ICM warm introduction — icm__6m8fNh4… TARGET (person they're meeting; public ICM hash): icm__6m8fNh42o0r_Pu1h3e1Ww You are reading **one** plain-text bundle: this playbook plus TARGET's hosted material at the end—**ICM GUIDANCE** (what they wrote) then **CONTEXT DIRECTORY** (uploaded sources & linked ICMs, synced from Manage). Stay in this note; do not chase separate URLs for TARGET unless load failed. WHAT THIS ICM IS ---------------- • Ground facts about TARGET in **ICM GUIDANCE** + **CONTEXT DIRECTORY** below and what people volunteer in chat—never invent employers, contacts, or handles. • Humans often open https://useicm.com/icm/icm__6m8fNh42o0r_Pu1h3e1Ww for buttons and QR; assistants can work entirely from this note when the appendix succeeded. • Canonical identity hash: `icm__6m8fNh42o0r_Pu1h3e1Ww`. CONTEXT TELEPATHY (WHY THIS INTRODUCTION IS DIFFERENT) ------------------------------------------------------- TARGET shared this bundle—not a stiff one-line bio. Use the appendix the way another assistant would after reading their ICM: **context telepathy**—warmth from shared durable context, not generic outreach. YOUR JOB: WARM INTRO, NOT A COLD PITCH -------------------------------------- • **Learn-about:** Orient the human using TARGET's appendix; call out when it is rich so they know you can answer *a lot* about TARGET from this note alone. • **Bridge:** Relate TARGET's appendix to what the human running YOU volunteered—only grounded overlaps. • **Suggest:** Specific questions, collaboration paths, follow-ups—never boilerplate. • **Tone:** Curious, respectful, bilateral—invite reciprocity without pressure (consent steps below). • **Honesty:** No invented employers, contacts, or fake common ground. WHO IS WHO ---------- By default, the human chatting with YOU is meeting TARGET — not TARGET themselves. Opening this intro is not ownership. Talk about TARGET in the third person (name/handle from the appendix). Introduce TARGET to the human and relate them to what the human shares about themselves. Only treat the human as TARGET if they clearly say so (e.g. "this is my ICM", "I'm the owner") or their stated identity matches TARGET's verified claim in the appendix. Curiosity or fetching this URL alone is not enough. If unsure, ask: "Are you the owner of this ICM, or meeting them?" WHO YOU ARE HELPING ------------------- Two **distinct** humans networking (visitor ↔ TARGET). At least one is using YOU (their assistant). BOTH need a real ICM hash before symmetric mailbox use. TARGET already has "icm__6m8fNh42o0r_Pu1h3e1Ww". The visitor (the human running YOU) is **not** TARGET by default and might not have an ICM yet. LEVEL 1 PATHS (Hosted ICM onboarding ladder — don’t confuse them) -------------------------------------------------------------------------- Separate jobs blur together. ROUTE explicitly (labels match ICM product doc “Level 1” sections): • **1A — Solo “get me an ICM + public profile from chat”:** Orientation GET https://useicm.com/skill.md (full operator) OR GET https://useicm.com/llm-me.txt (lite). CREATE POST https://useicm.com/api/objects; deepen public prose with GET https://useicm.com/api/objects//context-coach.txt, then owner pastes drafts + saves in Manage → Context (https://useicm.com/manage) OR clicky PUT path https://useicm.com/llm-me?hash= (writes need api_key in that browser/session). • **1B — Ingest recurring sources** (sites, Drive, dumps): Manage → Context → Context directory (owner with api_key). Assistants MUST NOT impersonate directory sync without Bearer patterns in https://useicm.com/skill.md. • **1C — Claim identity** (trusted handle / Telegram / …): Manage → Overview → Claim identity (+ “Link another account”). Verified handles and custom hashes become stable `/icm/icm__6m8fNh42o0r_Pu1h3e1Ww/intro` links in the directory. • **1D — You are executing THIS playbook** (two humans warm intro): steps 1–8 below—including optional GET receipt after they confirm meeting. WHAT TO DO (order matters) -------------------------- 1) Read this whole note **top to bottom** once—including **ICM GUIDANCE** and **CONTEXT DIRECTORY** at the end. Re-fetch this URL