> ## 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: "The Agentic Discovery Playbook: 11 Plays, Sequenced" description: "All 11 plays to become AI agents' default choice — what each does, who needs it, impact and effort — in one ten-minute overview with sequencing." slug: /agentic-discovery/agentic-discovery-playbook series: The Agentic Discovery Playbook — Part 4 of 6 last_verified: 2026-06-12 --- # The 11 Plays of Agentic Discovery — Overview & Sequencing > **In short:** Eleven plays across five surfaces: get SURFACED (win the agent's own web search and verification), get FOUND (registries, MCP, skills), get READ (llms.txt, docs, snippets), get OBEYED (directives over stale training), get INSTALLED (rules files, onboarding, evals). SURFACED is the new entry gate; INSTALLED is the strongest — a one-paragraph rules file flipped product choice 100% of the time in our pilots. ![The agentic-discovery territory: a matrix of who is choosing — coding agents (Claude Code, Codex, OpenCode), work agents, consumer agents (ChatGPT, Perplexity), and vertical enterprise “custobots” — against what the agent does across the find, evaluate, and select flow.](/agentic-discovery/images/diagram-discovery-matrix.svg "The whole territory: who is choosing, against what the agent does.") This page is the whole method in ten minutes. Each play links to a full-depth page with implementation steps, field examples, counterexamples, and a pass/fail eval. If you only skim one page in this guide, skim this one. ## Do this now - [ ] Identify which of the five surfaces you're weakest on (most teams: all five) - [ ] Run the [30-minute audit](/agentic-discovery/agent-readiness-audit) to get your baseline score - [ ] Pick your track below (new product / incumbent / platform) and queue plays in that order - [ ] Ship the week-one pair: registry entries (Play 2) + llms.txt (Play 5) — and make your category page corroborable for agent search ([Play 1](/agentic-discovery/ai-agent-web-search-and-fetch)) - [ ] Put the [weekly tracker](/agentic-discovery/measure-ai-visibility) in place before you change anything — you'll want the before/after ## What are the five surfaces? Every play optimizes one of five surfaces between your product and an AI agent: | Surface | Question it answers | Plays | |---|---|---| | **GET SURFACED** | When an agent searches the open web itself, do you appear, get opened, and survive its verification? | 1 | | **GET FOUND** | When an agent (or its client app) searches a structured index, do you appear — and first? | 2, 3, 4 | | **GET READ** | When an agent fetches your docs, does it get clean, complete, current text? | 5, 6, 7 | | **GET OBEYED** | When the agent has your content in context, does it follow it over its stale training data? | 8 | | **GET INSTALLED** | Are you written into the agent's environment so every future session prefers you? | 9, 10, 11 | The surfaces form the agent's journey, top to bottom: it searches the open web (SURFACED) → pulls structured indexes (FOUND) → reads what it fetches (READ) → obeys directives in context (OBEYED) → and, if you've earned it, prefers you by default in every future session (INSTALLED). For *changing what an agent selects*, our pilots rank them **installed > obeyed > read > found**, with **SURFACED as the entry gate** — the widest, least-owned layer, and a prerequisite for any product the model doesn't already trust. The sequencing below mostly runs in journey order. ## The eleven plays ### GET SURFACED **[Play 1 — Get surfaced in agent web search](/agentic-discovery/ai-agent-web-search-and-fetch).** Before an agent reaches your structured docs it searches the open web itself, opens only ~6% of what it surfaces, and kills ~48% of the self-reported claims it checks. Win the agent's own (long, dated, spec-loaded) query, be worth opening, and make every headline claim corroborable by a primary source. *Who:* everyone — it's the entry gate. *Effort:* ongoing content discipline, no engineering. *Impact:* in our instrumented runs this is where the training prior gets overturned and non-incumbents first break into the set. ### GET FOUND **[Play 2 — Registries & directories](/agentic-discovery/ai-agent-registries-and-directories).** Only four placements show measured impact (the Official MCP Registry chain into VS Code, skills.sh, Anthropic's surfaces, Context7); ~99% of real distribution bypasses the rest. Claim and curate the four, engineer your descriptions around task phrases, skip the junk tier. *Who:* everyone. *Effort:* 1–2 days, then 1 hr/week. *Expected impact:* immediate findability; the description-match win is free in uncontested categories. **[Play 3 — MCP server distribution](/agentic-discovery/mcp-server-distribution).** A docs-search MCP first, then a live server with a sandbox endpoint. The server is the easy half — distribution (registry publish, `.well-known` manifests, per-client install snippets) decides whether it ever gets used. *Who:* API products. *Effort:* 1–3 weeks. *Impact:* in our pilots, agent-operability flipped *selection* when the agent knew about it. **[Play 4 — Agent skills & AGENTS.md](/agentic-discovery/agent-skills-and-agents-md).** A public repo of SKILL.md workflows makes you installable across ~55 agent clients with no gatekeeper; the proven starter set is best-practices + quickstart + migrate-from-competitor. *Who:* devtools with conventions worth encoding. *Effort:* ~1 day for the starter set. *Impact:* vendors' best-practices skills run 100K+ installs; your competitors may already be there. ### GET READ **[Play 5 — llms.txt](/agentic-discovery/llms-txt).** The index file agents and retrieval tools fetch first: sectioned links with one-line descriptions, tiered variants, and — the part most guides miss — a directive section. Honest status: verified infrastructure, unproven ranking magic. *Who:* everyone. *Effort:* hours (free if your docs platform generates it). **[Play 6 — Markdown docs](/agentic-discovery/markdown-docs-for-ai-agents).