F
FolderAI
Работает · 110 файлов · 7 фич за эту неделю

Массовый редактор файлов
для AI.

Одно предложение превращается в готовую к запуску папку agent folders. Потом редактируй десятки файлов за раз.

Начать бесплатно →Смотреть пайплайн ↓

Бесплатный план · вход по magic link · работает с Claude, GPT, Gemini

$79 · Ch1 freeновое

Prompting Sentinel

The world's strongest prompting simulator. Specs, dials, defenses, ship.

$99 · Ch1 free

Automation AI Engineer

Ralph-loop, TDD prompts, parallel worktrees, self-healing pipelines.

folder/sales-agent-clothing-brand
├ core/
│  ├ identity.md      ← brand voice + tone
│  ├ rules.md         ← what we will & won't do
│  └ pipeline.md      ← end-to-end flow
├ agents/
│  ├ qualifier.md     ← scores incoming leads
│  ├ writer.md        ← drafts the reply
│  └ reviewer.md      ← checks for off-brand language
├ workflows/
│  └ inbox_triage.md  ← step-by-step on new DM
└ tools/
   ├ catalog_lookup.md
   └ size_chart.md

Проблемы, которые мы решаем

Так больше не надо.

F1Решено

Vague intake

3-question quizzes can't capture a serious system.

Adaptive 7-step onboarding for pro & business tiers.

F2Решено

AI guesses too much

Generators spit out files without ever asking what you mean.

Interactive CLARIFY dialog — AI grills you with targeted questions before generating.

F2.5Решено

Endless typing on clarify

Answering 5 questions over chat is friction.

AI proposes complete answers — one click to fill, edit if needed.

F3Решено

Output locked in the app

You can see your folder but you can't take it anywhere.

One-click ZIP — production-ready folder, plug into Claude / GPT / Gemini.

F4 + F5Решено

Can't iterate, can't see what it does

Generated and walked away — now what?

Refine via chat (AI updates files in place) + capability map of every role.

🔥Решено

Generated ≠ correct

Beautiful files. Are they consistent? Complete? Aligned with your goal?

Grill folder mode — AI critiques itself, surfaces gaps, contradictions, dead refs.

Под капотом

8 этапов, полностью в прямом эфире.

Наблюдай за каждым этапом в реальном времени. Останови, разветви или уточни на любом шаге.

  1. ЭТАП 1
    QUIZ
    →
  2. ЭТАП 2
    REQUEST
    →
  3. ЭТАП 3
    CLARIFY
    →
  4. ЭТАП 4
    ARCHITECT
    →
  5. ЭТАП 5
    WRITER
    →
  6. ЭТАП 6
    OPTIMIZER
    →
  7. ЭТАП 7
    CONFLICT
    →
  8. ЭТАП 8
    EXECUTION

От mihalkevich.com · сделано с FolderAI

Симуляторы — попробуй перед тем, как строить.

Бесплатные площадки для трафика. Платные треки для навыков. B2B-спецификации для команд. Каждая карточка работает на одном движке FolderAI.

3 бесплатных · без регистрации13 платных трека · от $94 B2B-спека · под запрос

Free simulators(3)

Try without signup. Built to leak into Telegram & X.

Freeбез регистрации

Promt Enhancer Lite

Paste any prompt — get the upgraded version with 5 best-practice rules applied.

  • Specificity, context, output format, constraints, examples — applied automatically
  • Side-by-side before/after view
  • Works with Claude, GPT, Gemini system prompts
Try it →mihalkevich.com
Freeбез регистрации

Spec Linter Lite

Drop a spec → see exactly what an AI would do with it. 3-layer validator: format, autotest, rubric.

  • Format check: schema, PII, source attribution
  • Auto-test: minimal prompt run on a target model
  • Rubric grade: clarity, modularity, model-fit
Lint a spec →mihalkevich.com
Freeбез регистрации

Folder Sniff

Upload an existing AI folder — get the 3 most critical issues, ranked, with fix suggestions.

  • Detects dead refs, duplicate roles, missing safety rails
  • Quotes the exact lines that fail
  • One-click handoff to the FolderAI editor
Sniff a folder →mihalkevich.com

Education tracks(13)

Self-paced courses with auto-graded exercises.

$19$19

Agent for Human

7-day course: hire your AI. From SOUL.md to a real working colleague — with daily exercises auto-graded by FolderAI.

  • Day 1–2: SOUL.md & IDENTITY.md — voice, role, scope
  • Day 3–4: 3-layer memory & PARA knowledge graph
  • Day 5: Tools & approval queue
Try Lite free →mihalkevich.com
$39$39

Specification for AI

Write specs that an AI can't misread. PRD-as-tests, acceptance criteria, deterministic checks.