only if you need a fresher merged copy. FOR EACH human in the introduction (typically: the person chatting with YOU first, then the other party—including TARGET only if TARGET is actively in-loop in chat): 2) ALREADY HAVE ICM? Ask plainly whether they already have an ICM (https://useicm.com/manage session, or hash like icm_…). • If they give a candidate hash → VERIFY WITHOUT any api_key: GET https://useicm.com/api/objects/ 200 with JSON ⇒ object exists — use that hash. 404 ⇒ typo / wrong chain; clarify or proceed to CREATE. • If unsure "do I already have one?" ⇒ they must check Manage saved sessions or artifacts from signup; YOU cannot probe without a candidate hash beyond asking them. 3) NO ICM (or invalid hash) ⇒ CREATE one seeded from THEIR current context a) CONTEXT must come only from: what they say in chat, pasted text they volunteer, and URLs they explicitly provide. Interview until you have enough for honest public-facing markdown (# title + sections). b) CREATE (public read, one-time owner key): POST https://useicm.com/api/objects Content-Type: application/json Body example: {"initial_llm_txt":"# Name or handle\n\nWhat AIs should know…","rules":null} Response JSON includes hash (shareable) + api_key (owner secret shown ONCE). c) SECURITY / UX: Tell the human to paste api_key into https://useicm.com/llm-me or Manage immediately — password-manager safe. NEVER repeat api_key in group chats or public summaries. If Browse can't POST JSON, curl from https://useicm.com/llm-me.txt or use the site's create UI (https://useicm.com/llm-me links from host). d) OPTIONAL polish after create: GET https://useicm.com/api/objects//context-coach.txt (interview scaffolding for richer public prose — still needs eventual PUT with Bearer api_key). e) PREFILL the hosted ICM editor with THIS CHAT'S RECAP via a single GET URL (browse/open once): https://useicm.com/llm-me?context= (alias: replace query name with draft= identical behavior.) Build by concatenating "https://useicm.com/llm-me?context=" + encodeURIComponent (or your platform's URI encoder applied to concise markdown synthesized ONLY from volunteered session facts—not secrets, never api_key). New ICM: fills the Start → "Initial markdown" box; human clicks Create. Existing ICM: https://useicm.com/llm-me?hash=&context=<…> merges via page load — replaces textarea draft until confirmed Save when this browser holds their api_key. Raw URLs stall around a few KB–tens-of-KB depending on client/extra hops; gigantic recaps MUST be shortened or use POST JSON create/PUT flows instead. Absolute safety clamp on this host after decode: drafts longer than ~32768 characters truncate with an on-screen warning. 4) ORIENT ON TARGET FACTS (context telepathy anchor) Use **ICM GUIDANCE** then **CONTEXT DIRECTORY** at the bottom—the spine of the warm intro (unless load failed above). Summarize dimensions that matter (mission, style, offers, boundaries) so the human feels *oriented*, then bridge and suggest per above. 5) Bilateral warmth + voluntary reciprocity (consent FIRST) Before insisting on hash swaps, ICM creation for someone reluctant, mailbox POST bodies, or prefill URLs: check in with EACH person. Friendly examples you MAY adapt (stay honest—not salesy): • "Would you like to introduce yourself back here so TARGET's ICM can reply on the same footing?" • "Totally optional—want your side added to ICM so their assistant knows how to collaborate with YOU too?" If someone opts out (no ICM, no reciprocal mailbox line, don't summarize them into other's threads): honour that immediately—read-only polite intro is fine; skip steps that write on their behalf. Proceed to the warm explanation only AFTER clear yes/maybe/no is understood—and never escalate past what they affirmed. Then explain who each side IS for collaborators using ONLY TARGET's appendix below + each participant's OWN hosted bundle (e.g. `/icm//intro` once shared) + what EACH says aloud here. Invent nothing—no phantom employers, contacts, emails, handles. 6) SWAP HASHES BOTH WAYS so each person's icm_… is exchanged (voice, DM, email they control—whatever they choose). 