** Every docs URL serves raw markdown at `.md`; the gold standard also content-negotiates on canonical URLs. Frontmatter, agent banners, machine-readable changelog. *Who:* everyone with docs. *Effort:* hours-to-days; platform choice can make it free. **[Play 7 — Snippet engineering](/agentic-discovery/code-snippets-for-ai-agents).** Retrieval indexes score your docs on five published metrics; density beats bulk (a 440-snippet library outscores a 2,297-snippet one by 18 points). Self-contained, task-shaped, deduplicated snippets — and your own scorer in CI. *Who:* everyone; the biggest lever on retrieval quality scores. *Effort:* 2–4 weeks of docs work. ### GET OBEYED **[Play 8 — The directive layer](/agentic-discovery/stop-ai-using-deprecated-apis).** Agents emit your deprecated APIs because models memorized them. ALWAYS/NEVER directives fix exactly the *stale window* — the months between your API change and the next training run. In our pilot: 100% wrong → 0% wrong on a recent breaking change, and zero effect on ancient history. ~40 tokens per directive. *Who:* anyone who has shipped a breaking change in ~18 months. *Effort:* days, plus a CI eval. ### GET INSTALLED **[Play 9 — Scaffolder rules & CLAUDE.md](/agentic-discovery/scaffolder-rules-claude-md).** The strongest lever we measured: rules files persist in the repo and bias every future agent session. Bun's CLI writes them at `bun init` — disclosed, opt-out-able. Our trials: 100% choice flip. Run it ethically or it backfires. *Who:* products with a CLI/scaffolder touchpoint (soft variants exist for everyone else). *Effort:* days. **[Play 10 — Agent-first onboarding](/agentic-discovery/agent-first-onboarding).** Remove every human step between "agent discovers you" and "passing integration test": keyless modes, no-signup provisioning endpoints, sandbox-by-default keys. Target: first successful API call in under five minutes, zero human actions. *Who:* API/SaaS products. *Effort:* product work, weeks. **[Play 11 — Evals & leaderboards](/agentic-discovery/ai-evals-and-leaderboards).** Build the internal eval harness (deprecation, flip-rate, integration-completion, doc-QA), gate docs changes on it, then publish it as a reproducible public leaderboard — QA tool, tuning loop, and citation magnet in one. *Who:* teams ready to compound. *Effort:* quarter-scale. ## What order should you run the plays in? | Track | Weeks 1–2 | Weeks 2–6 | Quarter 2+ | |---|---|---|---| | **New product breaking in** | **Play 1** + 2 + 5 (claim the empty space and be corroborable in agent search — your entry gate) | 7 → 8 → 4 | 3 → 9 → 11 | | **Incumbent with training-data baggage** | Play 8 first (your old APIs are the threat) + 2 | **1** → 5 → 6 → 7 (you're most exposed to the verification cut) | 3 → 10 → 11 | | **Platform / framework** | Play 2 + 5 | **1** → 4 → 9 (scaffolder is your unfair advantage) | 10 → 11 | ## If you only do three things 1. **Claim your four Tier-1 registry entries and rewrite the descriptions around task phrases** ([Play 2](/agentic-discovery/ai-agent-registries-and-directories)) — highest leverage per hour. 2. **Write the directive section for everything you've deprecated since 2024** ([Play 8](/agentic-discovery/stop-ai-using-deprecated-apis)) — the only play that fixes agents being *confidently wrong* about you. 3. **Ship a best-practices skill** ([Play 4](/agentic-discovery/agent-skills-and-agents-md)) — one day of work, distribution across ~55 agent clients, and the pattern your competitors are already running. ## The receipts The impact ordering (installed > obeyed > read > found) comes from our pilot experiments — single model, n=2–3 per arm, full designs and limitations in [Part 2](/agentic-discovery/how-ai-agents-choose-products) and the [Data Room](/agentic-discovery/data): a rules file flipped product selection 3/3 vs 0/3 control; a 5-line directive cut deprecated-pattern emission from 2/2 to 0/2; an operability fact flipped a recommendation 2/2. Retrieval-layer stats (n=17 audited entries): freshness is the strongest quality-score correlate (ρ=−0.54); corpus mass barely matters (ρ≈0.24–0.30). Field validation: the products running the full stack — measured install counts, scaffolder defaults, eval-tuned rules — are documented in [Part 2](/agentic-discovery/how-ai-agents-choose-products)'s teardowns. ## FAQ **What is the agentic discovery playbook?** Eleven evidence-backed plays for making a product the default choice of AI agents, organized across five surfaces: getting surfaced in the agent's own web search, getting found in registries, getting read by retrieval, getting obeyed over stale training data, and getting installed into the agent's environment. **Which play has the highest ROI?** Per hour invested: registry claiming and description engineering (Play 2). Per absolute impact on agent selection in our pilots: rules files in the agent's environment (Play 9), which flipped choices 100% of the time. **Do I need all eleven plays?** No. Run the audit, pick your track, and ship the week-one pair first. Plays 9–11 assume product surface (a CLI, an API) that not every company has; the soft variants are listed in each play. **How long until results?** Registry and retrieval changes surface within one re-parse cycle (days). Environment-layer effects apply to every new project immediately. Measurement setup (Part 5) should precede everything so you can prove it. --- *Last verified 2026-06-11. 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: [The Agent-Readiness Audit](/agentic-discovery/agent-readiness-audit) · Next: [Play 1 — Get Surfaced in Agent Web Search](/agentic-discovery/ai-agent-web-search-and-fetch) → > **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)