I publish practical gates for AI-generated work: approval gates, schema validation, audit logs, MCP server patterns, and deterministic code-review checks.
If you're building agents that need to touch real systems safely — not demo agents — this profile is for you.
- agent-approval-gate —
draft → validate → approve → dispatch → auditpattern with JSON schemas, n8n workflow, and email-approval example - agentproof-react — npm CLI that blocks common AI-generated React/Next.js shipping failures before release
- mcp-internal-tools-starter — TypeScript MCP starter with permissions, tenants, audit logs, approval tools (coming next week)
- leanix-mcp-integration — enterprise GraphQL MCP integration (LeanIX EAM)
- fixclaw — Claude Code runtime discipline for deterministic AI pipelines (Go)
Production AI Automation Notes — a running set of repos and gists on:
- approval gates for AI agents
- MCP server security (permissions, tenants, audit logs)
- Claude Code policies for company repos
- n8n workflows with human approval
- audit-log schemas
Follow if you're building agents that need to work outside demos.
| Gist | Topic |
|---|---|
| CapCut / JianYing draft_content.json schema cheat sheet | every top-level key + version differences + jq one-liners (May 2026) |
| JianYing 6.0+ draft_content.json encryption: detection and workarounds | 剪映 6.0 / 7.x / 10.3 / CapCut International — verbatim error strings (May 2026) |
| Driving CapCut / JianYing video drafts from an LLM agent (PAAN #4) | capcut-cli / bubble-text / audio-fade / mix-mode / Claude / DeepSeek / GLM (May 2026) |
| Hybrid AI agents: a 2B local VLM beats GPT-4V at browser-use UI grounding | browserground / Qwen3-VL / ScreenSpot-v2 / browser-use / Skyvern / Claude Computer Use (May 2026) |
| Claude Code with local LLMs: ANTHROPIC_BASE_URL, Ollama, LM Studio, vLLM, LiteLLM | gpt-oss / qwen3-coder / glm-4.7 setup + tool-call failures (Apr 2026) |
| Project | PR | What |
|---|---|---|
| Tencent/WeKnora | #835  |
Parallel tool calling support |
| steveyegge/beads | #2884 |
Multi-project support, Notion sync, backup/restore |
| e2b-dev/infra | #2273 |
Local dev docs: prerequisites, verification steps, troubleshooting |
| pacifio/cersei | #10 |
Native Google Gemini provider + Cohere & SambaNova support |
Stack: Go, TypeScript, Node.js, Kubernetes, Linux, systemd, vector databases, LLM APIs.
Website: renezander.com
A gist series on production-grade patterns for AI pipelines. Each entry covers one pattern with copy-pasteable code.
| # | Topic | Pattern |
|---|---|---|
| #1 | Agent Approval Gates | Schema-validated proposals, human review, deterministic dispatch |
| #2 | Token Budgets | Per-step, per-pipeline, per-day enforcement |
| #3 | Agentic Knowledge Base | Karpathy-style LLM wiki with pluggable adapters |
| #4 | CapCut / JianYing from an LLM agent | Deterministic JSON command boundary |
| #5 | SQLite Dedup + Crash Safety | WAL mode, seen_items, audit log |
| #6 | Prompt-Injection Defense | Input sanitization, schema validation |
| #7 | PDF Cite Verification | Auditable LLM extraction with per-fragment bounding boxes |
Reference implementation for entries #1, #2, #5, #6, #7: draftyard (Go, MIT).