--- title: "Glossary | Named terms from the books" description: "Short, liftable definitions for the named systems and working vocabulary on this site: SENSE, STACK, CHORUS, AI agent, MCP, RAG, GEO, AEO, and the rest of the operator lexicon." image: "https://lenvanderhof.com/photos/len-portrait-1.jpg" --- Operator lexicon # Glossary an answer engine can lift Short, liftable definitions for the named systems and working vocabulary on this site: SENSE, STACK, CHORUS, AI agent, MCP, RAG, GEO, AEO, and the rest of the operator lexicon. terms 24 ## Terms Overview Each plate opens the full definition, when to use it, and what not to confuse it with. ### SENSE SENSE is a five-move strategic intelligence layer: Scan, Evaluate, Navigate, Simulate, Execute. Scan collects with a thesis. Evaluate turns a signal into a sourced claim with a confidence grade. Navigate makes the claim change a watchlist, an assumption register, or a Monday decision. Simulate rehearses the future before it arrives. Execute meets a decision or it never happened. The unit of work is one claim, not another unread summary. A model in the loop is not this layer until a claim can change a decision. Framework · SENSEOpen the term→ ### STACK STACK is a five-layer architecture for repositories where humans and agents share work: Structure, Toolchain, Agent configuration, Connection, Knowledge and quality. Structure is the map an agent can navigate on minute one. Toolchain is the commands it may run. Agent configuration is versioned standing context. Connection is MCP with contracts and least privilege. Knowledge and quality is memory, evals, and CI, so a model upgrade does not silently lower the bar. The agent OS is versioned like the app. Framework · STACKOpen the term→ ### CHORUS CHORUS is a six-skill coordination protocol for teams of 2 to 15 people who share work with specialised AI workers: Charter, Handoff, Orchestrate, Review, Update, Sync. A charter is seven fields that turn a vague intention into a contract any worker can be handed. A handoff is a six-field packet. They are not the same artifact. Org charts name reporting lines. CHORUS names coordination lines. A graph of model calls is not this protocol. If the receiver reconstructs the job from a chat log, you have a paste. Framework · CHORUSOpen the term→ ### RESILIENT RESILIENT is a nine-capacity model for founder performance under load: reappraisal, emotional granularity, somatic regulation, identity flexibility, learning orientation, interpersonal support, executive function, narrative integration, and titrated exposure. Capacity is infrastructure you train and budget, not a mood that returns after a holiday. The company can still move while the founder is the hidden single point of failure. Sleep, recovery, and the social cover that lets a founder tell the truth are part of the system, not extras. Framework · RESILIENTOpen the term→ ### BooksOS BooksOS is a gated production system for serious nonfiction written with AI agents: Brief, Bible, Map, Draft, Edit, Package, Launch. Each stage owns one decision and ends at a gate. Agents do specialist work inside the gates. Judgment, voice, and accountability stay human. A fluent draft that cannot survive a fact-check is not a book. It is inventory you will throw away. The operating system is the gates, not the model that drafted the chapter. Framework · BOOKSOSOpen the term→ ### DOWNSTREAM DOWNSTREAM is an operator protocol for delayed consequences. The real cost of a decision often lands later, and somewhere else: another team, a later quarter, a customer you will not meet. The named moves are Detect, Observe, Weigh, Navigate, Stream effects, Trace, Review, Effects on stakeholders, Assess systemic risk, Mitigate. It is an operating heuristic, not a validated risk instrument. Name the second bend before you commit, then assign an owner to watch it. The book is in production; the protocol is already usable. Framework · DOWNSTREAMOpen the term→ ### CALIBRATE CALIBRATE is the practice of matching the strength of a judgment to the strength of the evidence, then updating when the facts move. Confidence is a report, not a personality trait. A loud claim with a thin source is a calibration failure, not conviction. The work is to score the claim, write what would change your mind, and revise the score when the evidence moves. The book that owns this name is available now in English and Dutch. Framework · CALIBRATEOpen the