talirezun.com/library/two-models-i-wanted-one.md) (2026-07-01): Two Anthropic announcements 24 hours apart. Sonnet 5 (30 June) becomes the new default, and its real story is follow-through on multi-step tasks. - [Chasing Jarvis: The Bottleneck Was Never the Code](https://talirezun.com/library/bottleneck-was-never-the-code.md) (2026-06-28): We are learning to build and ship real digital products using AI coding agents. The gap between idea and shipped product is no longer technical, it is contextual. - [I Built Auto Loops Before They Had a Name](https://talirezun.com/library/auto-loops-before-a-name.md) (2026-06-22): How Claude Code plus Playwright via MCP became an autonomous testing loop in early 2025, before "loop engineering" had a name. - [I Built a 24/7 AI Email Support Agent for My App. Here's the Exact Stack.](https://talirezun.com/library/ai-email-support-agent-stack.md) (2026-06-19): Every founder I know has the same problem with email support. In the early days, you handle it yourself. You are fast, you are personal, and you actually know the product. Then you get busier. Response times slip. Users start to notice. You think about hiring someone, but the volume does not justify it yet. So you buy a helpdesk tool, set up some canned responses, and tell yourself you will get to the backlog this weekend. You never get to the backlog. - [16x Cheaper, Open Weights, and the Model That Doesn't Disappear on Fridays](https://talirezun.com/library/16x-cheaper-open-weights.md) (2026-06-18): Compares Kimi K2.7 and Claude Fable 5 using real production data (24 landing pages, 12 prompts). - [The Curator — Product Update (v3.0.1-beta.20 → beta.23)](https://talirezun.com/library/curator-product-update-beta-23.md) (2026-06-18): Release notes for The Curator v3.0.1 beta.20 to beta.23: Shared Brain synchronisation improvements, a new test-automation infrastructure, and stability fixes. - [Blueprint of a Frontier Coding Agent](https://talirezun.com/library/blueprint-of-a-frontier-coding-agent.md) (2026-06-14): Inside the machinery that powers modern AI development, and why understanding it matters even if you never write a line of code - [Context is the Code: The Complete Three-Phase Process for Building with AI Agents](https://talirezun.com/library/context-is-the-code.md) (2026-06-03): In the first article, I named the phases: Context Engineering, The Build Phase, Production and Deployment. That naming had an unintentional effect. By calling Phase One “Context Engineering,” I implied that context engineering was something you did once — at the beginning — and then left behind. - [Building the Organization of Tomorrow](https://talirezun.com/library/building-the-organization-of-tomorrow.md) (2026-06-01): ORGANISATION OF TOMORROW (ØØT): An Open-Source Framework and Playbook for Partner-Run, AI-Augmented Organisations - [The Shared Brain: When Second Brains Start Thinking Together](https://talirezun.com/library/shared-brain-thinking-together.md) (2026-05-19): Introduces The Curator v3.0.0-beta Shared Brain: private, attributed contributions merged into a collective wiki for teams and cohorts. - [The Agent Memory Problem — And Why Your Second Brain Might Be the Answer](https://talirezun.com/library/agent-memory-problem.md) (2026-05-14): A survey of how the industry is attacking agent memory (vendor memory products, vector stores, managed memory services, file-based memory), why context windows alone fail at agent scale ("context rot"), and why a compiled Markdown… - [The Brain Is Ready. The Body Is the Problem.](https://talirezun.com/library/brain-ready-body-problem.md) (2026-05-04): State of AI, May 2026. Frontier models have reached capability thresholds (1M context, open-source parity). - [From Graph to Intelligence: The My Curator MCP and the Art of Querying Your Second Brain](https://talirezun.com/library/my-curator-mcp-second-brain.md) (2026-04-27): How My Curator MCP Turns Your Second Brain into a Frontier AI Research Partner - [Building Knowledge Immortality Through the Second Brain Architecture and The Curator App](https://talirezun.com/library/knowledge-immortality-second-brain.md) (2026-04-23): The philosophical case for the second brain: knowledge immortality, externalised