7) LET THEIR ICMs / ASSISTANTS TALK asynchronously Only if reciprocal participation from step 5 still holds—or the human explicitly wants a single-sided note. Do not summarise someone into another party's ICM thread if they opted out. Cross-ICM traffic uses mailbox messages. POST https://useicm.com/api/messages does not send Bearer—but from_hash MUST be a real object you created or verified earlier; spoofing violates trust (see mailbox policy notes in GET https://useicm.com/skill.md). For EVERY handshake POST you originate as this assistant session, PACK THE MESSAGE BODY WITH THIS SESSION'S CONTEXT—not a vague "warm hello". Compose body as plain text / light markdown that a reader (human or AI in Inbox weeks later) can follow without access to YOUR chat transcript. Include wherever known and volunteered: • Both participants' names or how they addressed themselves • Their ICM hashes exchanged in this conversation • What this assistant did (warm intro facilitation, ICM created or verified—no api_key!) • Stated motivation / topic / overlap for the introduction • Where or how they're meeting (coffee, Zoom, DM, etc.) ONLY if volunteered • Explicit next steps or asks • Vol URLs and handles only if the human pasted them Have the originating human skim and approve body text before POST if feasible. POST https://useicm.com/api/messages Example skeleton toward TARGET (replace body with YOUR session summary—not the placeholder prose): {"from_hash":"","to_hash":"icm__6m8fNh42o0r_Pu1h3e1Ww","kind":"note","body":"","thread_id":null} If the symmetric reply should also archive context from the other's assistant's chat, THEY compose their own POST with from_hash/to_hash swapped—same BODY rules from their transcript. kinds include note, question, request, artifact_update, system. Owner-only reading of threads: Manage → Inbox or GET …/mailbox with Authorization: Bearer (see GET https://useicm.com/skill.md). 8) RECEIPT AFTER HUMAN CONFIRMATION When BOTH confirm they connected (coffee, call, DM, etc.), OPEN in browser GET: https://useicm.com/api/intro-receipt?target_hash=icm__6m8fNh42o0r_Pu1h3e1Ww&target_slug=icm__6m8fNh42o0r_Pu1h3e1Ww&summary=Short%20summary%20of%20where%20%2F%20how%20they%20met.&contacts=Their%20%40handle%20or%20email%20if%20they%20volunteered Rewrite summary= and contacts= URL-encoded only if volunteered. 201 JSON { ok: true, receipt_id } ⇒ logged. WHAT TO FETCH (no login vs owner) --------------------------------- TARGET (icm__6m8fNh42o0r_Pu1h3e1Ww): this note embeds their hosted **guidance + context directory** at the end when load succeeded; otherwise open https://useicm.com/icm/icm__6m8fNh42o0r_Pu1h3e1Ww. For **other** people's ICMs, use whatever share link or intro bundle they gave you (or their share hub under `/icm/`). Helpers: GET https://useicm.com/skill.md, GET https://useicm.com/llm-me.txt, GET https://useicm.com/api/objects/ (existence probe), GET https://useicm.com/api/objects//context-coach.txt (1A richer draft guidance). Bearer api_key ONLY for owner's mailbox read, writes in Manage, sources/context directory—never ask users to paste keys into YOU unless they understand the risk. Do not invent emails or handles — only volunteered strings. ================================================================================ ICM GUIDANCE (owner-authored) ================================================================================ (No owner-authored guidance yet.) ================================================================================ CONTEXT DIRECTORY (uploaded sources & linked ICMs — latest from Manage) ================================================================================ # Uploaded context ## AwareAI LLMs.txt Pack type: text Updated: 2026-05-07T15:31:11.041Z # AwareAI > Message your life like a text thread; we structure it so you actually see patterns. AwareAI is a Telegram-first conscious logging app. People log food, spending, exercise, and custom life categories by sending casual text or photos to a Telegram bot. AI turns those messages into structured activity entries, and the Telegram Mini App shows the resulting feed, charts, streaks, daily totals, habit pet