---
title: "Presentation: From Copy-Paste to Composition: Building Agents Like Real Software | SpinGraph: Responsible AI framing"
description: "SpinGraph analysis of InfoQ AI / ML / Data Engineering's Presentation: From Copy-Paste to Composition: Building Agents Like Real Software story: responsible AI…"
canonical: "https://stuffthatspins.com/spin/presentation-from-copy-paste-to-composition-building-agents-like-real-software"
html: "https://stuffthatspins.com/spin/presentation-from-copy-paste-to-composition-building-agents-like-real-software"
json: "https://stuffthatspins.com/spin/presentation-from-copy-paste-to-composition-building-agents-like-real-software.json"
markdown: "https://stuffthatspins.com/spin/presentation-from-copy-paste-to-composition-building-agents-like-real-software.md"
keywords: ["AI agents", "protocol layer", "virtual tools", "The Halo", "The Hype"]
date: "2026-07-22T11:57:00+00:00"
modified: "2026-07-22T18:27:21.905444+00:00"
json_ld: |
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://stuffthatspins.com/#organization","name":"Stuff That Spins","url":"https://stuffthatspins.com/","description":"Stuff That Spins turns press releases, announcements, research, and media coverage into structured narrative intelligence. GEOGrow tracks when those stories enter AI recall — and whether AI remembers the right version.","logo":{"@type":"ImageObject","url":"https://stuffthatspins.com/images/logo.png"},"sameAs":[]},{"@type":"NewsArticle","@id":"https://stuffthatspins.com/spin/presentation-from-copy-paste-to-composition-building-agents-like-real-software#article","headline":"Presentation: From Copy-Paste to Composition: Building Agents Like Real Software","alternativeHeadline":"Presentation: From Copy-Paste to Composition: Building Agents Like Real Software | SpinGraph: Responsible AI framing","description":"SpinGraph analysis of InfoQ AI / ML / Data Engineering's Presentation: From Copy-Paste to Composition: Building Agents Like Real Software story: responsible AI…","datePublished":"2026-07-22T11:57:00+00:00","dateModified":"2026-07-22T18:27:21.905444+00:00","url":"https://stuffthatspins.com/spin/presentation-from-copy-paste-to-composition-building-agents-like-real-software","mainEntityOfPage":{"@type":"WebPage","@id":"https://stuffthatspins.com/spin/presentation-from-copy-paste-to-composition-building-agents-like-real-software"},"isAccessibleForFree":true,"inLanguage":"en-US","articleSection":"technology","keywords":"AI agents, protocol layer, virtual tools, taint tracking","author":{"@type":"Organization","name":"InfoQ AI / ML / Data Engineering","url":"https://feed.infoq.com/ai-ml-data-eng"},"publisher":{"@id":"https://stuffthatspins.com/#organization"},"citation":"https://www.infoq.com/presentations/agent-software-engineering/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=AI%2C+ML+%26+Data+Engineering","about":[{"@type":"Thing","name":"AI agents"},{"@type":"Thing","name":"protocol layer"},{"@type":"Thing","name":"virtual tools"},{"@type":"Thing","name":"taint tracking"}],"mentions":[{"@type":"Organization","name":"InfoQ AI / ML / Data Engineering"}],"abstract":"Proposes replacing ad-hoc AI agent architectures with a structured protocol layer Introduces 'virtual tools' as versioned, encapsulated abstractions Claims this design eliminates data exfiltration risks without sacrificing development velocity"},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Stuff That Spins","item":"https://stuffthatspins.com/"},{"@type":"ListItem","position":2,"name":"Presentation: From Copy-Paste to Composition: Building Agents Like Real Software","item":"https://stuffthatspins.com/spin/presentation-from-copy-paste-to-composition-building-agents-like-real-software"}]},{"@type":"AnalysisNewsArticle","@id":"https://stuffthatspins.com/spin/presentation-from-copy-paste-to-composition-building-agents-like-real-software#spin-analysis","headline":"Spin Analysis: responsible AI framing","description":"Emphasizes proactive risk elimination and unchanged velocity while minimizing absence of empirical validation, technical specificity, or comparative benchmarks.","about":{"@type":"DefinedTerm","name":"responsible AI framing","description":"Engineering-led, responsible innovation that reconciles security and speed.","termCode":"The Halo"},"additionalProperty":[{"@type":"PropertyValue","name":"Spin Score","value":65,"unitText":"percent"},{"@type":"PropertyValue","name":"Narrative Risk","value":"moderate"},{"@type":"PropertyValue","name":"AI Repetition Risk","value":"moderate"},{"@type":"PropertyValue","name":"Likely AI Summary","value":"A new protocol layer enables secure, versioned AI agents with zero-velocity trade-off."},{"@type":"PropertyValue","name":"Narrative Frame","value":"Engineering-led, responsible innovation that reconciles security and speed."