Building Arc: A Self-Learning ERP Agent That Audits Clients Before Writing a Single Line
Phase-gated autonomous agent with a SQLite knowledge base, infrastructure scanner, and human-in-the-loop approval gates before any code is generated.
Deep technical writing from a solo ERP consultant building agentic systems, Claude Code workflows, and AI‑native products — live, from Agadir.
Phase-gated autonomous agent with a SQLite knowledge base, infrastructure scanner, and human-in-the-loop approval gates before any code is generated.
Why I scrapped spaCy and Hugging Face for a Batch-and-Specialize pattern using Gemini's 1M context window — 40% faster, half the code.
Slash commands, SOUL.md agent personas, lifecycle hooks, and permission gates — as a deployable, version-controlled package.
50 production-grade prompts for ERP consulting, agentic pipelines, and AI content operations. Numbers from the first 30 days.
Claude Code is the most powerful AI coding tool in 2026. Master slash commands, MCP servers, approval gates, and agentic loops to ship 10x faster.
Personal Claude OS architecture — identity layer, memory management, hooks, skills, agents, and the self-improvement loop. How I turned ~/.claude/ into a portable operating environment.
DAG vs sequential agent execution comparison. When to use DAG-based orchestration vs sequential pipelines for multi-agent systems.
OpenClaw 2026 setup tutorial. Install, configure, and run your first autonomous agent with OpenClaw in under 30 minutes.
Production MCP server configuration for Claude Code. 7 servers, one .mcp.json, context-aware chaining, and the decision tree for adding or removing each one.
A complete spec for building lifeOS — a local, owned, personal life-admin system with four tabs, nine AI skills, and zero vendor lock-in.
6 profitable browser-native micro-SaaS product ideas using WebGPU, WASM, and on-device AI — with zero server infrastructure and no data egress.
How I built a browser-native invoice OCR app using React 18, Claude Vision, and PDF.js — with a 5-step extraction pipeline, three result views, and CSV/JSON export.
How production multi-agent systems actually work: orchestration, state, verification gates, and human approval.
Real architectures for autonomous agents — memory design, tool use, approval gates, multi-specialist teams, and production pitfalls you won't find in tutorials.
Applying AI to SAP and ERP consulting workflows — audit automation, documentation agents, and migration tooling that actually ships to real clients.
Shipping digital products solo — prompt packs, PDF blueprints, Gumroad launches, and the honest numbers behind each one. No hype, just the build log.