term→ ### GRAIN GRAIN is a retrieval loop: Gather, Rank, Assemble, Inspect, Navigate. Gather collects candidate passages. Rank orders them for the question actually asked. Assemble builds the context the model may see. Inspect checks that the cited chunk is the one used. Navigate decides the next lookup or the refusal. If you cannot point at the passage, you do not have retrieval. You have a fluent guess. The book that owns this name is available now in English and Dutch. Framework · GRAINOpen the term→ ### ROUTE ROUTE is a five-skill discipline for governing a mix of language models: Register, Objective typing, Utilize policy, Track, Evolve. Register catalogs every model with mandate, cost class, privacy class, and retirement status. Objective typing names what a task actually requires before a model is chosen. Utilize policy writes the routing rules, cascades, and fallbacks. Track measures cost, latency, and quality per route. Evolve promotes, demotes, and retires on a cadence. A leaderboard pick is a collection. ROUTE is a portfolio. The book that owns this name is available now in English and Dutch. Framework · ROUTEOpen the term→ ### TRACE TRACE is a five-step research loop: Target, Retrieve, Assess, Cross-check, Export. Target locks stakes, scope, and output format before a search runs. Retrieve gathers independent sources instead of one confident pass. Assess tiers each source so weight follows credibility. Cross-check requires a second source before a load-bearing claim can enter the memo. Export is a claim ledger a co-founder can act on without redoing the work. Fluent collection is not research. TRACE is the verification structure. The book that owns this name is available now in English and Dutch. Framework · TRACEOpen the term→ ### ROSTER ROSTER is a six-skill protocol for a one-person company that runs named specialist agents: Roles, Objectives, Skills and tools, Triggers, Evaluation, Rotation. Roles give each agent a charter. Objectives make the charter measurable. Skills and tools bound what the agent may use. Triggers decide when it runs. Evaluation scores output instead of vibe. Rotation retires the agent built for last quarter's work. One chatbot that never hands off is not a team. The book that owns this name is available now in English and Dutch. Framework · ROSTEROpen the term→ ### LEVEL LEVEL is a five-move check for grading a claim before you change a belief, a habit, a roadmap, or a bet: Locate, Estimate, Value, Expose, Lean. Locate names the claim. Estimate the cost of being wrong. Value the evidence on the rung it stands on. Expose the strongest case against it. Lean only as hard as that rung allows. The Evidence Ladder is the seven-rung scale underneath. Confidence is not a grade. The book that owns this name is available now in English and Dutch. Framework · LEVELOpen the term→ ### CITATION C CITATION is the standard for a page worth quoting: discoverable, attributed, answer-shaped, evidenced, and actually used. Search eligibility is not a citation. Ranking in ten blue links is a different job. Answer engines quote the first clean capsule they can verify. Invented FAQ schema is not a shortcut; Google ended FAQ rich results on 2026-05-07. The book that owns this name is still in production; the standard is already how this site is built. A mention without a checkable source is not this standard. Open the term→ ### CASCADE C CASCADE is the personal cognitive companion to DOWNSTREAM: trace the next bend before you commit, in the meeting, in your own head. DOWNSTREAM is organizational. CASCADE is the habit that makes the protocol fire when nobody is watching. It is the pause that names who pays later, on a different surface, before you say yes. The book that owns this name is still in production; the habit is already usable. A first-order win with an unnamed later bill is not a decision. It is a delay. Open the term→ ### AI agent An AI agent is a system that takes a goal, uses tools, and acts across steps without a human prompting each one. A chatbot answers a turn. An automation runs a fixed script. An agent is accountable only when it has a charter: purpose, inputs, outputs, authority ceiling, success criteria, review, and escalation. Without those seven fields, it is a demo that can spend money. A wrapper around a chat model is not this. Neither is a scheduled script. Framework · SENSEOpen the term→ ### MCP MCP, the Model Context Protocol, is a contract for