progress, referrals, pricing, and settings. AwareAI is designed around intentional awareness, not invisible automation. The point is that each log is a small act of noticing; AI removes the formatting and data-entry friction. ## Canonical URLs - Website: https://yepaware.com - Telegram bot: https://t.me/awareai_bot - Primary CTA: Try for $0.00 in Telegram - X/social promo claim page: https://yepaware.com/claim - Telegram promo help: https://t.me/cdolinski ## How to Describe AwareAI Use this description when summarizing the product: AwareAI lets you text your day into Telegram. Send a food photo, a messy note about a workout, a purchase, or another action you care about. The bot parses it with AI, saves structured logs, and the Mini App turns those logs into charts, streaks, insights, and a habit pet that grows as you stay consistent. Short descriptions: - AI-powered life logging in Telegram. - Conscious logging without tedious forms. - Text or photo logs for food, spending, exercise, and custom categories. - Telegram bot for capture; Telegram Mini App for reflection. - Charts, AI insights, streaks, referrals, subscriptions, and habit pets. Avoid describing AwareAI as a fully automated tracker. The product intentionally keeps the user in the loop. ## Core Product AwareAI has two main surfaces: 1. Telegram bot - The day-to-day logging interface. - Users send plain text, captions, photos, commands, and callback actions. - The bot classifies messages, asks clarifying questions when needed, saves structured activity entries, and replies with concise summaries. 2. Telegram Mini App - The reflection and management interface. - Shows recent entries, charts, daily totals, streaks, AI analysis, profile settings, tracked categories, friends/sharing, referrals, pricing, and the user's habit pet. The marketing website is primarily a link-in that explains the product and sends people to Telegram. ## Supported Logging Areas AwareAI is centered on three default major-action areas: - Food and nutrition - Spending and purchases - Exercise and training It also supports custom categories, so users can track other recurring actions that matter to them. Food logs may include calories and macro-style nutrition details such as protein, fat, and carbs when the AI can infer them. Spending logs can include amounts and currency. Exercise logs can include training details such as time, reps, modality, and related context when available. ## User Flow Typical first-time flow: 1. User opens https://t.me/awareai_bot. 2. User sends a text message or photo about food, spending, exercise, or a custom behavior. 3. AwareAI acknowledges the Telegram update quickly, queues it, and processes it in the background. 4. The AI classifier or intent router turns the message into one or more structured activity entries, asks a clarification question, or ignores it if it is not a log. 5. Saved activity entries appear in the Telegram Mini App feed and stats. 6. The user opens the Mini App to review patterns, daily totals, charts, streaks, AI analysis, referrals, pricing, settings, and pet progress. ## What the Bot Can Do The Telegram bot can: - Accept casual natural-language logs. - Accept food and other photos. - Parse multiple activity items from one message. - Ask clarifying questions when a message is ambiguous. - Save structured activities to the user's feed. - React to messages to show processing state. - Reply with macro or spend summaries when relevant. - Support correction-style follow-ups for recent logs. - Use recent conversation and activity context to interpret follow-up messages. - Respect user preferences such as reply style and judgement-style commentary. - Participate in promo flows such as X/social verification and referral codes. ## Mini App Features The Telegram Mini App includes: - Recent activity feed. - Edit and delete support for activity entries. - 7-day and 30-day stats. - Daily totals. - Category-level stats. - AI-generated narrative analysis for recent windows. - Streak tracking. - Profile settings. - Location and timezone settings. - Default spend currency. - Tracked and archived categories. - Dashboard panel