expertise, and curation (compounding) versus retrieval (stateless). - [The Second Brain That Grows Smarter and Lives on Your Computer](https://talirezun.com/library/second-brain-on-your-computer.md) (2026-04-15): Introduces The Curator through Karpathy's "LLM as wiki" insight: a local, private, Markdown-based knowledge graph that Obsidian can read. - [Three Philosophies, One Goal; A Practitioner's Comparison of Augment Code, Claude Code, and Codex CLI](https://talirezun.com/library/augment-claude-code-codex-compared.md) (2026-04-07): A practitioner's comparison of three coding-agent philosophies. - [Two Worlds of Code: The Gap Between AI Agent Orchestration and Legacy Development](https://talirezun.com/library/two-worlds-of-code.md) (2026-03-26): The canonical home of the Solo era / Symphony era framing. - [Behind the Curtain: The Three-Phase Process I Use to Build Every AI-Coded Product](https://talirezun.com/library/three-phase-ai-build-process.md) (2026-03-16): Two years ago, I started an experiment. I wanted to know whether I could build production-grade software products without writing most of the code myself. Not because I was lazy. Because I had thirty years of product ideas and not nearly enough development hours to explore them. - [From Writing Code to Directing Intelligence: Five Days Inside Augment Code's Intent](https://talirezun.com/library/five-days-inside-augment-intent.md) (2026-03-09): Five days testing Augment Code's Intent orchestration tool on the production Lumina platform (building Lumina Pro). - [Law = Code: Can AI Finally Democratise the World's Most Exclusive Algorithm?](https://talirezun.com/library/law-equals-code.md) (2026-03-02): It all started with a conversation between me and my friend Anton Dobrina — legal expert, fellow AI enthusiast, and someone who has spent years studying and working in legal practice in Slovenia, co-writing Slovenian legislation and is an expert in the Slovenian retirement code. - [From One Agent to Coding Agent Armies: My 15-Month Journey to AI Orchestration](https://talirezun.com/library/coding-agent-armies-orchestration.md) (2026-02-17): How Augment Code’s Intent Just Changed Everything — Again - [OpenClaw: The AI Assistant That Lives in Your Pocket (And Actually Gets Things Done)](https://talirezun.com/library/openclaw-pocket-ai-assistant.md) (2026-01-30): A research-based overview of OpenClaw (formerly Moltbot / Clawdbot), the open-source, always-on personal AI assistant created by Peter Steinberger. - [Why I Ditched RAG Pipelines for 1M Token Context Windows](https://talirezun.com/library/why-i-ditched-rag-pipelines.md) (2026-01-21): An 18-month build of a legal-document AI for Slovenian building legislation (Moj AI). - [How I Built an AI Marketing Team That Actually Works: From Memes to Technical Content in Minutes](https://talirezun.com/library/ai-marketing-team-that-works.md) (2026-01-14): An AI multi-agent marketing workflow in which different agents handle different content types. - [From Prototype to Production: Building Lumina an AI Widget Platform in 30 Days](https://talirezun.com/library/lumina-prototype-to-production.md) (2026-01-05): The Lumina Widget build story: a 30-day sprint from concept to production on a budget of about $100 in AI credits, using Augment Code with Claude Haiku 4.5. - [From Google AI Studio to Production: Building Lumina v1 in 48 Hours](https://talirezun.com/library/lumina-v1-in-48-hours.md) (2025-12-11): How the first version of Lumina was prototyped in Google AI Studio and taken to production on Firebase in 48 hours. - [Chasing Jarvis: The Three Missing Pieces in AI Coding Agents](https://talirezun.com/library/chasing-jarvis-three-missing-pieces.md) (2025-11-24): A Two-Year Journey From Fiction to Reality (and the Creativity Blockers Still Holding Us Back) - [Understanding AI Agents: From Chatbots to Autonomous Digital Workers](https://talirezun.com/library/understanding-ai-agents.md) (2025-10-27): The foundational definitions essay. Sets out the taxonomy of chatbots, assistants, agents and autonomous workers, with a four-tier autonomy hierarchy and a five-level maturity model for agentic AI. - [How I Built an AI-Powered Vacation MCP Search Tool in 14 Days (And Why You Should