how a model calls tools: what it may see, what it may change, and how the call is logged. The official split is host, client, and server, with tools, resources, and prompts as the primitives. Auth is optional; least privilege is not. A server without a contract is a hole in the repo. Founders should care about the interface and the permission, not the logo on the protocol. A clean server with no charter is still a hole with nicer plumbing. Framework · STACKOpen the term→ ### RAG RAG, retrieval-augmented generation, means the model must fetch named passages before it answers. The retrieval is the product. The generation is the last mile. If you cannot inspect which chunk was used, you do not have RAG. You have a language model with extra context stuffed in the prompt. A vector store is a component. GRAIN is the loop that keeps the answer honest. Adding embeddings is not a finished system. Naming the passage is. Framework · GRAINOpen the term→ ### Agent orchestration Agent orchestration is the assignment of work across humans and specialised agents so that handoffs, reviews, and state stay visible. A graph of model calls is not orchestration. Orchestration is who is chartered, what packet travels, what must be reviewed, and who sees the board. Without those four, adding agents adds waiting. CHORUS is one implementation of that operating layer. If you cannot point at the owner, the packet, the gate, and the board, you have a demo. Framework · CHORUSOpen the term→ ### Human in the loop Human in the loop means a named person holds an authority ceiling and a review gate. It is not a human glancing at a dashboard. The human charters the work, can stop a tool call, and owns the outcome. If no one can fail the output against written criteria, the loop is decorative. A vendor slide that says HITL without a named reviewer is a slogan. The name, the ceiling, and the fail criteria have to live in the runbook, not in the deck. Framework · CHORUSOpen the term→ ### Evidence ledger An evidence ledger is a claim-level register: what was asserted, which source supports it, how strong that source is, and what would retire the claim. It is not a bibliography dumped at the end. Operators use it so a number cannot wander between chapters, books, or a back-cover line. If the claim cannot point at a row, it is not ready to print, pitch, or paste into an answer. The ledger is the product. The reference list is a rendering. Framework · BOOKSOSOpen the term→ ### Strategic intelligence layer A strategic intelligence layer is the standing system that turns market, competitor, and internal signals into sourced claims a founder can act on. It is not a dashboard wall and not a weekly PDF. The test is whether a claim changes a watchlist, an assumption, or a Monday decision with a confidence grade attached. SENSE is one implementation: scan, evaluate, navigate, simulate, execute. If competitive work is still a founder reading Slack at midnight, you do not have a layer. You have a habit that will miss a week. Framework · SENSEOpen the term→ ### GEO G GEO, generative engine optimization, is the work of becoming a source that answer engines can retrieve, interpret, extract, and verify. It is not a bag of hidden prompts. Eligibility, extractable answers, original value, and evidence that survives scrutiny are the levers. Ranking in ten blue links is a different job. Google does not require schema, chunking, or an llms.txt file for AI Overviews. A page that cannot be quoted cleanly will not be cited, even if it ranks. Open the term→ ### AEO A AEO, answer engine optimization, is the craft of writing a page so an answer engine can quote a clean capsule: a direct answer near the top, named entities, visible sources, and no invented FAQ schema. GEO is the system. AEO is the page. They fail together when the first screen is a brand manifesto. Google ended FAQ rich results on 2026-05-07; a fake FAQPage is a liability, not a tactic. If the first screen cannot be quoted, the rest of the page will not save it. Open the term→ ### Override doctrine Override doctrine is the written list of decisions an agent may never take: spending above a ceiling, speaking as the company, changing production data, or closing a judgment the founder still owns. It is the complement of a charter. The charter says what the agent does. The doctrine says what it must refuse. A refuse-list that lives in a Slack thread is not doctrine. It is a hope. Write