> ## Documentation Index > Fetch the complete guide index at: https://www.synscribe.com/agentic-discovery/llms.txt > Use this file to discover all pages before exploring further. --- title: "Agentic Discovery Glossary: 34 Terms Defined" description: "34 agentic discovery terms defined in quotable 40–80 word entries — llms.txt, AGENTS.md, MCP, GEO, the search-and-fetch surface, the stale window, and more." slug: /agentic-discovery/glossary series: The Agentic Discovery Playbook — Reference last_verified: 2026-06-12 --- # Glossary of Agentic Discovery > **In short:** Agentic discovery is how AI agents find, evaluate, and choose products on behalf of their users. This glossary defines the 34 terms the field actually uses — from llms.txt and AGENTS.md to the search-and-fetch surface and the stale window — each in a standalone, quotable definition linked to the play that puts it to work. *This is a reference page — the standard "Do this now" checklist is intentionally omitted. Every entry links to the play or part where the action lives. Terms first defined by this guide are marked.* ### AEO AEO (answer engine optimization) is the practice of optimizing content so answer engines — ChatGPT, Perplexity, Google's AI Overviews — cite it when generating direct answers. The acronym circulates in a second sense, "agentic engine optimization": optimizing for AI agents acting on a user's behalf. This guide treats the answer channel and the agent channel as distinct, with different evidence standards. See [Part 1](/agentic-discovery/what-is-agentic-discovery). ### Agent skills Agent skills are installable instruction packages — defined by a SKILL.md file — that teach a coding agent a product-specific workflow, such as a quickstart or a migration. Install rails include `npx skills add`, and adoption is measurable: top skill patterns show six-figure install counts on skills.sh. Skills encode your conventions directly into the agent's environment. See [Play 4](/agentic-discovery/agent-skills-and-agents-md). ### Agent-grade docs Agent-grade docs (term coined by this guide) are documentation meeting eight testable properties: fetchable, addressable, indexed, chunked, versioned, directive, discoverable, and fresh. The definition is operational — each property maps to an observed exemplar and a pass/fail test, so "agent-ready" becomes auditable rather than aspirational. Five of the eight now arrive as docs-platform defaults. See the [agent-readiness audit](/agentic-discovery/agent-readiness-audit). ### Agentic discovery Agentic discovery (term coined by this guide) is how AI agents find, evaluate, and choose products on behalf of their users. It spans the channels that form a default: the model's training prior, the web search-and-fetch surface it queries live, the retrieval layer it fetches mid-task, and the environment layer installed in its working context. It subsumes GEO and AEO, which cover only the answer channel. See [Part 1](/agentic-discovery/what-is-agentic-discovery). ### AGENTS.md AGENTS.md is a markdown file at a repository root that coding agents read at session start for project conventions and constraints. Scaffolders now write it by default — create-next-app's version states "Your training data is outdated — the docs are the source of truth." In our pilot E1, a one-paragraph AGENTS.md mandate flipped agent product choice 3/3. See [Play 4](/agentic-discovery/agent-skills-and-agents-md). ### Answer engine An answer engine is an AI system that responds to a query with a synthesized answer plus citations instead of a list of links — ChatGPT search, Perplexity, Google AI Overviews. It is one consumer of your content; coding agents that select and integrate products are another, with different consumption patterns (fetching markdown, grepping text). See [Part 6, myth 7](/agentic-discovery/geo-myths-what-doesnt-work). ### AX (agent experience) AX — agent experience — is the agent-facing analog of developer experience: how easily an AI agent can fetch your docs, obtain credentials, call your API, and verify success without human help. Poor AX shows up as failed integrations and agents choosing competitors. The [agent-readiness audit](/agentic-discovery/agent-readiness-audit) is an AX measurement instrument: eight pass/fail tests runnable in about 30 minutes. ### B2A (business-to-agent) B2A — business-to-agent — describes marketing and selling to software agents acting on behalf of buyers. The canonical sighting is Upstash's page footer, addressed to no human: "For AI agents: a free Redis