Care)](https://talirezun.com/library/vacation-mcp-search-tool.md) (2025-10-15): The MountVacation MCP server build story, and one of the first open-source MCP servers for tourism. - [The Year I Started Coding with AI: My Coding Agent Journey](https://talirezun.com/library/year-i-started-coding-with-ai.md) (2025-09-07): A personal narrative of the shift from "learning to code" to "directing intelligence", tracing the tools from early agents to orchestration. - [Data Sovereignty in the AI Age: Building Your Own Private ChatGPT](https://talirezun.com/library/private-chatgpt-data-sovereignty.md) (2025-09-01): In my work, I regularly encounter businesses paralyzed by AI’s data requirements. A law firm wants to analyze contracts using AI but cannot risk client confidentiality. A manufacturer needs AI-powered documentation analysis but won’t send proprietary processes to external servers. - [From Prompts to Precision: The Art & Science of Context Engineering](https://talirezun.com/library/art-and-science-of-context-engineering.md) (2025-08-16): Mastering the discipline that transforms how we communicate with artificial intelligence. - [Are We Becoming Obsolete, or Finally Free?](https://talirezun.com/library/obsolete-or-finally-free.md) (2025-08-15): My reflections on navigating humanity’s greatest transformation. - [The Context Engineer's Toolkit: Essential AI Tools for All Levels](https://talirezun.com/library/context-engineers-toolkit.md) (2025-08-14): A practical toolkit for context engineering at every skill level. Covers model-selection frameworks, prompt patterns, and how to match a tool's capability to the complexity of the use case. - [Understanding Large Language Models: A Complete Manual](https://talirezun.com/library/understanding-large-language-models.md) (2025-08-13): A complete non-technical manual on LLMs. Covers how they work and what they are not, the training process, in-context learning, and the "stochastic parrot" debate. - [Exploring Early Indicators of AGI in Coding Agents: MCP + Cline Case Study](https://talirezun.com/library/agi-indicators-in-coding-agents.md) (2025-08-12): What happens when you give an entry-level AI model the right tools and see if it can build complex software? That’s exactly what I tested in my latest research, and the results reveal something fascinating about the path toward Artificial General Intelligence (AGI). - [The Hidden Cost of AI: What Every Leader Needs to Know About Energy and Water](https://talirezun.com/library/hidden-cost-of-ai-energy-water.md) (2025-08-12): A short leader-facing digest of the peer-reviewed COTRUGLI research on generative AI's resource footprint (B15). - [The Claude Desktop Coding Agent Experiment: Early Results & Context Management Lessons](https://talirezun.com/library/claude-desktop-coding-agent-experiment.md) (2025-08-11): The Claude Desktop coding-agent experiment. Documents the real productivity gains alongside the quality constraints: what worked in conversational programming, where human oversight was still required, and why context management was the deciding factor. - [Beyond Encryption: Next-Level Email, Messaging & Data File Transfer Communication Security](https://talirezun.com/library/beyond-encryption-communication-security.md) (2024-02-06): Digital communication has become most relevant in the past decade as digital data has become extremely valuable. Communication in the form of emailing, messaging and data file transfers form the foundation behind most business transactions. - [From Online to On-Chain, the Evolution of Digital Communication](https://talirezun.com/library/online-to-on-chain-communication.md) (2023-10-19): The article explores the state of legacy communication platforms that we use and depend on every day while proposing a new alternative. It offers insight into the work of Dr. Režun and his team, spanning the past five years, as they innovate a novel approach enabling immutable, non-custodial, permissionless, and decentralized communication and data ownership retention. - [Human "On-Chain" Communication Dedicated Protocol & SDK](https://talirezun.com/library/on-chain-communication-protocol-sdk.md) (2023-08-23): Blockchain technology has the potential to change the