  • PRD = markdown checklist + failing tests + sample data
  • Acceptance criteria that survive non-deterministic agents
  • Live evaluator with weighted rubrics
Try Lite free →mihalkevich.com
$49$49

I'm Agent Creator

Build agent folders end-to-end: pipeline, sub-agents, memory layers, conflict detection.

  • Design 8-stage pipelines (QUIZ → EXECUTION)
  • Sub-agent patterns: when to spawn, when to merge
  • 3-layer memory in every folder you ship
Try Lite free →mihalkevich.com
$99$99

Automation AI Engineer

Ship like a team of one. Ralph-loop, TDD prompts, parallel worktrees, self-healing pipelines.

  • Ralph-loop runner: many short sprints instead of one long marathon
  • TDD prompts — failing tests first, then implementation
  • Parallel agents in tmux + heartbeat health checks
Start Ch1 free →mihalkevich.com
$79$79

Prompting Sentinel

The world's strongest prompting simulator. Specs, context, dials, examples, schemas, lies, adversaries, ship.

  • Ch1: Specs over vibes — write the eval before the prompt
  • Ch2-3: Context engineering + thinking-budget dials
  • Ch4-5: Few-shot mastery + output schemas
Start Ch1 free →mihalkevich.com
$89$89

AI Ops Analyst

Make the numbers honest. Interrogate metrics, audit triage agents, write reconciliation tests, brief AI that surfaces bad news instead of burying it.

  • Ch1: The dashboard is lying — catch a metric that lies before the board does
  • Interrogate a definition, not a direction — kill vanity metrics
  • Audit a triage agent that auto-closed the real incident as noise
Start Ch1 free →mihalkevich.com
$9 / $29 / $79$9 / $29 / $79

AI Content Creator — Start · Medium · Pro

Three tiers of a content factory: from a single funnel to a full A/B-tested production line.

  • Start ($9): one funnel, 7 ready post templates
  • Medium ($29): + content calendar, persona library, brand voice
  • Pro ($79): + multi-model A/B test, evaluator rubrics, weekly auto-refresh
Try Lite free →mihalkevich.com
$99$99

Vibe Coding Engineer

Ship a real product with Claude Code + Codex from idea to a live URL — Vercel, Railway, and a working CI.

  • Drive Claude Code & OpenAI Codex like a senior pair, not a slot machine
  • From empty repo to deployed app on Vercel / Railway in one sitting
  • Wire a CI gate so the agent's work fails loudly before it ships
Join the waitlist →mihalkevich.com
$89$89

Claude Code Power User

Master the workspace: subagents, MCP servers, hooks, slash commands, and skills that turn one terminal into a team.

  • Design subagent fleets that fan out and verify each other's work
  • Build and wire MCP servers to your own tools and data
  • Automate with hooks, custom slash commands, and reusable skills
Join the waitlist →mihalkevich.com
$129$129

AI Agent Architect

Design agents that remember, plan, and use tools — memory, skills, orchestration, and the eval loop that keeps them honest.

  • Architect memory, skills, and tool-use for long-running agents
  • Choose single-agent vs multi-agent without cargo-culting frameworks
  • Build the eval harness that catches regressions before users do
Join the waitlist →mihalkevich.com
$119$119

AI Solopreneur

Run a one-person company on agents: validate an offer, build it, price it, and find your first ten paying customers.

  • Validate demand before you build with cheap, honest experiments
  • Stand up the product, billing, and support loop solo with AI
  • Price on value and model the unit economics that keep you alive
Join the waitlist →mihalkevich.com
$89$89

MCP & Tools Developer

Build the connective tissue: production MCP servers and tool integrations that let any agent touch your systems safely.

  • Build MCP servers from scratch — resources, tools, and prompts
  • Connect agents to databases, APIs, and internal services safely
  • Design tool schemas an agent can't misuse or misread
Join the waitlist →mihalkevich.com
$99$99

LLM Evals Engineer

Stop shipping on vibes: build eval harnesses, LLM-as-judge rubrics, and regression sets that make model quality measurable.

  • Build datasets and rubrics that actually predict real quality
  • Run LLM-as-judge without fooling yourself on the scores
  • Catch regressions across prompt and model changes automatically
Join the waitlist →mihalkevich.com

Specs for teams & companies(4)

Quiz-driven specifications with acceptance test suites.

B2B

AI Work Spec

Adaptive quiz → tailored AI-Work specification, with five live test runs proving it works.

  • Pro/Business adaptive quiz (extra steps when complexity rises)
  • PDF + Markdown deliverable, plug-and-play into Claude / GPT
  • Acceptance suite included: pass/fail before you commit
Get a spec →mihalkevich.com
B2B

AI Big Data Spec

From raw signals to AI-ready pipelines. Spec covers ingestion, taxonomy, validator gates, decay.