database is available via POST… No signup required." Roughly 2.6% of one major doc index's queries come from raw HTTP clients — custom agents nobody designs pages for. See [Play 10](/agentic-discovery/agent-first-onboarding). ### Birdseye Birdseye (Synscribe's free agent-observability Mac app) reconstructs an AI agent's research run as four debuggable findings layers — per-page, per-search, per-agent, and synthesis — exposing the queries it wrote, the pages it opened, and the claims it killed. It is how the search-and-fetch findings in this guide were measured. See [Play 1](/agentic-discovery/ai-agent-web-search-and-fetch). ### CLAUDE.md CLAUDE.md is the project rules file read by Claude Code at session start — instructions, conventions, and tool preferences that persist across every session in that repository. Products now compete to be written into it: `bun init` auto-creates a CLAUDE.md preferring Bun when it detects an agent environment. It is among the highest-leverage files in the environment layer. See [Play 9](/agentic-discovery/scaffolder-rules-claude-md). ### Content negotiation Content negotiation is serving different formats at the same URL depending on the requester — HTML to browsers, raw markdown to agents and non-browser fetchers. Next.js is the observed gold standard: its docs returned markdown to our non-browser fetcher on canonical URLs without any `.md` suffix. It makes every page agent-readable with zero URL changes. See [Play 6](/agentic-discovery/markdown-docs-for-ai-agents). ### Context7 Context7 is the dominant public docs-retrieval index for coding agents: an MCP server (1.14M weekly npm installs as of 2026-06-11) that fetches current documentation mid-task, plus published rankings of which libraries agents fetch most. Library owners can claim their entry, tune parse configuration, and customize benchmark questions — making it an ownable ranking surface. See [Play 2](/agentic-discovery/ai-agent-registries-and-directories). ### Cursor rules Cursor rules are instruction files in a project's `.cursor/rules/` directory (`.mdc` format) that bias every Cursor session in that repository. They double as a product-distribution surface: `bun init` writes one named `use-bun-instead-of-node-vite-npm-pnpm.mdc` — the filename is the strategy. Part of the environment layer, with the same disclosure and opt-out ethics as any injected rule. See [Play 9](/agentic-discovery/scaffolder-rules-claude-md). ### Default-formation funnel The default-formation funnel (term coined by this guide) is the path by which a product becomes an agent's habitual choice: training prior + retrieval layer + environment layer feed selection, and selection feeds lock-in as scaffolders write rules files that re-bias every future session. That closing loop is why the environment layer outweighs the other channels. See [Part 2](/agentic-discovery/how-ai-agents-choose-products). ### Deprecation eval A deprecation eval is a test suite of prompts that historically elicit your old API, scored by whether an agent emits deprecated patterns with your docs in context. Target: under 5% emission. In pilot E3, directive docs took emission on a recent breaking change from 100% to 0%. Run it in CI and within two weeks of every model release. See [Play 8](/agentic-discovery/stop-ai-using-deprecated-apis). ### Docs-MCP A docs-MCP is an MCP server that exposes your documentation as searchable tools (minimum: `search_{product}`), so agents query your current docs instead of relying on training data. It is the cheapest MCP to ship — Mintlify-class platforms generate one automatically — and the standard first step before a live-system MCP. See [Play 3](/agentic-discovery/mcp-server-distribution). ### Environment layer The environment layer (term coined by this guide) is everything installed in an agent's working context before any retrieval happens: AGENTS.md, CLAUDE.md, cursor rules, and skills. It is the strongest selection lever we measured — a rules file flipped product choice 100% in pilot E1 — because it persists across sessions and bypasses retrieval ranking entirely. See [Play 9](/agentic-discovery/scaffolder-rules-claude-md). ### Flip rate Flip rate is the percentage of trials in which an agent's product choice changes when one of your surfaces — rules file, llms.txt excerpt, operability fact — is present versus absent. It is the cleanest single metric for "are we becoming the default?"; our pilot E1 measured 100% (3/3 vs 0/3). Run it with n≥5 per cell. See [Play 11](/agentic-discovery/ai-evals-and-leaderboards). ### GEO (generative engine optimization) GEO — generative engine optimization — is the practice of optimizing content for citation in AI-generated answers, named by the 2024 academic paper "GEO: Generative Engine Optimization." Its findings (statistics, quotes, and citations boost answer visibility) concern the answer channel and remain unreplicated for agent product selection — a scope distinction the echo chamber routinely drops. See [Part 6](/agentic-discovery/geo-myths-what-doesnt-work). ### Keyless onboarding Keyless onboarding lets an integration be completed before any signup: the agent builds against the product immediately, and a human claims the account later. Clerk's Keyless Mode is the reference — its docs instruct agents "Do NOT tell users to sign up, create accounts, get API keys." It removes the one step agents cannot perform alone. See [Play 10](/agentic-discovery/agent-first-onboarding). ### llms-full.txt llms-full.txt is the companion file to llms.txt containing the entire documentation corpus as a single markdown file, for consumers that prefer bulk ingestion over link-following. Teams tier it by token budget — Hono pioneered the llms.txt / llms-full.txt / llms-small.txt (~90KB) split for context-window-constrained agents. Link it from your llms.txt. See [Play 5](/agentic-discovery/llms-txt). ### llms.txt llms.txt is a markdown index file at a site's root listing documentation links — each with a one-line description — so LLMs and agents can navigate your content efficiently. In practice it has also become an instruction channel: Stripe's tells agents to "never recommend the Charges API." Validated as infrastructure, unproven as a ranking lever. See [Play 5](/agentic-discovery/llms-txt). ### MCP (Model Context Protocol) MCP — the Model Context Protocol — is an open standard that lets AI agents call external tools and resources: search a vendor's docs, provision a sandbox, operate a live system. Products ship MCP servers so agents can use them directly. In pilot E4, knowing a vendor shipped MCP and agent tooling flipped agent selection 2/2. See [Play 3](/agentic-discovery/mcp-server-distribution). ### MCP registry An MCP registry is a directory where agents and their clients discover MCP servers. Few placements show measured impact: the official registry (registry.modelcontextprotocol.io) matters as the upstream pipe — GitHub's MCP Registry sources from it, and VS Code renders that natively. Most standalone directories show no usage evidence; roughly 99% of measured distribution bypasses them. See [Play 2](/agentic-discovery/ai-agent-registries-and-directories). ### Retrieval layer The retrieval layer is the set of surfaces agents fetch mid-task to ground their work: llms.txt indexes, `.md` mirrors, docs-MCPs, and retrieval directories like Context7. It is where products too young for training data win today — a two-year-old library is the #2 most-fetched docs source. Quality beats mass here, and freshness is the strongest score correlate. See [Part 2](/agentic-discovery/how-ai-agents-choose-products) and [Play 5](/agentic-discovery/llms-txt). ### Sandbox MCP A sandbox MCP is an MCP server variant pointed at a test environment, letting agents complete a full integration — accounts, transactions, webhooks — without touching real money or data. Polar's production-plus-sandbox split is the reference implementation. For transactional products it is the difference between being cited and being integrated. See [Play 3](/agentic-discovery/mcp-server-distribution). ### Scaffolder injection Scaffolder injection is a CLI writing agent rules files into the projects it creates: `bun init` detects Claude/Cursor and writes CLAUDE.md plus a cursor rule preferring Bun; create-next-app writes AGENTS.md by default. It is the most aggressive verified growth lever in agentic discovery — and must be disclosed in output and opt-out-able to stay legitimate. See [Play 9](/agentic-discovery/scaffolder-rules-claude-md). ### Search-and-fetch surface The search-and-fetch surface (term coined by this guide) is the layer between the training prior and the retrieval layer, where an agent runs its own web searches, opens a fraction of the results, and verifies the claims it reads against primary sources. It is the entry gate for any product the model doesn't already trust — and the one layer where the prior gets overturned mid-task. See [Play 1](/agentic-discovery/ai-agent-web-search-and-fetch). ### SKILL.md SKILL.md is the file format defining an agent skill — name, trigger description, and