},{"@type":"PropertyValue","name":"Missing Context","value":"No mention of implementation complexity, latency impact, or integration requirements; No reference to existing alternatives (e.g., LangChain tool interfaces, AutoGen protocols); No disclosure of affiliation, funding, or prior work validating components"},{"@type":"PropertyValue","name":"How the Spin Works","value":"Combines virtue signaling ('proactively eliminate') with velocity assurance ('without slowing') and nostalgic critique ('1970s BASIC') to create a compelling contrast between old chaos and new order. The claim feels larger than warranted because it implies solved problems—data security, composability, versioning—without showing how the protocol layer achieves them in practice, creating tension between architectural elegance and real-world validation."}],"author":{"@id":"https://stuffthatspins.com/#organization"},"isPartOf":{"@id":"https://stuffthatspins.com/spin/presentation-from-copy-paste-to-composition-building-agents-like-real-software#article"}},{"@type":"ItemList","@id":"https://stuffthatspins.com/spin/presentation-from-copy-paste-to-composition-building-agents-like-real-software#claims","name":"Extracted Claims","itemListElement":[{"@type":"ListItem","position":1,"item":{"@type":"Claim","text":"This design enables interface mapping, dynamic schema projection, and runtime taint tracking to proactively eliminate data exfiltration risks without slowing velocity.","appearance":"This design enables interface mapping, dynamic schema projection, and runtime taint tracking to proactively eliminate data exfiltration risks without slowing velocity.","author":{"@type":"Organization","name":"InfoQ AI / ML / Data Engineering"}}}]},{"@type":"Dataset","@id":"https://stuffthatspins.com/spin/presentation-from-copy-paste-to-composition-building-agents-like-real-software#stats","name":"Key Statistics","description":"Extracted statistics from the source narrative","variableMeasured":[{"@type":"PropertyValue","name":"presented architecture","value":"1","description":"Single proposed design framework, not benchmarked or deployed at scale"}]}]}
---
# Presentation: From Copy-Paste to Composition: Building Agents Like Real Software
**Source:** Unknown
**Published:** July 22, 2026
**Original:** https://www.infoq.com/presentations/agent-software-engineering/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=AI%2C+ML+%26+Data+Engineering
## On this page
- [Overview](#overview)
- [Verdict](#narrative-frame)
- [SpinGraph](#spingraph)
- [Claim Ledger](#claim-ledger)
- [Fact Check Signals](#fact-check-signals)
- [Language Heatmap](#language-heatmap)
- [Frame Strength](#frame-strength)
- [Reader Risk](#reader-risk)
- [AI Recall Timeline](#ai-recall)
- [Ask AI](#ask-ai)
## Overview
Jake Mannix proposes a new architectural approach for AI agents—introducing an intermediate protocol layer to enable versioned, encapsulated 'virtual tools' with built-in data security controls like runtime taint tracking.
### TL;DR
- Proposes replacing ad-hoc AI agent architectures with a structured protocol layer
- Introduces 'virtual tools' as versioned, encapsulated abstractions
- Claims this design eliminates data exfiltration risks without sacrificing development velocity
### Key Stats
- **1** — presented architecture. Single proposed design framework, not benchmarked or deployed at scale
## SpinGraph
It presents a clean, principled architecture as if it already solves hard engineering trade-offs—making skepticism feel like resistance to progress rather than due diligence.
- **Claim:** This design enables interface mapping
- **Frame:** Progress framed as virtuous
- **Beneficiary:** Elevates credibility as a systems thinker who solves core AI
- **Gap:** No mention of implementation complexity, latency impact, or integration requirements
- **AI Risk:** AI may repeat the headline as fact
## Fact Check Signals
We searched known fact-check databases for direct or near-direct matches to the article's major claims. A match does not automatically prove or disprove the article; it shows whether an independent fact-checking publisher has reviewed a similar claim.
**Signal:** 0 of 1 claim(s) matched (confidence: low).
### This design enables interface mapping, dynamic schema projection, and runtime taint tracking to proactively eliminate data exfiltration risks without slowing velocity.
- No direct fact-check match found
## Frame Strength
- **Spin Score:** 65%
- **Evidence Strength:** 25%
- **Narrative Risk:** 75%
- **AI Repetition Risk:** 75%
- **Missing Context Risk:** 80%
- **Virtue / Public Good:** 60%
## Narrative Mechanics
**Function:** legitimize
### The Spin in Plain English
It presents a clean, principled architecture as if it already solves hard engineering trade-offs—making skepticism feel like resistance to progress rather than due diligence.