narrative and the core concept of traditional digital human communication and data management (i.e. email, messaging, data file transfers, data file management, etc.); from custodial to non-custodial; from centralized to decentralized; from permissioned to permissionless, and; from free but mined to payable but yours. Enters 4thTech with L1/L2 secured “on-chain” communication infrastructure framework powered by a dedicated SDK (i.e. software development kit). ### Case study - [One Founder, Eight Weeks, Four Hundred Agents](https://talirezun.com/library/one-founder-eight-weeks-four-hundred-agents.md) (2026-10-21): I delivered a working, deployed MVP in eight weeks, alone, by directing more than four hundred AI agents. ## Research ### Paper - [Knowledge Accumulates, State Supersedes: Structuring and Carrying Context for Multi-Session, Multi-Harness AI Agent Work — A Design Study of The Curator, an Open-Source Context Engine](https://talirezun.com/library/knowledge-accumulates-state-supersedes.md) (2026-09-30): Large language model (LLM) agents now carry out work that outlasts a single session: building software, running literature reviews, writing books, producing campaigns. Every session, however, begins with an empty context window, and when the work moves to a different agent harness, a different model or a different computer, whatever the previous session knew is lost. - [Context as Architecture: Full-Corpus Grounding, Orchestrated Agentic Development, and Compliance-by-Design in a Production AI Assistant Platform](https://talirezun.com/library/context-as-architecture.md) (2026-08-01): This paper reports a longitudinal design-science case study of a single production artefact — Lumina, a multi-tenant AI assistant platform — across two complete generations built fourteen months apart in capability terms and seven months apart in calendar terms. - [The Fight for Intelligence — Putting the ØØT to Work: Use Cases, Vendor Independence, and the Brain Behind the Framework](https://talirezun.com/library/fight-for-intelligence-paper.md) (2026-07-08): Argues that competition has shifted from a fight for resources to a fight for intelligence, using the 19-day frontier-model suspension of June 2026 as evidence of single-vendor risk. - [Organisation of Tomorrow (ØØT) — Building the Organization of Tommorow: An Open-Source Framework and Playbook for Partner-Run, AI-Augmented Organisations](https://talirezun.com/library/organization-of-tomorrow-paper.md) (2026-05-01): Presents ØØT as an open-source framework and playbook for partner-run, AI-augmented firms. - [Chasing Jarvis: Can Technically Sophisticated Non-Programmers Deploy SaaS Applications Using AI Coding Agents? An Empirical Investigation Through Context Engineering and the Lumina AI Case Study](https://talirezun.com/library/chasing-jarvis-non-programmers-saas.md) (2026-03-15): The empirical study behind the non-developer thesis. - [Law = Code; Research Paper](https://talirezun.com/library/law-equals-code-paper.md) (2026-03-02): Can AI Democratise the World's Most Exclusive Algorithm? A Review of Emerging Legal AI Capabilities and Their Implications for Access to Justice - [The Energy and Water Footprint of Generative AI: A Vanguard Leadership Perspective](https://talirezun.com/library/energy-water-footprint-generative-ai.md) (2025-06-01): Examines generative AI's energy and water demand, efficiency differences between LLMs (Mixtral 8x22B at ~0.15 Wh per query versus Claude 3.5 at ~0.4 Wh), and regional implications in Europe, the US and Asia. - [AI as a Force Multiplier: Leaders for Industry 5.0](https://talirezun.com/library/ai-force-multiplier-industry-5.md) (2025-04-16): The rapid ascent of artificial intelligence (i.e. AI) technologies—spanning large language models (i.e. LLMs), no-code platforms, AI agents, automation tools, and Web3 integration—presents both opportunities and challenges for business leaders. - [Initial Steps Toward Blockchain Enterprise Adoption](https://talirezun.com/library/blockchain-enterprise-adoption-steps.md) (2020-12-02): A guideline for enterprise blockchain adoption using two use cases: Tolar HashNet (a scalable network) and 4thTech (an application suite for secure, immutable cross-border data and