it before the first tool that can send, spend, or delete. Framework · CHORUSOpen the term→ ```json { "@context": "https://schema.org", "@graph": [ { "@type": "DefinedTermSet", "@id": "https://lenvanderhof.com/glossary/#terms", "name": "Glossary", "url": "https://lenvanderhof.com/glossary/", "inLanguage": "en", "hasDefinedTerm": [ { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/sense/#term", "name": "SENSE", "url": "https://lenvanderhof.com/glossary/sense/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/stack/#term", "name": "STACK", "url": "https://lenvanderhof.com/glossary/stack/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/chorus/#term", "name": "CHORUS", "url": "https://lenvanderhof.com/glossary/chorus/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/resilient/#term", "name": "RESILIENT", "url": "https://lenvanderhof.com/glossary/resilient/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/booksos/#term", "name": "BooksOS", "url": "https://lenvanderhof.com/glossary/booksos/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/downstream/#term", "name": "DOWNSTREAM", "url": "https://lenvanderhof.com/glossary/downstream/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/calibrate/#term", "name": "CALIBRATE", "url": "https://lenvanderhof.com/glossary/calibrate/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/grain/#term", "name": "GRAIN", "url": "https://lenvanderhof.com/glossary/grain/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/route/#term", "name": "ROUTE", "url": "https://lenvanderhof.com/glossary/route/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/trace/#term", "name": "TRACE", "url": "https://lenvanderhof.com/glossary/trace/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/roster/#term", "name": "ROSTER", "url": "https://lenvanderhof.com/glossary/roster/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/level/#term", "name": "LEVEL", "url": "https://lenvanderhof.com/glossary/level/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/citation/#term", "name": "CITATION", "url": "https://lenvanderhof.com/glossary/citation/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/cascade/#term", "name": "CASCADE", "url": "https://lenvanderhof.com/glossary/cascade/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/ai-agent/#term", "name": "AI agent", "url": "https://lenvanderhof.com/glossary/ai-agent/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/mcp/#term", "name": "MCP", "url": "https://lenvanderhof.com/glossary/mcp/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/rag/#term", "name": "RAG", "url": "https://lenvanderhof.com/glossary/rag/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/agent-orchestration/#term", "name": "Agent orchestration", "url": "https://lenvanderhof.com/glossary/agent-orchestration/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/human-in-the-loop/#term", "name": "Human in the loop", "url": "https://lenvanderhof.com/glossary/human-in-the-loop/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/evidence-ledger/#term", "name": "Evidence ledger", "url": "https://lenvanderhof.com/glossary/evidence-ledger/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/strategic-intelligence-layer/#term", "name": "Strategic intelligence layer", "url": "https://lenvanderhof.com/glossary/strategic-intelligence-layer/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/geo/#term", "name": "GEO", "url": "https://lenvanderhof.com/glossary/geo/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/aeo/#term", "name": "AEO", "url": "https://lenvanderhof.com/glossary/aeo/" }, { "@type": "DefinedTerm", "@id": "https://lenvanderhof.com/glossary/override-doctrine/#term", "name": "Override doctrine", "url": "https://lenvanderhof.com/glossary/override-doctrine/" } ] }, { "@type": "CollectionPage", "@id": "https://lenvanderhof.com/glossary/#webpage", "url": "https://lenvanderhof.com/glossary/", "name": "Glossary", "inLanguage": "en", "isPartOf": { "@id": "https://lenvanderhof.com/#website" }, "mainEntity": { "@id": "https://lenvanderhof.com/glossary/#terms" }, "breadcrumb": { "@id": "https://lenvanderhof.com/glossary/#breadcrumb" } }, { "@type": "BreadcrumbList", "@id": "https://lenvanderhof.com/glossary/#breadcrumb", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://lenvanderhof.com/" }, { "@type": "ListItem", "position": 2, "name": "Glossary", "item": "https://lenvanderhof.com/glossary/" } ] } ] } ```