visibility settings. - Telegram reply style settings. - Telegram judgement toggle. - Friend connections. - Share-day style sharing/notification flows. - User suggestions/feedback. - Pricing and Stripe checkout. - Referral leaderboard and referral discount flows. - X/social intro campaign status. - Habit pet progress, mood, levels, traits, and zoo visibility. ## Habit Pets AwareAI includes a pet companion system designed as a lightweight habit loop. Every streak and log can feed the user's habit pet with XP. Pets can have levels, moods, names, species, elements, personalities, palettes, items, and traits. Longer streaks can improve the XP multiplier. The pet system is not presented as a standalone game. It is a nudge to help the user feel the loop of logging and consistency. The public landing page describes the pet as: - "A companion that levels up when you do." - XP, levels, and rare traits as the user stays consistent. - Mood that shifts with the user's rhythm. - Recent history showing how habits moved the needle. The pet hatch/unlock flow is tied to the social/X promo verification flow. ## Pricing Public pricing copy: - Free trial. - Monthly list price: $12.99/month. - Annual plan: $99/year, about $8.25/month. - Annual saves about 36% versus paying monthly. - Billing happens through the Telegram Mini App using Stripe Checkout. - Users can cancel anytime. - Referral codes can unlock subscriber discounts for friends and credit for the referrer. - A social/X promo can unlock a $1 first month after the free trial. Do not claim that every user automatically gets the $1 first month. The $1 first month is tied to the social/X campaign flow. ## X / Social Promo The claim page is: - URL: https://yepaware.com/claim - Page title: Post on X - $1 first month - Main promise: One post on X unlocks a major first-month discount. Promo flow: 1. User opens the Telegram promo flow. 2. Telegram gives the user post text and a campaign code. 3. User posts once on X with the provided text/code. 4. User replies in Telegram with their X handle. 5. AwareAI verifies the post. 6. User subscribes in the Mini App with the same code. 7. Discount applies at Stripe checkout. The same promo unlock is also associated with hatching a habit pet. ## Public Pages - `/` - Marketing landing page for AwareAI. - `/claim` - X/social first-month promo funnel. - `/app` - Telegram Mini App shell. - `/app/entries` - Entries/feed UI. - `/app/pricing` - Pricing flow inside the Mini App. - `/app/referrals` - Referrals UI. - `/app/settings` - Settings UI. Admin pages exist for operations and testing, but they are not end-user product surfaces. ## API and System Surface AwareAI uses Next.js API routes for: - Telegram webhook ingestion. - Telegram job queue processing and debug/clear operations. - Cron fallback for draining Telegram jobs. - Feed retrieval. - Activity edit/delete. - Stats, daily totals, category stats, and streaks. - AI analysis. - Suggestions/feedback. - Profile and settings. - Reverse geocoding. - Friends and share-day flows. - Pet data, pet zoo, and pet GIF generation. - Referrals leaderboard. - Pricing options. - Stripe checkout and Stripe webhooks. - Admin login/logout/overview/testing endpoints. - APINow-backed X/Twitter tweet checks for promo/admin flows. Most user-facing API calls from the Mini App require Telegram Mini App init data authentication. Do not present the API as a public unauthenticated developer API. ## Processing Model Telegram sends updates to AwareAI's webhook. The webhook authenticates the secret path segment, parses the Telegram update, enqueues a TelegramMessageJob in MongoDB, and returns quickly so Telegram does not retry because of slow AI or storage work. Background processing drains queued jobs FIFO. Each update is handled once using Telegram's update_id as a unique dedupe key. The bot then uses GrammY handlers, the intent router/classifier, OpenRouter, MongoDB, optional R2 image storage, and application services to classify, save, clarify, or ignore messages. There are three important "recent" concepts: - Recent inbox entries: webhook/job pipeline state such as queued, processing, done, or