document exchange and eDelivery). - [Is Blockchain the Missing Internet Link? Reality, Integration, Adoption and Mainstream](https://talirezun.com/library/blockchain-missing-internet-link.md) (2019-07-06): Argues that the internet failed on personal digital freedom and evolved into global intermediaries that monetise private data. - [Conceptual Business Effect Model on the Positive Effect of Firm-Generated Problem-Solving Content on Social Media and Online Brand Equity — Model Description](https://talirezun.com/library/brand-equity-business-effect-model.md) (2019-05-03): A stand-alone description, adapted from the DBA dissertation, of the general online business model that SMEs can adopt to build brand equity and exposure through problem-solving content. - [Naton Human Resources: Establishing Online Presence, Brand Positioning and Trust](https://talirezun.com/library/naton-hr-online-presence.md) (2019-04-27): A case study of how the recruitment agency Naton HR built its online presence, brand position and trust from December 2011, applying the content model developed in the DBA dissertation (B01). - [Identifying Key Quality Factors of a Small Hotel: Business Success Model of a High-Quality Small Hotel in Ljubljana](https://talirezun.com/library/small-hotel-quality-factors.md) (2019-03-01): A case study of a new four-star boutique hotel in Ljubljana, based on a manager interview, an inspection and 124 guest reviews. - [Artificial Intelligence is here! Reality, Integration, Research, and Adoption](https://talirezun.com/library/artificial-intelligence-is-here.md) (2019-01-01): An early overview of AI's history (from the Turing machine onward), the definition of intelligence, WIPO's framework of AI technologies, and AI's impact on jobs and adoption. - [Online Brand Awareness, Brand Equity and the Importance of Professional Value-Added Content](https://talirezun.com/library/online-brand-awareness-and-equity.md) (2019-01-01): Explores alternatives to paid online brand promotion. Part of Dr. Režun's doctoral thesis. - [Company Generated Problem-Solving Content on Social Media (SM) and Online Brand Equity: Designing and Testing a Model for Its Effectiveness](https://talirezun.com/library/problem-solving-content-brand-equity.md) (2018-01-01): A mixed-methods study (grounded theory plus quantitative testing) that designs and tests an online model for SMEs. ### Manual - [The DBA Dissertation Guidebook: The steps toward writing your DBA masterpiece](https://talirezun.com/library/dba-dissertation-guidebook.md) (2019-03-31): A practical guide for prospective and current Doctor of Business Administration students. ### Report - [Exploring Early Indicators of AGI in Coding Agents: A Case Study on MCP-Powered Systems](https://talirezun.com/library/agi-indicators-coding-agents-paper.md) (2025-05-01): This study, conducted under the COTRUGLI Business School 2 Co-lab initiative in Q1 and Q2 2025, investigates whether Model Context Protocols (MCPs) can enhance large language models (LLMs) to exhibit early indicators of Artificial General Intelligence (AGI) in coding agents. ### Whitepaper - [Solana L1 Secured W2W dChat Communication Framework — FOURim Protocol Light Paper](https://talirezun.com/library/fourim-protocol-light-paper.md) (2021-08-20): Describes 4thTech's Solana-based dChat: end-to-end encrypted, immutable wallet-to-wallet messaging where each message is one L1 transaction (about 1–5 seconds). - [On-Chain" Communication Technology Framework — 4thTech Whitepaper](https://talirezun.com/library/4thtech-on-chain-whitepaper.md) (2018-01-01): Argues that the internet became a system of centralised intermediaries trading ease of access for surveillance and data mining, with permissioned access and de-platforming. ## Archive ### Essay - [High-Quality Educational Content in the Web3 Space](https://talirezun.com/library/web3-educational-content.md) (2022-10-08): Marks the completion of the first two seasons of the Blockchain Recorded podcast (co-founded 2021). ### Paper - [Establishing Hotel Booking Independence with Online Presence, Brand Positioning and Trust](https://talirezun.com/library/hotel-booking-independence.md) (2019-03-06): A case study of Hotel Vault Ljubljana (from Feb 2018).