Library.

Agent context contracts — local rules the model must not guess A context contract states a project’s local rules: what an agent may change, how it should proceed, how to verify a change, and when to hand work to a person. It limits guesswork where a general prompt is insufficient. → Agent identity and permissions — who is actually acting An agent needs more than tools. It needs its own identity, bounded permissions and an audit trail so it is clear who stands behind an action, what it was allowed to do and where it must stop. → Agent infrastructure — the boring layer agents need to work An agent is not just a model with a task. In production it needs identity, permissions, inboxes, tools, memory, audit, telemetry and clear boundaries. Without infrastructure, autonomy is just a pretty demo with risk attached. → Agent memory — what an AI system may carry from past runs Agent memory is not a bigger prompt. It is a design for what gets stored, how it is retrieved, when it may be used, and who can correct a bad memory. Good memory saves work; bad memory produces confident mistakes with a history. → Agent safety and sandboxing An agent with tools is a tiny machine for consequences. Sandboxes, approvals, least privilege and audit logs are not enterprise decoration; they are brakes before the fire. → AI content consent — who may read, train and act AI no longer reads the web only like a search engine. Crawlers, training datasets and agentic browsers have different effects, so publishers and creators need finer rules than simply allow or block. → AI Data Supply Chain AI data is not one pile of files but a supply chain: from sources and rights through cleaning and provenance to continuous audit. The open web remains important, but high-quality, usable data is increasingly constrained, contested, and expensive to govern. → AI in Cybersecurity — The New Layer of Attack and Defense AI can accelerate code analysis, alert triage and attack preparation. Its value depends on tools, data and verification; an agent does not replace patching, access control or the security team's accountability. → AI vendor lock-in — when the model is not the only dependency AI lock-in is not created only by choosing a model. It grows through contracts, data, tools, evals, pricing and workflows that slowly stop being portable. → AI-assisted research — the model as a research partner AI-assisted research uses models to find hypotheses, write code, test variants and read literature. It is not automatic science. It is a faster research loop with new ways to fall on your face. → Async agents — work that does not live in chat An agent that takes a task, runs outside the conversation, and returns a finished artifact. Powerful for long workflows, dangerous without state, limits and review. → Computer-use agents — the model that clicks A computer-use agent sees the screen and controls the UI. It sounds like sci-fi; in practice it is fragile automation over pixels, forms and badly labelled buttons. → Evals and benchmarks — measurement instead of vibes A benchmark is not truth carved in stone. It is an instrument with error bars. Without it, though, you are only guessing whether a model or agent works. → Fine-tuning — a scalpel, not a universal hammer Fine-tuning changes model weights. It is powerful when you have data, evals and a clear reason. It is an expensive mistake when it hides a bad prompt, missing RAG or an unclear process. → Frontier model governance — who checks the model before release Frontier model governance asks who tests the strongest models before deployment, under which rules and with what power to intervene. A voluntary audit, a system card and government testing are not the same thing. → Inference-time compute (Reasoning models) Extra computation for an individual prompt can improve some demanding tasks, but it does not guarantee a correct answer and adds latency. → Long-Horizon Agents When an agent tackles a task that lasts hours or days rather than one turn. The decisive layer is not just the model, but state, checkpoints, budgets, verification, and safe recovery. → Model economics — the operating cost of intelligence Tokens, latency, throughput, quality, and risk on one bill. A model is not just smart or dumb; it is expensive, slow, cheap, local, or operationally bearable. → Model orchestration: how AI systems choose and combine models Model orchestration decides which model should handle each part of the work. It combines routing, handoffs, fallbacks, cost, latency, quality, security and portability in one operational control layer. → Model reliability — when a pretty answer is not enough Reliability is about when the model knows, when it does not, when it invents, and how often its output can be trusted in production. Elegant wording is not evidence. → Multi-agent systems — when and why to split work between roles A multi-agent system divides work among specialized agents. It can help when one agent struggles with complex rules or tools, but it adds coordination, cost, and new places for errors. → Open vs. closed models — who pays the frontier premium An open model is not automatically freedom, and a closed model is not automatically lock-in. The practical question is when control, cost and local deployment matter more than paying for frontier capability. → Physical AI — when an agent reaches into the world Physical AI connects models, robots, simulation and actions in the real environment. It is not about a cute robot demo, but about who carries the risk when a model starts moving things. → Small Language Models (SLM) and specialized models A smaller model can suit a narrow task and local deployment, but the task, hardware, and operating setup—not parameter count alone—determine whether it is practical. → Tool use — when a model calls tools Tool use is the moment an LLM stops merely answering and starts calling APIs, running commands, reading files or touching databases. Useful, sharp and dangerous. → Watermarks in AI text — capabilities and limits Invisible statistical signals in AI outputs can support provenance claims, but they do not prove authorship or reliably classify every human and machine-written text. → Zombie internet — when AI text eats the web Zombie internet is a web flooded with generated text, summaries without accountability and content that only looks human from far away. The problem is not just spam. The problem is loss of trust. →