Public playbooks
Find a method for your next project and explore public cases that used it.
Use this workflow when an enterprise prospect or customer asks for a product capability, integration, security requirement, support model, SLA, or other commitment that may require additional company investment. The goal is to decide whether the company should make the commitment, and in what form. AI helps gather evidence and structure the decision. Sales, Product, Engineering, and customer-facing teams review the assumptions and make the final call.
A practical, batch-agnostic playbook for writing, reviewing, and defending a Y Combinator application. Suitable for idea-stage, launched, revenue-generating, and technical startups. Outcome: a clear English application supported by an evidence ledger, honest stage-appropriate metrics, founder and market insight, a founder video outline, and interview preparation. Operating principles: Lead with what the product actually does. Answer each prompt directly, then support the claim with specific, verifiable facts. Separate what has been done, observed, inferred, and planned. Show founder-specific achievements, customer understanding, execution, competitive insight, and credible potential to grow. Use plain English. Do not invent users, revenue, quotes, credentials, or results. Start with minimal context. Gather company details and evidence progressively in the steps, only when relevant. No batch deadlines or preset schedule. Exact form questions and constraints are checked when available. References live in each step's Resource Hints. The included review rubric is an editorial tool, not an official YC scoring system.
Take a product opportunity from first principles through a scoped build, independent validation, launch, and learning.
Adaptive mission control for software engineering with Poteto Mode. It turns an open-ended request into a checkable mission, lets pstack choose the right execution mode from focused work to swarm or autopilot, and preserves just enough durable context to make long-running work easy to review, pause, resume, or hand off. When a run produces a reusable method or correction, it captures that learning without adding ceremony to routine work. Use or create an Epismo Case only when the mission benefits from durable coordination.
Move from a customer problem through discovery, validation, strategy, a build-ready PRD, launch, measurement, and the next product decision.
Turn a consequential question into a decision and an executable plan. Start proportionally, investigate only what could change the choice, use specialist skills when the decision calls for them, then make one recommendation with a clear path to act. Use when: there is a real choice or problem to resolve, more than one viable move exists, or the result needs a deliberate plan. Do not use for: simple factual lookup, straightforward drafting, trivial reversible choices, or work where the requested action is already unambiguous. Working convention: keep intermediate work in runtime-private scratch state and return a concise decision brief and action plan in the conversation. Do not create tickets, files, Cases, or Records unless the requester explicitly asks for durable collaboration or an export.
Use when someone has an Epismo account but no Playbook yet, and does not know what to write. Sets up the surface and the Epismo skill, finds the recurring work already living in their environment, filters it to the one thing a single skill cannot carry, writes it with input, output, and harness pinned so a stranger's agent can rerun it, then rehearses it against real past evidence and publishes it on the owner's go-ahead. Ends in one session with a working setup and one published, aliased Playbook — not a library plan. Quickstart — choose an install route, then say one sentence. macOS or Linux: `curl -fsSL https://epismo.ai/install.sh | sh`. Windows PowerShell: `irm https://epismo.ai/install.ps1 | iex`. npm: `npm install -g epismo`. You can also download native binaries and SHA-256 checksums directly from https://github.com/epismoai/cli/releases. Then run `epismo login`. MCP: add https://mcp.epismo.ai/ as a Streamable HTTP server with OAuth. Then prompt your agent: "Use pb:epismo/first-playbook to build my first Playbook." It will read this guidance, look at what you already do, and come back with a candidate — you only decide what to publish and to whom. Everything else is in the Steps below. Execution convention: keep intermediate materials in runtime-private scratch state, not in the user’s repository. After each meaningful step, present a concise, human-readable summary in the conversation. Create a local file only when the user explicitly asks to export one.
Turn a request into a well-designed, tested, reviewed, and verified software change.