erekle chakvetadze

Former sales closer building AI tools for small businesses.

Ready for work

erekle is ready for their next project!

Italy

Work About

Italy

A Telegram bot built as a parallel layer to a productivity system, designed to intercept moments of negative impulse and convert them into structured reflection conversations. How it works: Every user message triggers an AI intervention conversation grounded in the user's Chief Definite AIM, recent insights, current goal pacing, and reflection history Voice messages auto-transcribed via OpenAI Whisper, treated as text turns in the conversation /done command ends the session, prompts trigger word + outcome (avoided / indulged / unclear), persists everything to SQLite for downstream daily summary integration /restart wipes session state for fresh context System prompt is brother-tone, AIM-grounded, 80–200 words per response, deliberately not therapy-speak Runs in the same Node process as a separate productivity bot — two bots, two tokens, one codebase. Tech: Node.js, Telegram Bot API, Claude API, OpenAI Whisper, SQLite.

A weekly and monthly AI suggestion engine that ingests the full user state and returns three ranked, goal-aligned recommendations per call. What goes into the LLM context: Chief Definite AIM (text, target, deadline, days remaining, current balance, pace status) Perpetual goals (with AIM-link flags so aligned goals weight heavier) Non-negotiable habits and their streaks Recent insights with integration status (active / implemented / integrated:date) Last 7–14 daily summaries Past 28-day (weekly) or 90-day (monthly) suggestion history — for recursive learning What it returns: three suggestion cards per call, each with priority + difficulty + AIM-alignment + tags + rationale. Includes: Intent gate — default AIM-aligned mode vs. custom prompt mode Auto-detected response shape (ranked / analysis / hybrid) Unified rate limiting across four endpoints (weekly default, monthly default, weekly custom, monthly custom) Persistence to suggestion_history table for the next round's recursive context Tech: Claude API, OpenAI API, custom prompt engineering, SQLite, Node.js, in-memory rate limiting.

Cover image for A goal-tracking sub-system that grounds

A goal-tracking sub-system that grounds an AI assistant in the user's full life-state — target amount, hard deadline, days remaining, current balance, pace status (ahead / on-pace / behind), and reflection streak. Core features: Multi-entry timestamped reflection log — plain Enter submits, Shift+Enter newline, optimistic UI, all entries inside one unified container with centered timestamp dividers Ephemeral Summarize chat modal — loads today's braindumps as live AI context, brother-tone system prompt, conversation NOT persisted (privacy by design) Nightly auto-summary cron at 23:55 — pulls reflections, runs through Claude, creates a standalone daily summary that downstream AI engines pick up automatically Pace analysis — surfaces required-vs-actual daily rate, projected gap at deadline, status flag Each AI engine pulling this data adapts its suggestions based on whether the user is ahead or behind on their goal — recursive context that compounds over time. Tech: Claude API, SQLite, Node.js cron, custom retrieval logic.

Cover image for A multi-feature productivity system shipped

A multi-feature productivity system shipped in 36 hours using Claude Code. Built on Node.js + SQLite with a plain HTML/JS frontend, deployed to Fly.io (http://Fly.io). Visible in this view: Perpetual Goals — circle-grid tracker with three-state cycle (empty/done/missed), today highlighted, auto-extends on miss, AIM-link badge, optional repository for archived goals. Each goal links to a daily task description. The Frog — single most important task of the day, locked once set, with a Future Frogs queue for upcoming priorities. Weekly / Monthly / Long-Term tabs — each with a Suggest button that calls an AI engine grounded in the user's Chief Definite AIM, deadline, current balance, pace status, perpetual goals, recent insights, and prior suggestion history. Returns three ranked, AIM-aligned recommendations per call. Includes a Custom Prompt mode with auto-detected response shape. Goal-creation form — name, daily task description, target days, plus an AIM-link toggle that weights AIM-aligned goals heavier in the suggestion engine. Tech: Node.js, Express, node:sqlite, Claude API, OpenAI Whisper, Fly.io (http://Fly.io) cron, plain HTML/CSS/JS (no framework, no build step).