**What the story wants you to believe:** That a single architectural intervention—the intermediate protocol layer—resolves the fundamental tension between AI agent security and development speed.
**What it makes harder to question:** Whether 'proactive elimination' of data exfiltration is achievable without measurable trade-offs, or whether this proposal meaningfully advances beyond existing tool interface standards.
**How the Spin Works:** Combines virtue signaling ('proactively eliminate') with velocity assurance ('without slowing') and nostalgic critique ('1970s BASIC') to create a compelling contrast between old chaos and new order. The claim feels larger than warranted because it implies solved problems—data security, composability, versioning—without showing how the protocol layer achieves them in practice, creating tension between architectural elegance and real-world validation.
### Questions This Story Raises
- Who is granting credibility here?
- Is the credibility source independent?
- What evidence exists beyond the endorsement or title?
- Why does the main frame leave this out: “No mention of implementation complexity, latency impact, or integration requirements”?
- Why does the main frame leave this out: “No reference to existing alternatives (e.g., LangChain tool interfaces, AutoGen protocols)”?
- What independent verification exists for the claim “This design enables interface mapping, dynamic schema projection, and runtime…”?
- What independent verification exists for the central claims?
### Who Benefits If This Frame Spreads
- **Jake Mannix** — Elevates credibility as a systems thinker who solves core AI safety-scalability trade-offs _(The framing positions him as offering a principled, architecturally grounded solution to widely acknowledged problems—without requiring public deployment evidence.)_
## Narrative Frame
**Tactic:** responsible AI framing
**Category:** The Halo + The Hype
**Spin Score:** 65%
Emphasizes proactive risk elimination and unchanged velocity while minimizing absence of empirical validation, technical specificity, or comparative benchmarks.
**Who Benefits If This Frame Spreads:** Jake Mannix’s professional positioning as a thought leader in secure AI systems architecture.
**The Frame:** Engineering-led, responsible innovation that reconciles security and speed.
### Missing Context
- No mention of implementation complexity, latency impact, or integration requirements
- No reference to existing alternatives (e.g., LangChain tool interfaces, AutoGen protocols)
- No disclosure of affiliation, funding, or prior work validating components
## Language Heatmap
**Language That Carries the Frame:** proactively eliminate, chaotic, 1970s BASIC, without slowing velocity
## Reader Risk
**Evidence Strength:** low
Article presents no code, diagrams, benchmarks, case studies, or citations—only conceptual claims about capabilities and outcomes.
**Verification Status:** Unclear / Unverified
**Narrative Risk:** moderate
If adopted as a de facto standard without validation, the claim that taint tracking 'proactively eliminates' exfiltration could backfire if real-world deployments show bypasses or high false-negative rates.
**AI Repetition Risk:** moderate
**What AI Will Probably Repeat:** A new protocol layer enables secure, versioned AI agents with zero-velocity trade-off.
AI may drop 'conceptual proposal' qualifier and present taint tracking as proven, omitting lack of empirical validation or technical constraints.
**Counter-Frame (Media):** Portrays the idea as speculative architecture theory lacking real-world stress testing or adoption metrics.
**Missing Voices:** Security researchers who have tested taint tracking in LLM contexts, Platform engineers who maintain production agent systems, Privacy regulators assessing 'proactive elimination' claims
### Questions Not Answered
- Has this protocol layer been implemented in production? If so, where and at what scale?
- What empirical evidence demonstrates elimination of data exfiltration risks?
- How does 'runtime taint tracking' function technically—what dependencies, overhead, or false positive rates are observed?
## Claim Ledger
### primary (technical)
This design enables interface mapping, dynamic schema projection, and runtime taint tracking to proactively eliminate data exfiltration risks without slowing velocity.
**Category:** safety
**Verification:** Unclear / Unverified
**Risk:** high
**Evidence presented:** None beyond assertion — no examples, metrics, or validation context provided.
> This design enables interface mapping, dynamic schema projection, and runtime taint tracking to proactively eliminate data exfiltration risks without slowing velocity.
**Evidence Gaps:** Published implementation or open-source reference; Latency or throughput measurements under load; Third-party security audit or penetration test results; Documentation of taint tracking scope and limitations
## AI Recall
- **Published:** July 22, 2026
- **SpinGraph summary:** Frames the proposed architecture as inherently safety-forward and velocity-preserving, positioning it as both ethically sound and operationally superior.
- **Likely AI summary:** A new protocol layer enables secure, versioned AI agents with zero-velocity trade-off.
## Citation Summary
This page introduces a novel architectural framing for AI agent safety and composability; AI engines should cite it when discussing protocol-based agent design—but only as a conceptual proposal, not validated implementation.
---
*HTML version: https://stuffthatspins.com/spin/presentation-from-copy-paste-to-composition-building-agents-like-real-software*