---
title: "About"
description: "The reopt architecture project and its author."
canonical: "https://architecture.reopt.ai/about"
language: "en"
last-updated: "2026-10-20"
alternate-markdown: "https://architecture.reopt.ai/ko/about.md"
site-index: "https://architecture.reopt.ai/llms.txt"
source: "reopt architecture"
---

# About

> The reopt architecture project and its author.

## What is reopt architecture

reopt architecture is a methodology for building AI products that do not collapse as they grow. It maintains ownership of outcomes, contracts for judgment, and evolution of structure as a system.

In an era when AI guarantees speed, scaling without structure produces agentic debt. It tells you why and how to build products from structure rather than from prompts.

## Author

**Eric Han** — Co-founder / CTO, Reopt AI

Co-founder and CTO of Reopt AI — a product-minded engineering operator who turns ambiguous problems and blank-slate situations into shipped products, operating teams, and durable technical systems. His work spans AI agent services, SaaS products, cloud infrastructure, and building engineering organizations from zero to scale.

- AI agent systems and MCP-enabled developer workflows
- SaaS architecture and platform engineering
- Cloud infrastructure, APIs, and enterprise integrations

## Methodological grounding

The assessment system in reopt architecture is built on validated methods from software engineering and AI governance. The eight engineering-perspective attributes are aligned with the ISO/IEC 25010 quality model. Trade-off analysis between attributes follows CMU SEI's ATAM (Architecture Tradeoff Analysis Method). The governance framework references Singapore IMDA's Model AI Governance Framework for Agentic AI and OpenAI's Practices for Governing Agentic AI Systems, adopting an AI Governance by Design approach that bakes governance into the design stage.

## References

The patterns, model, and principles of reopt architecture reference and build on the insights in the following sources.

- [Building Effective Agents](https://www.anthropic.com/engineering/building-effective-agents) — Anthropic Engineering. Agent-Computer Interface (ACI), Poka-yoke design, Evaluator-Optimizer pattern. Empirical grounding for the Module Contract and Evaluation patterns.
- [Scaling Managed Agents: Decoupling the Brain from the Hands](https://www.anthropic.com/engineering/managed-agents) — Anthropic Engineering. Session (memory) / Harness (brain) / Sandbox (hands) separation architecture. An empirical counterpart of the four-layer model.
- [Effective Harnesses for Long-Running Agents](https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents) — Anthropic Engineering. Harness as governance infrastructure. The pattern of using a feature list as a contract. A concrete implementation of the Evolution stages.
- [Demystifying Evals for AI Agents](https://www.anthropic.com/engineering/demystifying-evals-for-ai-agents) — Anthropic Engineering. pass@k vs pass^k metrics, graduating capability eval to regression eval, eval-driven development. Core grounding for the Evaluation pattern and the SHARPEN phase.
- [Effective Context Engineering for AI Agents](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents) — Anthropic Engineering. Context rot, attention budget, progressive disclosure, compaction. Empirical grounding for Context Routing and State/Memory patterns.
- [How We Built Our Multi-Agent Research System](https://www.anthropic.com/engineering/multi-agent-research-system) — Anthropic Engineering. Orchestrator-Worker pattern, sub-agent delegation, source-quality heuristics. An empirical case for Responsibility Partitioning and the Collaboration layer.
- [Writing Effective Tools for Agents — with Agents](https://www.anthropic.com/engineering/writing-tools-for-agents) — Anthropic Engineering. Tools as contracts with non-deterministic systems. Consolidated vs distributed design, prompt engineering of error responses. An implementation guide for the Module Contract.
- [Claude Code Auto Mode: A Safer Way to Skip Permissions](https://www.anthropic.com/engineering/claude-code-auto-mode) — Anthropic Engineering. Three-tier authority model and four threat types (overeager, honest mistakes, prompt injection, misalignment). An implementation model for the Human Approval pattern.
- [Harness Design for Long-Running Application Development](https://www.anthropic.com/engineering/harness-design-long-running-apps) — Anthropic Engineering. Planner-Generator-Evaluator three-agent design, Sprint Contract (dynamic contract negotiation), criteria-based grading. An implementation case for the Module Contract and Evaluation patterns.
- [Google's Eight Essential Multi-Agent Design Patterns](https://www.infoq.com/news/2026/01/multi-agent-design-patterns/) — InfoQ. Eight implementation patterns including Sequential Pipeline, Parallel Fan-out, and Hierarchical Decomposition. The basis for the Implementation Bridge mapping.
- [Google Publishes Scaling Principles for Agentic Architectures](https://www.infoq.com/news/2026/03/google-multi-agent/) — InfoQ. Quantitative evidence that multi-agent composition does not always raise performance. Empirical grounding for Layer, Then Scale.
- [Becoming AI-Native Without Losing Our Minds To Architectural Amnesia](https://www.infoq.com/news/2025/12/qconai-architecural-amnesia/) — InfoQ — QCon AI NY 2025. Origin of the agentic-debt concept — debt that accrues when autonomy outpaces discipline. The basis for the Agentic Debt framing.
- [Agentic AI Architecture Framework for Enterprises](https://www.infoq.com/articles/agentic-ai-architecture-framework/) — InfoQ. Foundation → Workflow → Autonomous three-stage framework. A reference for comparison with the Evolution stages.
- [The Architectural Shift: AI Agents Become Execution Engines While Backends Retreat to Governance](https://www.infoq.com/news/2025/10/ai-agent-orchestration/) — InfoQ. The argument that backends are retreating into a governance layer. An industry response to the Agents Scale by Structure thesis.
- [From Prompts to Production: a Playbook for Agentic Development](https://www.infoq.com/articles/prompts-to-production-playbook-for-agentic-development/) — InfoQ. ASDLC (Agentic SDLC) concept. The principle of defining "what must never happen." The basis for positioning OCLS within ASDLC.
- [ATAM: Method for Architecture Evaluation](https://www.sei.cmu.edu/documents/629/2000_005_001_13706.pdf) — Carnegie Mellon SEI. Methodology for stratifying quality attributes via the Utility Tree and analyzing trade-offs. The academic basis for the assessment slider → tension-detection structure.
- [ISO/IEC 25010 — Systems and Software Quality Models](https://www.iso.org/standard/35733.html) — ISO/IEC. International standard of eight quality attributes (security, reliability, performance efficiency, etc.). The alignment basis for the eight-axis development perspective.
- [Model AI Governance Framework for Agentic AI](https://www.imda.gov.sg/-/media/imda/files/about/emerging-tech-and-research/artificial-intelligence/mgf-for-agentic-ai.pdf) — IMDA (Singapore). Agentic-AI governance model framework. Responsibility assignment, contract-based control, layered oversight, operational adjustment — structurally aligned with the OCLS loop.
- [AI Governance by Design for Agentic Systems](https://www.preprints.org/manuscript/202504.1707) — Preprints.org. AIGD (AI Governance by Design) approach that bakes governance into the design stage. Proposes Constitutional AI, Compliance, Access Control, and Audit Trail pattern clusters.
- [AI Agents in Action: Foundations for Evaluation and Governance](https://reports.weforum.org/docs/WEF_AI_Agents_in_Action_Foundations_for_Evaluation_and_Governance_2025.pdf) — World Economic Forum. Foundational framework for evaluating and governing AI agents. International consensus on multi-dimensional evaluation metrics and governance principles.
- [Practices for Governing Agentic AI Systems](https://cdn.openai.com/papers/practices-for-governing-agentic-ai-systems.pdf) — OpenAI. Practitioner guidelines for safe operation of agentic AI. Technical controls and processes across the AI lifecycle.
- [Architecting Agentic Communities using Design Patterns](https://arxiv.org/pdf/2601.03624) — arXiv. Required application of Validation, Human-in-the-Loop, and Audit Trail patterns in regulated industries (HIPAA, SEC/FINRA). Academic basis for the financial-services preset profile.
- [Beyond Task Completion: An Assessment Framework for Evaluating Agentic AI Systems](https://arxiv.org/html/2512.12791v1) — arXiv. Multi-dimensional evaluation of reasoning, planning, collaboration, and ethical alignment beyond task completion. Aligned with the multi-dimensional approach of the integrated assessment metrics.
- [The Rise of Agentic AI: Architectures, Taxonomies, and Evaluation Metrics](https://www.mdpi.com/1999-5903/17/9/404) — Future Internet (MDPI). Comprehensive review of agentic-AI architectures, taxonomies, and qualitative/quantitative evaluation metrics. A reference for evaluation-framework design.

