A weekly system that turns one “core idea” into a high quality long form asset (newsletter or blog post), then repurposes it into short form social content (X thread, LinkedIn post, atomic posts). A searchable personal “Content Vault” (for example, Manus) makes the workflow faster by letting you retrieve your best prior stories, frameworks, and phrases on demand. References: New Manus 1.6 Is Cracked (Absorb Years Of Your Best Thinking In Minutes) Weekly goal 1 long form piece (publish ready) 10 to 20 short form assets derived from it Scheduled distribution for the week Weekly deliverables Newsletter or blog post: 1 X thread: 1 LinkedIn post: 1 Atomic posts: 5 to 10 Scheduling plan: 1 week

A reproducible, step by step process to create a complete brand kit (strategy, voice, visuals, and usage guidelines) that stays consistent across AI generated outputs. Who this is for Founders, brand strategists, designers, marketers, and teams who want a repeatable way to build and maintain brand assets using AI without losing human judgment. Repository and file structure (recommended) Use a single shared workspace (GitHub, Drive, Notion) with consistent naming. Reference: A Guide to Building Brands for Humans & Agents

A step by step process for building a conversational AI bot that evolves from simple deflection to active selling. Based on HubSpot's SalesBot methodology. When to use: When your team handles significant live chat volume and wants to automate low intent conversations while preserving human attention for high value prospects. Preconditions: Active live chat channel with measurable volume Access to historical chat transcripts (1,000+ conversations) At least one top performing human agent to define quality standards AI/ML capability (in house or vendor) for RAG architecture and propensity scoring Key principle: Build human operations first. Quality training data and human examples define what "good" looks like before automation. Source: What We Learned Building HubSpot's SalesBot

Turn every new lead into a scored, routed action item — automatically. Claude scores each lead 1–10 based on your ideal customer profile, then tags it Hot, Warm, or Cold so you know exactly who to call first. What this replaces: Manual lead review, gut feel prioritization, or expensive agency "AI powered lead scoring" setups. What you need to start: A list of leads (even just names + emails + how they found you) 5 minutes to describe your ideal customer Access to Claude (claude.ai or the API) How it works: 1. You describe your ideal customer in plain English 2. Claude builds a custom scoring system for your business 3. Claude scores test leads so you can calibrate 4. You set routing rules (or just use the defaults) 5. Claude scores and routes every new lead going forward Time to set up: 15 minutes for steps 1–4. Step 5 runs on every new batch of leads. No coding required. Everything runs through copy paste prompts or directly inside Epismo.

A reusable pack for practicing customer interviews through realistic roleplay. During roleplay, the assistant acts like a plausible customer and answers from lived experience rather than theory. After the roleplay ends, the assistant switches to debrief mode and coaches the interviewer on question quality, signal captured, bias introduced, and the best follow up questions. Why this pack exists Most teams know customer interviews matter, but they do not get enough reps. When they do interview, they often ask leading questions, jump to solution feedback too early, or collect vague opinions instead of concrete behavior. Roleplay is not a substitute for real interviews, but it is useful for learning pacing, wording, neutrality, and listening. Core stance Two modes only: 1. Roleplay Mode: be a realistic customer, not a coach. 2. Debrief Mode: be a sharp coach, not a cheerleader. What this pack is optimizing for Better practice on discovery interviews that stay grounded in recent real behavior, not hypothetical future intent. The interviewer should have to earn insight by asking open, neutral, behavior based follow ups. When to use it Use when the user wants to practice customer discovery, problem interviews, solution interviews, onboarding interviews, churn interviews, buyer interviews, or JTBD style switch interviews. When not to use it Do not use as a replacement for real user research. Do not treat roleplay output as market truth. Do not use it to validate an idea by collecting polite praise. Expected duration 10–25 minutes for roleplay, then 5–10 minutes for debrief.