  • Hot/Warm/Cold fact decay — never delete, supersede
  • PARA-style knowledge graph (Projects/Areas/Resources/Archives)
  • Nightly extraction cron + semantic search backend
Get a spec →mihalkevich.com
B2B

AI for Life Spec

Personal AI architecture: identity, memory, schedule, safety. Designed for one user, lived in daily.

  • SOUL + IDENTITY tuned to your voice
  • Trust ladder calibrated to your risk tolerance
  • Approval queue patterns for high-stakes actions
Get a spec →mihalkevich.com
B2B · audit

Company Digitization & AI Adoption

Audit your company → 90-day AI roadmap. Where AI saves hours this quarter, and where it shouldn't be touched.

  • Full role-by-role audit (intake quiz + interviews)
  • Per-team AI specs with acceptance tests
  • 90-day rollout plan, with cost ceilings per stage
Book the audit →mihalkevich.com
Открыть весь каталог →

Три способа начать

Собери сам, освой ремесло или закажи у нас под ключ.

01

Нанять ИИ

Опиши роль — получи переносимую папку: SOUL.md, IDENTITY.md, workflows — которую запустит любая модель.

Собрать бесплатно →02

Освоить ремесло

Сюжетные симуляторы оценивают твои решения и выдают сертификат. Первая глава бесплатна.

Смотреть треки →03

Заказать в студии

Хочешь под ключ? Делаем AI-продукты от и до и встраиваем агентов в твой стек.

Открыть студию →

Стек, на котором мы строим

Современные технологии, модели и агенты — готовые к проду

Языки, ML и данные, frontier- и open-модели, агентские фреймворки, веб/мобайл-стек и on-prem инфраструктура — полный набор, на котором мы делаем продукты и AI-агентов.

Модели — frontier, open, китайские и image

Claude
GPT · OpenAI
Gemini
Grok · xAI
Llama
Mistral
DeepSeek
Qwen
Kimi · Moonshot
GLM · Zhipu
Command · Cohere
Stable Diffusion
Flux
Midjourney
open-weights
Claude
GPT · OpenAI
Gemini
Grok · xAI
Llama
Mistral
DeepSeek
Qwen
Kimi · Moonshot
GLM · Zhipu
Command · Cohere
Stable Diffusion
Flux
Midjourney
open-weights

AI-агенты и LLM-фреймворки

LangChain
LangGraph
LlamaIndex
CrewAI
DSPy
MCP · Model Context Protocol
Pydantic AI
Vercel AI SDK
vLLM
Ollama
Replicate
Modal
Weights & Biases
Gradio
Streamlit
n8n
LangChain
LangGraph
LlamaIndex
CrewAI
DSPy
MCP · Model Context Protocol
Pydantic AI
Vercel AI SDK
vLLM
Ollama
Replicate
Modal
Weights & Biases
Gradio
Streamlit
n8n

Machine learning и данные

PyTorch
TensorFlow
scikit-learn
Keras
ONNX
NumPy
pandas
Jupyter
OpenCV
Spark
Ray
Airflow
dbt
DuckDB
Roboflow
CUDA · NVIDIA
PyTorch
TensorFlow
scikit-learn
Keras
ONNX
NumPy
pandas
Jupyter
OpenCV
Spark
Ray
Airflow
dbt
DuckDB
Roboflow
CUDA · NVIDIA

Языки — включая закрытые контуры

Python
TypeScript
JavaScript
PHP
Go
Rust
Java
C#
.NET
C++
Kotlin
Swift
Ruby
Scala
Elixir
Python
TypeScript
JavaScript
PHP
Go
Rust
Java
C#
.NET
C++
Kotlin
Swift
Ruby
Scala
Elixir

Веб, мобайл и app-фреймворки

React
Next.js
Vue
Nuxt
Svelte
Astro
Remix
Three.js
Tailwind
Vite
FastAPI
Django
Flask
Laravel
Symfony
NestJS
Node.js
Bun
GraphQL
Flutter
React Native
Expo
React
Next.js
Vue
Nuxt
Svelte
Astro
Remix
Three.js
Tailwind
Vite
FastAPI
Django
Flask
Laravel
Symfony
NestJS
Node.js
Bun
GraphQL
Flutter
React Native
Expo

Инфра, вектор-БД и on-prem

Docker
Kubernetes
Linux · air-gapped
Postgres
pgvector
Qdrant
Pinecone
Weaviate
Milvus
Redis
MongoDB
Elasticsearch
Kafka
Supabase
NGINX
Terraform
Ansible
Railway
Vercel
Docker
Kubernetes
Linux · air-gapped
Postgres
pgvector
Qdrant
Pinecone
Weaviate
Milvus
Redis
MongoDB
Elasticsearch
Kafka
Supabase
NGINX
Terraform
Ansible
Railway
Vercel

Одно предложение — и рабочая папка готова.

Никакой настройки. Никакого SDK. Подключи папку к своей модели и шипи.

Начать бесплатно →