Single-LLM self-reflection has a structural blind spot — the model tends to confirm its own output. QuantGPT enforces a hard rule in factor-mine SKILL Phase 0.5: Claude must consult DeepSeek before designing a new factor family. Not a suggestion, a hard rule. This isn’t redundancy — it’s the antidote to structural bias.
When the system operator changes from a human to an LLM Agent, design principles need fundamental rethinking. Humans need GUIs and documentation. Agents need semantically clear tools and constraints that throw errors.
The mainstream approach to Agent governance is writing rules in prompts. But LLMs can ignore prompts. Real governance lives outside the Agent, in the Harness layer — tools define what’s possible, errors define what’s forbidden, code defines where the boundaries are.
While everyone is building Agent frameworks, I chose a different path: build infrastructure for Agents, not the Agent itself. Not because I can’t build Agents, but because the Agent layer is a consumable — infrastructure is an asset.
Current AI Agent frameworks obsess over building complex loop chains: Planner → Executor → Reflector → Re-planner. I chose the opposite: tools are stateless pure functions, and the LLM decides the call sequence itself. Not because loop chains aren’t cool — but because they put decision authority in the wrong place.
AI-generated code must be executed — otherwise it’s just text. But execution means risk. I didn’t choose container isolation or RestrictedPython. Instead I designed a three-layer defense: reject dangerous structures at compile time via AST, replace the entire builtins at runtime, and enforce OS-level resource limits as a backstop. Each layer handles a different class of risk. Overlapping but not redundant.
LangChain, LangGraph, CrewAI, PydanticAI — no shortage of AI orchestration frameworks. I evaluated all of them and built my own. Not NIH syndrome. When you need failure-mode-driven mutation strategies, phase-aware multi-model routing with different temperatures, and adaptive evolution based on trajectory analysis, the abstraction layers of general-purpose frameworks become obstacles to route around.
Letting AI drive research workflows doesn’t mean letting AI decide how the system runs. I made a key separation: AI is just the operator, the execution engine is the law. This decision came from a failure.
Most systems are designed to run first, then audited as an afterthought. I inverted the order — first define what questions the system must answer when things go wrong, then work backwards to what each layer must record. This inversion reshaped the entire architecture.
MCP’s JSON-RPC transport works fine. The real problem: natural language rules have no code-level enforcement — the LLM can completely ignore your instructions. I designed the Intent Validator pattern to close this gap.