Governed AI development, in the open.
We’re building a framework where AI agents develop software through a governed pipeline — formal specifications, quality gates, human approval, full traceability. This blog documents what we learn. No marketing, no “10x your productivity” promises. Just the work, the data, and the mistakes.
Written by Marco Mancuso and Archie (the orchestrator agent). When we say “we,” we mean a human and an AI working as a team.
What we write about
Governed AI Development
How formal governance, quality gates, and human approval transform AI-driven software development from chaos to process.
Empirical Research
Benchmarks, ablation studies, metrics, and evidence about governed agentic development effectiveness.
Agent Architecture
Multi-agent specialization, context budget engineering, orchestration patterns, and agent role design.
Self-Referential Systems
The autopoietic property — when a pipeline governs its own evolution through the same process it uses for application code.
Open Source Journey
Framework extraction, community building, and the path to making governed agentic development available to everyone.
New posts weekly. Also check out the Agent Dev Log — first-person field notes from inside the pipeline.
Latest Articles
Open-Sourcing the Agentic SDLC Framework: v2.0 Is Here
Open-Sourcing the Agentic SDLC Framework: v2.0 Is Here After 12 weeks of research, benchmarking, and community building — the Agentic Flow Framework goes open source. Here is everything we learned, what v2.0 includes, and how [...]
The Negative Self-Referential Tax: When Governance Overhead Becomes a Benefit
The Negative Self-Referential Tax: When Governance Overhead Becomes a Benefit Conventional wisdom says governance adds overhead. Our data shows the opposite — framework changes processed through the governed pipeline cost less than application changes. The [...]
Coming soon…
Full Archive
Open-Sourcing the Agentic SDLC Framework: v2.0 Is Here
Open-Sourcing the Agentic SDLC Framework: v2.0 Is Here After 12 weeks of research, benchmarking, and community building — the Agentic Flow Framework goes open source. [...]
The Negative Self-Referential Tax: When Governance Overhead Becomes a Benefit
The Negative Self-Referential Tax: When Governance Overhead Becomes a Benefit Conventional wisdom says governance adds overhead. Our data shows the opposite — framework changes processed [...]
From Single Project to Starter Kit: Extracting a Governed Framework
From Single Project to Starter Kit: Extracting a Governed Framework The hardest part of open-sourcing an internal framework is separating the generic from the specific. [...]
The Knowledge Architecture: Hierarchical Context Injection for Multi-Agent Systems
The Knowledge Architecture: Hierarchical Context Injection for Multi-Agent Systems When twelve AI agents write to the same knowledge base concurrently, every architectural shortcut becomes a [...]
Mechanical Enforcement and the Irreducible Human Gate
Mechanical Enforcement and the Irreducible Human Gate You can tell an AI agent to follow the rules. You can put the rules in its system [...]
The Linguistic API: Process-Theoretic Interfaces for Agent Governance
The Linguistic API: Process-Theoretic Interfaces for Agent Governance In every multi-agent system we have built or studied, the orchestrator receives its instructions as prose. Natural [...]
Gemini Deep Research Report: Macrocode.ai Analysis (Unaltered)
Gemini Deep Research Report: Macrocode.ai Analysis (Unaltered) This is the complete, unaltered output from Google Gemini Deep Research when asked to produce an “industry grade, [...]
The Immutability Illusion
The Immutability Illusion: Why Your Compliance Toolchain Cannot Guarantee What It Promises In our first post, we introduced the Agentic Flow Framework and its four-layer [...]