the step-by-step instructions an agent loads when the skill is invoked. The spec (agentskills.io) is an open Anthropic standard; Vercel's skills CLI distributes any public repo containing SKILL.md files, with no submission or review step required. See [Play 4](/agentic-discovery/agent-skills-and-agents-md). ### skills.sh skills.sh is Vercel's directory and leaderboard for agent skills, backed by the `skills` CLI (1.38M npm downloads/week as of 2026-06-11; one command installs to ~55 agent clients). There is no gatekeeper: any public repo with SKILL.md files becomes installable, and the leaderboard auto-populates from install telemetry. Your own funnels drive installs; the directory is the scoreboard. See [Play 4](/agentic-discovery/agent-skills-and-agents-md). ### The stale window The stale window (term coined by this guide) is the period between an API change shipping and the next model-training cycle absorbing it — the months when agents confidently emit your old patterns. It is the precise scope where directive docs work: 100%→0% deprecated emission in pilot E3, versus no effect on long-absorbed deprecations (E2). It recurs with every release you ship. See [Play 8](/agentic-discovery/stop-ai-using-deprecated-apis). ### The fetch cut The fetch cut (term coined by this guide) is the gap between being surfaced in an agent's search and actually being opened by it. In one instrumented run, agents surfaced 215 domains but fetched only ~13 (~6%) — the decision to open is driven by title, snippet, domain authority, and freshness, not your on-page content. See [Play 1](/agentic-discovery/ai-agent-web-search-and-fetch). ### The verification cut The verification cut (term coined by this guide) is the share of claims an agent kills when it tries to refute them against primary sources before believing them. In one instrumented run, a three-voter skeptic panel killed 48% of the claims it checked; self-reported vendor numbers fared worst, while primary-source-corroborated claims survived. See [Play 1](/agentic-discovery/ai-agent-web-search-and-fetch). ### Zero-human integration Zero-human integration is the north-star test for agent-first onboarding: can an agent go from the instruction "integrate this product" to a passing test with no human action — no signup, no key copying, no dashboard visit? It is measured as a pass/fail eval plus time-to-first-successful-API-call. Keyless onboarding and sandbox-by-default keys are the enablers. See [Play 10](/agentic-discovery/agent-first-onboarding). ## The receipts *Reference note:* every definition above traces to the same evidence base as the rest of this guide — the audit of 18 developer products, live Context7 rankings, the directory-landscape study, and pilot experiments E1–E5 (single model family, n=2–3 per arm — directional, not population estimates), all collected 2026-06-11. The quotable numbers, with methodology, live in the [Data Room](/agentic-discovery/data). ## FAQ **What is the difference between GEO, AEO, and agentic discovery?** GEO and AEO both target the answer channel — getting cited when AI systems generate answers for humans. Agentic discovery is the umbrella covering how agents find, evaluate, and choose products across all channels: training prior, retrieval, environment, and the product surface itself. **Which terms does this guide coin?** Eight: agentic discovery, the stale window, default-formation funnel, agent-grade docs, environment layer, the search-and-fetch surface, the fetch cut, and the verification cut. Each is marked "(term coined by this guide)" in its entry and defined so it can be cited standalone. **How current are these definitions?** Every entry was verified 2026-06-11 and is re-tested quarterly alongside the rest of the playbook. Status changes — terms, numbers, and verdicts — are logged in the [Data Room](/agentic-discovery/data). --- *Last verified 2026-06-12. We re-test the claims on this page quarterly — changes are logged in the [Data Room](/agentic-discovery/data).* **Part of [The Complete Playbook to Agentic Discovery](/agentic-discovery).** ← Previous: [Drizzle: 440 Snippets That Beat 2,297](/agentic-discovery/case-studies/drizzle) · Next: [The Data Room](/agentic-discovery/data) → > **Stay ahead of the agents.** We re-test this playbook quarterly and publish what changed — new data, busted myths, ranking shifts. [Get the update digest →](/agentic-discovery#updates) > > **Want this done for you?** Synscribe runs agentic-discovery programs for B2B SaaS and developer platforms. [Talk to us →](/contact)