Skip to content
View unisone's full-sized avatar
:electron:
Context is consciousness.
:electron:
Context is consciousness.

Block or report unisone

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
unisone/README.md

Alex Zaytsev

Product systems analyst who ships production AI — 7+ years in ProdOps, now building it

     

 

What I do

I spent seven years as the person who kept streaming products shipping — requirements, release management, incident response, and the analytics that told us whether any of it worked. Biweekly releases across seven platforms, high-severity incident response, and a QA org to run.

Now I build the software too. Most of my current work is a production AI customer engagement platform: WhatsApp-first lead handling, autonomous agent routing, freight quoting, and an operator console — Next.js, React, Supabase, multi-tenant RLS.

The combination is the point. I write the acceptance criteria and the code, so specs survive contact with implementation.

 

Open source

openclaw-config ⭐14 Production-tested OpenClaw configs — hardening, memory engine, skill routing, agent personas, CI security scanning
self-improving-skills ⭐6 Closed-loop skill improvement for AI agents: Observe → Inspect → Amend → Evaluate
claude-learner Every mistake becomes a rule — analyzes Claude Code sessions and auto-generates CLAUDE.md improvements
intel-skill Market intelligence in seconds — gaps, competitors, sentiment, pricing, trends. No API keys required
claude-toolkit Techdebt scanner + git worktree parallelization for AI coding tools
openclaw-skill-suite Curated agent skills — design inspiration, product demo video, security scanning
ai-prompts Personal AI prompt library, organized by category

 

Currently building

Private work, described rather than linked:

  • AI customer engagement platform — autonomous WhatsApp agent, freight quoting, proposal generation, real-time operator console. Next.js 16 · React 19 · Supabase · OpenAI
  • Domain-neutral workflow compiler — validates declarative domain packs, routes goals without executing them, compiles deterministic plans into verifiable bundles. Zero runtime dependencies
  • Self-hosted SEO intelligence — replaces a paid SEO data vendor for multi-market rank tracking and SERP analysis

 

Stack

TypeScript Next.js React Tailwind CSS Node.js Python Supabase PostgreSQL Vercel

Claude Code OpenClaw Cursor Vercel AI SDK Playwright Vitest

Jira Confluence Datadog Amplitude Snowflake

 

Austin, TX · open to AI/GenAI analyst, product ops, and technical PM roles

Popular repositories Loading

  1. openclaw-config openclaw-config Public

    Production-tested configs, scripts, and workspace templates for OpenClaw. Hardening guides, memory engine, skill routing, agent personas, and CI security scanning.

    Shell 14 2

  2. self-improving-skills self-improving-skills Public

    Self-improving skills for AI coding agents. Closed-loop system: Observe → Inspect → Amend → Evaluate. Works with Claude Code hooks and slash commands.

    Shell 6

  3. ai-prompts ai-prompts Public

    Personal AI prompt library organized by category

    1

  4. claude-learner claude-learner Public

    🧠 Every mistake becomes a rule. Analyze Claude Code sessions and auto-generate CLAUDE.md improvements.

    TypeScript 1

  5. openclaw-skill-suite openclaw-skill-suite Public

    Curated agent skills for OpenClaw — design inspiration, product demo videos, security scanning

    Shell 1

  6. unisone unisone Public

    GitHub profile README