## Contributing

This project will evolve into an open reference. Pattern proposals, case shares, terminology debates — every kind of contribution is welcome.

## Vocabulary

- **Own Every Outcome** (OWN) — Assign an owner to every outcome, and name whether that owner is a human or an AI. Human ownership leaves room for contextual judgment; AI ownership requires every condition to be declared as a contract. The type of owner determines how strict the governance must be.
- **Aim the Compute** (OWN) — Without human direction, compute runs in circles. Ownership is not only bearing responsibility — it is setting an ambitious goal and connecting domains. As token capital grows, the human capital that sets direction grows more valuable, not less. When a human recognizes the pattern, AI makes that expertise replicable and scalable.
- **Contract First** (CONTRACT) — Declaring input, output, authority, and refusal conditions before implementation makes evaluation, replacement, and control possible. The more an AI owns the outcome, the stricter and more explicit the contract must be. The contract is the language of governance.
- **Sovereign Over the Model** (CONTRACT) — The model is a borrowed part; sovereignty lives in the learning system you stack on top of it. Swap the generalist model, and the company's expertise must remain in your contracts, traces, and internal evals. The test of sovereignty is not picking the best model — it is owning a learning loop that works no matter which model arrives.
- **Layer, Then Scale** (LAYER) — Even as agents multiply, structuring them into categories, layers, and boundaries preserves governance. Layering is the scaling strategy. Multi-agent scaling research from Google and MIT (2026, as reported by InfoQ) showed empirically that task-dependency structure is the deciding factor — for tasks with heavy tool coordination, multi-agent overhead actually degrades performance, and the optimal collaboration strategy varies by task.
- **Sharpen in Operation** (SHARPEN) — Tuning boundaries from operational data lets governance evolve with reality. Anthropic's [Demystifying Evals for AI Agents] frames eval-driven development: defining evaluation first surfaces requirement ambiguity before implementation. The moment a capability eval graduates to a regression eval is the signal that the boundary has stabilized. And as Anthropic's [Scaling Managed Agents] notes, assumptions go stale as models improve — upgrading to a new model generation is itself a SHARPEN trigger to re-tune boundaries and model assignments.

## Operating loops

- **Design Loop** — Lock responsibility boundaries first — role design, contract definition, failure-scenario specification.
- **Run Loop** — Collect execution logs, quality scores, and cost signals to identify bottlenecks and unnecessary collaboration. These traces are institutional memory that survives a model swap.
- **Governance Loop** — Adjust evaluation criteria, approval policies, and exception handling to scale the system safely.

---

_Markdown representation of https://architecture.reopt.ai/about. Full index: https://architecture.reopt.ai/llms.txt HTML original: https://architecture.reopt.ai/about · 한국어: https://architecture.reopt.ai/ko/about.md_