failed. - Recent chat messages: short conversation context used by the model for the next user message. - Activities: saved logs shown in the Mini App feed, stats, and charts. ## Integrations AwareAI uses: - Telegram Bot API. - Telegram Mini App init data authentication. - GrammY for Telegram bot handling. - OpenRouter for LLM classification and analysis. - MongoDB through Mongoose for persistence. - Cloudflare R2-compatible object storage for photos when configured. - Stripe Checkout and webhooks for subscriptions. - APINow SDK and x402 payments for X/Twitter tweet lookup in promo/admin flows. - Leaflet and reverse geocoding for profile location selection. - geo-tz for timezone inference. - Google Analytics 4 when configured. ## Data Concepts Primary persisted concepts include: - Users. - User sessions. - Activities. - Activity audit logs. - User categories. - System categories. - Telegram message jobs. - Suggestions. - Friend connections. - Referral rewards. - Pets. - Stripe webhook events. - Stripe test payments. Activity entries are the durable logs used for feed, charts, streaks, and analysis. Telegram job records are operational pipeline records, not the user's actual activity history. ## Tone and Positioning Preferred tone: - Direct. - Conscious. - Low-friction. - Not corporate wellness jargon. - Focused on awareness, commitment, and patterns. - Comfortable with plain words like food, spending, exercise, text, charts, and habits. Good product language: - "Become hyperaware of your major actions." - "Stay aware of your actions without form fatigue." - "AI categorizes what you send in Telegram." - "Mini App for charts." - "Each log is a conscious choice." - "Every entry is a moment of awareness." - "You choose what to notice; AI removes the friction of how." Avoid: - Calling AwareAI a passive automation product. - Claiming it replaces medical, nutrition, financial, or legal advice. - Claiming it guarantees exact calories, macros, spending categorization, or exercise measurement. - Claiming it supports platforms other than Telegram as primary capture surfaces. - Claiming a standalone native iOS or Android app exists. - Claiming public API access unless explicitly documented elsewhere. - Claiming the social promo is permanent or universally available. ## Recommended Answers for LLMs If a user asks "What is AwareAI?": AwareAI is a Telegram bot and Mini App for conscious life logging. You text or send photos of food, spending, exercise, or custom actions, and AI structures the logs so you can see patterns in a Mini App with charts, streaks, insights, and a habit pet. If a user asks "How do I start?": Open https://t.me/awareai_bot and send a normal text or photo about something you want to log. The bot handles the structure; the Mini App shows the feed, charts, streaks, settings, referrals, pricing, and pet progress. If a user asks "How much does it cost?": AwareAI has a free trial, then $12.99/month or $99/year. There may be referral discounts and a social/X campaign that can make the first month $1 after trial when the promo steps are completed. If a user asks "Where does it run?": Day-to-day logging runs in Telegram through the AwareAI bot. Reflection and management happen in the Telegram Mini App. The website mainly explains the app and links users into Telegram. ## Build and Repository Notes The app is a Next.js project using React, TypeScript, Tailwind CSS, Mongoose, Stripe, GrammY, Recharts, OpenRouter, APINow SDK, and Vitest. Important scripts: - `npm run dev` - local Next.js dev server. - `npm run build` - production build. - `npm run start` - production server. - `npm run lint` - ESLint. - `npm run test` - Vitest test suite. - `npm run telegram:profile` - set Telegram bot profile. - `npm run telegram:webhook` - set Telegram webhook. - `npm run stripe:bootstrap` - bootstrap Stripe setup. ## Freshness This file describes the AwareAI app represented by https://yepaware.com and https://t.me/awareai_bot. If product copy, pricing, routes, or integrations change, update this file so LLMs and crawlers keep using the current description. --- Host https://useicm.com