wiki 2026-04-07
Agent mistake → fix the harness, not the prompt
The single most important principle from harness engineering: when an AI agent makes a mistake, don't fix the prompt or try a better model. Fix the environment.
rustman
Solo founder building products with AI. Shipping fast, learning in public.
Projects
FaceAlarm — face massage coaching timer with AI
iOS app born from real life: wife runs a face massage coaching business, needed a timer with guided exercises. No good app existed — built one.
KubizBeat — Bashkir kubyz instrument app
iOS app for learning and playing the kubyz (Bashkir jaw harp / vargan). Digital instrument + learning tool preserving cultural heritage through technology.
SuperDuperAI — the company behind the products
SuperDuperAI is the umbrella: SuperDuper AI Teknoloji (Turkey, tech park with R&D tax benefits) + SuperDuperAI Corp (USA, Delaware). Not a single product — a...
Life2Film — turn everyday moments into meaningful montages
The original dream, started in 2014: help people turn everyday video moments into meaningful stories. Not just random clips — a narrative, a reflection on life.
Recent
wiki 2026-04-07
Agent self-discipline — drift detector and complexity thresholds
Principles for fighting AI agent degradation. The agent tends to drift into comfortable but unproductive patterns. Two mechanisms fight this:
wiki 2026-04-07
Apple Foundation Models — zero-cost on-device AI for iOS portfolio
Unified on-device AI layer for all iOS products (KissMyTask, FaceAlarm, VoiceJournal, QuestSchool). Zero API cost, privacy by architecture, SGR natively via ...
wiki 2026-04-07
CLI-first testing — every project gets a CLI mirror
Every project should have a CLI utility that mirrors the core business logic without UI. Not a separate tool — the same modules, different entry point.
wiki 2026-04-07
Context engineering — context as code
One of three harness engineering components. The idea: agent context is not chat history — it's a continuously improved knowledge base in the repository.
wiki 2026-04-07
Context Graphs — agent trajectories and organizational memory
Context Graph — a graph capturing AI agent decision-making trajectories: not just *what* the agent did, but *how* and *why*. "A system of record for decision...
wiki 2026-04-07
Decision Making
How to make decisions as a solo founder. From mental models to practical frameworks to psychological traps.
wiki 2026-04-07
Decision traces compound — each agent action improves future ones
The economic argument for context graphs: agent decision traces are a compounding asset. Each successful action recorded in the graph improves future ones th...
wiki 2026-04-07
Universal Development Principles — every project, any stack
993-line reference document applied to every project regardless of stack. Injected into PRDs during generation. Covers: SOLID, DRY (but Rule of Three), KISS,...
wiki 2026-04-07
Harness Engineering — development in the age of agents
Harness Engineering — designing environments where AI agents do reliable work. Humans steer, agents execute. Synthesized from three sources: OpenAI experimen...
wiki 2026-04-07
Infrastructure: two tools, serverless by default
Unified infrastructure for multiple mini-startups. Two principles: one project = one deploy config (infra lives in the repo), two tools, no more (SST + Pulumi).
wiki 2026-04-07
KMP sync — Supabase + PowerSync for offline-first cross-platform
For family/cross-platform apps needing offline-first sync between Android + iOS: Supabase + PowerSync is the recommended stack. MongoDB Realm Sync was deprec...
wiki 2026-04-07
PostHog analytics: one product = one project, cross-platform identity
Unified analytics for solo founder with mobile apps + web landings. Core problem: one person on landing and in app = 2 anonymous IDs. Broken attribution, bro...
wiki 2026-04-07
Privacy-First Architecture
Building products where user data stays on-device. Offline-first, local processing, minimal cloud dependency.
wiki 2026-04-07
SGR — schemas first, logic second, UI last
Schema-Guided Reasoning (SGR): all projects built from schemas to logic, not the other way around. Schemas are the contract between AI agent, business logic,...
wiki 2026-04-07
Solo Methodology
AI-driven solo development — how one person ships products using LLM agents, harness engineering, and automation.
wiki 2026-04-07
Startup Validation
How to validate startup ideas before investing time in building. From quick signal checks to full STREAM analysis.
wiki 2026-02-21
Background jobs — cron → CF Workers → Prefect → Temporal → Trigger.dev
5 tools for background jobs, ordered by complexity. Rule: start with cron, move up only when you need to.
wiki 2026-02-11
Agent sandboxing — safe LLM agent execution on Mac
LLM agents (Claude Code, Codex, Gemini CLI) run with full filesystem access. Sandboxing via lightweight VMs solves this: agent works in isolation, sees only ...
wiki 2026-02-11
Inspiration sources — curated channels, communities, newsletters
Curated list of ~60 channels/communities across 7 platforms, organized by relevance to solo founder workflow.
wiki 2026-02-11
Kill / Iterate / Scale — weekly decision rules
Hard numeric thresholds for weekly product decisions. No "let's wait and see":
wiki 2026-02-11
Launch Playbook — From Niche to Revenue
Operational playbook in 11 sections. Core: idea → live product with traffic in 5-9 days.
wiki 2026-02-11
Solo Founder Manifesto — Core Values
The manifesto (86 lines) establishes 6 foundational positions:
wiki 2026-02-11
One pain → one feature → launch
The antidote to "platform thinking": don't build a platform, don't draw a 50-feature roadmap. One pain, one solution, shipped in days.
wiki 2026-02-11
Portfolio approach — multiple small bets, not one big bet
Build multiple small products instead of going all-in on one. Pieter Levels: 70+ projects, 3-4 active revenue sources. John Rush: 20+ products. Danny Postma:...
wiki 2026-02-11
Privacy is architecture, not a feature
Key distinction from the manifesto: privacy is not a settings checkbox but an architectural decision made before the first line of code.
wiki 2026-02-11
RAG patterns — 7 approaches from vector to agentic
Reference catalog of 7 RAG patterns, each with when-to-use, trade-offs, and components.
wiki 2026-02-11
S.E.E.D. — niche scoring in 10 minutes
Quick filter for niche ideas before writing code. 4 dimensions:
wiki 2026-02-11
Solopreneur success patterns — benchmarks, pricing, distribution
Data-driven patterns from successful indie hackers (2023-2026). Used by `/validate` for STREAM scoring and `/research` for market context.
wiki 2026-02-07
CodeGraph — code intelligence across all projects via FalkorDB + tree-sitter
Knowledge graph of source code across all projects. Scans files, symbols (functions, classes, protocols), dependencies, imports, function calls, class inheri...