> ## 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 Case Studies: 10 Company Teardowns" description: "How Better Auth, Bun, Stripe, Tailwind, Convex and more win (or lose) AI-agent discovery — evidence-based teardowns with verbatim receipts and copyable lessons." slug: /agentic-discovery/case-studies series: The Agentic Discovery Playbook — Case Studies last_verified: 2026-06-11 --- # Case Studies: What the Winners (and the Paradoxes) Actually Do > **In short:** Ten company teardowns from our 18-product audit, each built on verbatim evidence — what they shipped, the numbers it produced, what to copy, and what only works because of who they are. Three breakout stories, three engineered mechanisms, two incumbent paradoxes, two live tensions. Snapshot date 2026-06-11. The playbook tells you what to do. These pages show you who already did it — with receipts. Every claim traces to our audits and the [Data Room](/agentic-discovery/data); every page ends with a "what NOT to over-copy" section, because the fastest way to waste a quarter is imitating an incumbent's privilege instead of a challenger's mechanics. ## The breakouts — products that won without a training-data prior **[Better Auth: #2 docs source at two years old](/agentic-discovery/case-studies/better-auth)** No prior, mediocre trust score, more agent retrieval traffic than React. The anatomy of a break-in — and which part of it is actually replicable. **[DodoPayments: taking the "payments" query Stripe never claimed](/agentic-discovery/case-studies/dodopayments)** Description engineering in its purest form: the registry description states the task, so the task query returns them — not the incumbent. **[Resend: the smallest corpus with the highest score](/agentic-discovery/case-studies/resend)** Benchmark 92.3 on a corpus a fraction of its rivals' size, plus the only `.well-known` agent-discovery manifests we found in the wild. ## The mechanisms — engineered loops you can copy **[Bun: the growth hack that is a filename](/agentic-discovery/case-studies/bun)** `bun init` writes `use-bun-instead-of-node-vite-npm-pnpm.mdc` into every project — disclosed, opt-out-able, and measured (the mechanism flipped agent choice 100% in our pilots). **[Next.js: what running every play at once looks like](/agentic-discovery/case-studies/nextjs)** Docs inside the npm package, AGENTS.md by default at scaffold time, content negotiation, a public benchmark. The maximalist reference build. **[Convex: the eval-driven operator](/agentic-discovery/case-studies/convex)** Rules tuned "using rigorous evals," a public LLM leaderboard, and a CLI that keeps customers' AGENTS.md current. Measurement as the strategy, not the afterthought. ## The incumbents — privilege, and what it costs **[Stripe: fighting its own training-data ghost](/agentic-discovery/case-studies/stripe)** The 265K-snippet docs index and an llms.txt that orders agents to never recommend Stripe's own legacy API. The incumbent problem isn't absence — it's being confidently wrong in the model's memory. **[The Tailwind Paradox: top-10 with zero agent surface](/agentic-discovery/case-studies/tailwind)** No llms.txt, no markdown, no MCP — carried by training-data mass and third-party volunteers. Why that path is closed to you, and where it leaks even for them (agents emit obsolete v3 config 100% of the time). ## The tensions — live experiments worth watching **[Clerk: docs written for agents, not developers](/agentic-discovery/case-studies/clerk)** The strongest instruction layer we audited paired with the weakest retrieval-quality score among winners. Instruction vs retrieval investment — the natural experiment is running now. **[Drizzle: 440 snippets that beat 2,297 (with Polar and Hono as contrasts)](/agentic-discovery/case-studies/drizzle)** Minimal-but-dense beats full-stack-but-stale (Polar) and exemplary-but-uncurated (Hono). Density is the rubric. ## Which case study for which play? | If you're working on… | Read | |---|---| | Registries & description engineering ([Play 2](/agentic-discovery/ai-agent-registries-and-directories)) | DodoPayments · Drizzle | | llms.txt & directives ([Plays 5](/agentic-discovery/llms-txt), [8](/agentic-discovery/stop-ai-using-deprecated-apis)) | Stripe · Clerk · Tailwind (the cost of skipping it) | | Markdown & snippets ([Plays 6](/agentic-discovery/markdown-docs-for-ai-agents), [7](/agentic-discovery/code-snippets-for-ai-agents)) | Next.js · Resend · Drizzle | | MCP & skills ([Plays 3](/agentic-discovery/mcp-server-distribution), [4](/agentic-discovery/agent-skills-and-agents-md)) | Better Auth · Resend · Convex | | Scaffolders & environment ([Play 9](/agentic-discovery/scaffolder-rules-claude-md)) | Bun · Next.js · Convex | | Evals & leaderboards ([Play 11](/agentic-discovery/ai-evals-and-leaderboards)) | Convex · Next.js | ## How to read these All ten are point-in-time teardowns (2026-06-11; single-day metrics carry ±10% error bars) of *surviving winners plus two deliberate counterexamples* — survivorship caveats are stated in each file, and items we couldn't verify are flagged UNVERIFIED rather than asserted. They are anecdotal evidence by design: the systematic data lives in [Part 2](/agentic-discovery/how-ai-agents-choose-products) and the [Data Room](/agentic-discovery/data); these pages supply the texture the aggregates can't. ## FAQ **Are these endorsements or paid placements?** Neither. Companies appear because they showed up in our research data; none were contacted, none paid, and the counterexamples didn't volunteer. Critique and praise both trace to published evidence. **Will these be updated?** Quarterly, with the rest of the guide — case studies are re-snapshotted and changes logged in the [Data Room](/agentic-discovery/data). A teardown that ages badly is itself a finding (see openclaw's −50% month in Part 2). **Why isn't [company] here?** The set covers the 18 products in our original audit, selected for lesson density. Suggest additions via the contact page — products with a measurable, distinctive mechanism get priority. --- *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: [GEO Myths: What Doesn't Work](/agentic-discovery/geo-myths-what-doesnt-work) · Next: [How Better Auth Became AI Agents' #2 Docs Source](/agentic-discovery/case-studies/better-auth) → > **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)