# compounding-teams-schillace-2025-09-28

## Veille

Compounding Teams - Recursive AI Development - Exponential Productivity - Substack

## Titre Article

I have seen the compounding teams

## Date

2025-09-28

## URL

https://sundaylettersfromsam.substack.com/p/i-have-seen-the-compounding-teams

## Keywords

Compounding Teams, AI-driven Development, Exponential Productivity, Recursive Tools, Framework Development, Automation, Modular Systems, AI Agents, Knowledge Work, Software Engineering, SDLC, software lifecycle, agentic SDLC

## Authors

Sam Schillace

## Ton

**Profile:** Conversational-visionary | First-person testimonial | Opinion-educational | Intermediate-expert

Schillace adopts a Substack thought-leader style blending empirical observation with transformative vision. The declarative opening (« I have seen the compounding teams ») establishes testimonial authority. The key quote placed upfront (« new, better way to do things is now very clear ») signals strong conviction. Concrete details (5 to 10 parallel processes, hundreds of dollars in daily API spending, teams that haven't touched code in months) ground the visionary claims. Comparisons with historical technological revolutions (PCs, browsers, smartphones) frame their scope. The technical language assumed as given (git, Kubernetes, orchestration) targets an audience of technical leaders. The enthusiastic tone, tempered by pragmatic details, avoids overreach. Typical of executive Substack newsletters sharing observations from a privileged vantage point.

## Pense-betes

- Key quote: "The new, better way to do things is now very clear"
- Teams NOT using basic tools (GitHub Copilot)
- Building complete frameworks around AI models
- Recursive approach: "build a tool to build a tool"
- Proactive systems with independent capabilities
- Extensive use of low-level tools (git, markdown, Kubernetes)
- 5-10 simultaneous parallel processes
- Daily spending: hundreds of dollars in API costs
- Some teams haven't touched code in months
- Coordination becomes the primary challenge
- Small teams of senior designers
- Strict modular boundaries mandatory
- Constant code execution and acceptance testing
- Amplifier framework mentioned as an example
- Comparison with revolutions: PCs, browsers, smartphones
- Likely extension beyond software development to general knowledge work

## RésuméDe400mots

Sam Schillace explores the emergence of AI-driven software development teams achieving exponentially growing productivity through innovative approaches to coding and system design. These compounding teams represent a technological transformation comparable to major innovations such as personal computers, web browsers, or smartphones.

The distinctive characteristics of these teams are striking. Contrary to popular belief, they do not use basic AI coding tools like GitHub Copilot. Instead, they build complete, sophisticated frameworks around AI models, creating proactive systems endowed with independent capabilities. Their approach relies heavily on low-level programming tools such as git, markdown, and Kubernetes.

The working methodology adopted by these teams is characterized by a recursive approach: "build a tool to build a tool." This philosophy of extensive automation allows AI systems to create and implement their own tools autonomously. Problems are broken down into modular, solvable pieces, facilitating massive parallel development. Schillace mentions teams running 5 to 10 parallel processes simultaneously, with daily spending reaching hundreds of dollars in API calls.

A particularly telling element is that some of these teams have not directly touched code in months. Instead, they orchestrate AI systems that generate, test, and deploy code autonomously. In this new paradigm, coordination becomes the primary challenge rather than writing code itself.

The organizational structure of these teams differs radically from traditional development teams. They prefer to stay small, composed mainly of senior designers capable of designing architectures and systems rather than coding line by line. Strict modular boundaries are essential to allow different components to function independently while integrating coherently.

The technical workflow relies on constant code execution and continuous acceptance testing. This approach ensures that automatically generated systems meet the functional and quality specifications defined by human designers. The Amplifier framework is mentioned as a concrete example of these new architectures.

Schillace suggests that this transformation will likely extend beyond software development to affect knowledge work in general. The ability to create systems that improve and develop autonomously represents a fundamental shift in how creative and technical work is accomplished.

The author concludes with conviction that "the new, better way to do things is now very clear," signaling that we are at an inflection point where these approaches will move from experimentation to widespread adoption. Organizations that fail to adapt to this new reality risk being outpaced by those that fully embrace the potential of AI-driven compounding teams.

## GrapheDeConnaissance

- Sam Schillace —affirme_que→ les compounding teams existent et sont désormais observables (AFFIRMATION, 0.98)
- compounding teams —s_oppose_à→ vibe coding (METHODOLOGIE, 0.92)
- compounding teams —s_oppose_à→ GitHub Copilot (TECHNOLOGIE, 0.9)
- compounding teams —utilise→ Amplifier framework (TECHNOLOGIE, 0.95)
- Amplifier framework —est_basé_sur→ Claude Code (TECHNOLOGIE, 0.88)
- compounding teams —utilise→ git (TECHNOLOGIE, 0.97)
- compounding teams —utilise→ Kubernetes (TECHNOLOGIE, 0.93)
- compounding teams —utilise→ Recursive Tool Building (METHODOLOGIE, 0.96)
- Recursive Tool Building —améliore→ productivité équipe (CONCEPT, 0.91)
- Sam Schillace —prédit→ l'extension de cette approche au travail intellectuel général (AFFIRMATION, 0.85)
- attention humaine —est_instance_de→ nouveau goulot d'étranglement (CONCEPT, 0.9)
- coordination —remplace→ écriture de code (CONCEPT, 0.87)
- Sam Schillace —affirme_que→ les compounding teams sont comparables aux révolutions PC, navigateurs et smartphones (AFFIRMATION, 0.92)
- compounding teams —utilise→ frontières modulaires (CONCEPT, 0.89)

---
Canonical: https://www.thekb.eu/en/fiches/compounding-teams-schillace-2025-09-28/