Adopting AI Without Adopting Tech Debt

[Updated 2026-02-05] This is the blog adaptation of a talk I gave at the Austin CTO Club in January 2026:

TL;DR: Minimize AI-era tech debt through context window management (Skills, markdown, monorepos), smaller teams with clear system boundaries, and open-source MCP App and ChatGPT App tooling.

Hi, I’m Abe. I recently sold my company, Trigo, where I was CTO building AI in property tech. Over the last few months I’ve been focused on the forefront of AI while building my new company, sunpeak, the leading MCP App framework.

Software development looks very different today, and I no longer think about tech debt the same way. I group my approach to minimizing AI-era tech debt into three areas: tech, people, and how we ship AI-native software.

---

Tech

Coding

Ground zero for AI tech discussions. Leading coding agents include Claude Code, OpenAI Codex, Cursor, GitHub Copilot, and Gemini Code Assist. Specifics here focus on Claude, where I am currently maxing out three subscriptions.

Unlike humans, agents don’t struggle with deadlines or extra work. The real driver for tech debt in an agentic world is misalignment. Keeping all developers agents rowing in the right direction is key, and the way to do that is via context window management:

• Context windows are 200k to 500k tokens in Claude Code, which are about 500 - 1250 pages of text
• We need to fit everything about our company, policies, vision, market, product, organization, team, project, personal preference, feature specification, and current conversation in this window
  • Everything single thing you hope your senior engineers know
• We can host a bunch of markdown from each relevant team and level of the organization hierarchy to ensure all agents have the same context over time
  • Agent Skills are one way to accomplish this, implemented as directories with SKILLS.md files
  • IT team maintains company policies, SOC-related instructions, handbook. Division leaders maintain… etc. etc.

Coupled with context window management, the monorepo remains the simplest way to keep context unified across related systems.

Ancillary Tech

A 10x increase in coding speed requires a 10x increase in everything around it:

• Code review: GitHub Copilot, CodeRabbit
• Testing: coding agents can do this really well, use Playwright MCP, Chrome devtools MCP
  • CI/CD, infra, monitoring: anything defined as code the agents do well
• Security: Semgrep, Snyk, Dependabot with cooldowns

---

People

People are far more productive, but our human context windows haven’t changed in 200,000 years. To stay on the same page, teams need to be smaller.

• Smaller teams with tighter coordination
• Larger ownership per engineer

With empowered individuals and small teams, it becomes more important to have clear boundaries around systems to maximize autonomy & speed with decentralization. If Amazon made the switch to a Service Oriented Architecture at 7,000 employees, that number is much, much lower today.

Additional tactics to keep people coordinated with AI:

• Agentic access to your ticketing and other SDLC systems via MCP
• Dedicated early adopter(s)
• Clear product processes around specs, reviews, and launches

---

Shipping AI-Native Software

The proliferation of agents has come with the need for new types of software systems more usable by agents. Besides Skills mentioned above, we builders are being tasked with building novel MCP and MCP App systems.

MCP

Model Context Protocol (MCP) lets agents interact with our systems. If skills are the static websites of the agent internet, MCP servers are the dynamic websites.

MCP is about a year old and should be treated as early infrastructure. It will change significantly, especially following its move from Anthropic to the Linux Foundation.

There’s no way to avoid a significant amount of technical debt as the MCP protocol changes out from under us, but we can at least offload some of the work to other people by adopting open-source software. In MCP, a great open-source protocol utility is mcp-use.

MCP Apps (ChatGPT Apps)

MCP Apps (also known as ChatGPT Apps) let anyone embed interactive, visual apps in ChatGPT conversations for use by ChatGPT’s 800M users and ChatGPT itself. If a user is asking about cold symptoms, OpenAI can render the CVS map of nearby stores for medicine.

MCP Apps launched as ChatGPT Apps in October 2025. They are MCP-based, but include extra OpenAI-specific UI protocols on top.

Like (and alongside) MCP, this protocol will change a lot and we can offload work to open-source software. For MCP Apps, the leading framework is sunpeak, which I’ve been building the last few months!

---

Wrapping Up

The AI era demands a new playbook for managing technical debt. By keeping context windows aligned, teams small, and embracing emerging protocols like MCP and MCP Apps (ChatGPT Apps), we can unlock 10x productivity gains without drowning in legacy complexity.

I’d love to hear how you’re thinking about AI adoption at your company. Feel free to reach out on LinkedIn, X, or [email protected] to talk about AI or MCP Apps!