C:C03
Chapter 3: Limits and Capability of Coding Agents
A guide to the published second edition, with literal citations separated from wider editorial reading suggestions.
Chapter guide
Turns agent capability into a bounded engineering hypothesis. Permissions, tools, budgets, stopping rules and escalation constrain execution; the chapter compares execution routes and parallel work while keeping technical completion separate from authorized acceptance.
Sintesi in italiano
Trasforma la capacità degli agent in un'ipotesi ingegneristica delimitata. Permessi, strumenti, budget, condizioni di arresto ed escalation vincolano l'esecuzione; il capitolo confronta percorsi operativi e lavoro parallelo distinguendo il completamento tecnico dall'accettazione autorizzata.
Learning goals
- translate a task request into a permission and budget envelope
- tell a model suggestion from an orchestrator-authorized action
- stop or escalate an agent without confusing technical completion with acceptance
Obiettivi in italiano
Obiettivi di apprendimento
- tradurre una richiesta di lavoro in un envelope di permessi e budget
- distinguere un suggerimento del modello da un'azione autorizzata dall'orchestrator
- fermare un agent o portare un caso in escalation, senza confondere completamento tecnico e accettazione
Chapter outline
- 3.1 From suggestion to a permission-bounded agent
- 3.2 What an agent actually observes
- 3.3 The task envelope
- 3.4 Agent benchmarks and observed pull requests
- 3.5 Common failure modes in real changes
- 3.6 A bounded propose–act–observe loop
- 3.7 The minimum sufficient execution route
- 3.8 When parallel agents help and hurt
- 3.9 Stopping rules versus acceptance authority
- 3.10 Agent capability as a testable hypothesis
- Technical laboratory — A permission-bounded candidate, not an autonomous release
- 3.11 Worked engineering example: permission is a state-machine input
- 3.12 Practice exercise: define an agent's actual authority
Struttura del capitolo
- 3.1 Dal suggerimento a un agent con permessi delimitati
- 3.2 Che cosa osserva realmente un agent
- 3.3 Il perimetro del task
- 3.4 Benchmark degli agent e pull request osservate
- 3.5 Modalità di fallimento frequenti nelle modifiche reali
- 3.6 Un loop delimitato propose–act–observe
- 3.7 Scegliere il percorso minimo di esecuzione sufficiente
- 3.8 Quando gli agent paralleli aiutano e quando peggiorano il risultato
- 3.9 Regole di arresto e autorità di accettazione
- 3.10 Le capacità dell'agent come ipotesi verificabili
- Laboratorio tecnico — Una candidata con permessi delimitati, non una release autonoma
- 3.11 Esempio ingegneristico svolto: i permessi sono input della macchina a stati
- 3.12 Esercizio pratico: definire l'autorità effettiva di un agent
Cited in the published chapter
21 linked atlas references from literal citations in the English and Italian editions. General bibliography membership and identifier-index entries are counted separately.
SE@PoliMi bibliography 16
- W002 — Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows
Chen · 2026 - W011 — The Productivity-Reliability Paradox: Specification-Driven Governance for AI-Augmented Software Development
Farrag · 2026 - W012 — Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale
Liu · 2026 - W013 — Quantifying the Expectation-Realisation Gap for Agentic AI Systems
Lobentanzer · 2026 - W034 — Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance
Pinna · 2026 - W060 — Your AI, My Shell: Demystifying Prompt Injection Attacks on Agentic AI Coding Editors
Liu · 2025 - W071 — Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study
Peralta · 2026 - W079 — Correlated Errors in Large Language Models
Kim · 2025 - W095 — Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle
Bhati · 2026 - W101 — Articulate but Wrong: Self-Review Failures in LLM-Based Code Modernization
Purnachandra Reddy · 2026 - W111 — Many SWE-bench-Passing PRs Would Not Be Merged into Main
Whitfill · 2026 - W151 — Blueprint First, Model Second: A Framework for Deterministic LLM Workflow
Qiu · 2026 - W152 — Agentic Software Engineering: Foundational Pillars and a Research Roadmap
Hassan · 2026 - W158 — Should I Give Up Now? Investigating LLM Pitfalls in Software Engineering
Tie · 2026 - W191 — Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub
Ehsani · 2026 - W193 — MirrorCode: Evidence that AI can already do some weeks-long coding tasks
METR / Epoch AI · 2026
Addy Osmani 3
- O006 — Practical Loop Engineering
Addy Osmani · 2026-08-14 - O010 — Agentic Autonomy Levels
Addy Osmani · 2026-07-03 - O012 — Loop Engineering
Addy Osmani · 2026-06-08
The Pragmatic Engineer 1
- P110 — What is “loop engineering?”
Gergely Orosz · 2026-07-14
Martin Fowler’s website 1
- F008 — How to tackle unreliability of coding assistants
Birgitta Böckeler · 2023-11-29
Trace literal citations to chapter sections
Locations come from the supplied English and Italian source files. Chapter text and figure captions are identified separately; identifier-index references and general bibliography membership are not treated as chapter citations.
- F008 · How to tackle unreliability of coding assistants
- EN · From suggestion to a permission-bounded agent
EN/chapters/chapter03.tex:14 - ITA · Dal suggerimento a un agent con permessi delimitati
ITA/chapters/chapter03.tex:14
- EN · From suggestion to a permission-bounded agent
- O006 · Practical Loop Engineering
- EN · A bounded propose–act–observe loop
EN/chapters/chapter03.tex:88 - ITA · Un loop delimitato propose–act–observe
ITA/chapters/chapter03.tex:88
- EN · A bounded propose–act–observe loop
- O010 · Agentic Autonomy Levels
- EN · The task envelope
EN/chapters/chapter03.tex:43 - ITA · Il perimetro del task
ITA/chapters/chapter03.tex:43
- EN · The task envelope
- O012 · Loop Engineering
- EN · A bounded propose–act–observe loop
EN/chapters/chapter03.tex:88 - ITA · Un loop delimitato propose–act–observe
ITA/chapters/chapter03.tex:88
- EN · A bounded propose–act–observe loop
- P110 · What is “loop engineering?”
- EN · A bounded propose–act–observe loop
EN/chapters/chapter03.tex:110 - ITA · Un loop delimitato propose–act–observe
ITA/chapters/chapter03.tex:110
- EN · A bounded propose–act–observe loop
- W002 · Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows
- EN · What an agent actually observes
EN/chapters/chapter03.tex:31 - ITA · Che cosa osserva realmente un agent
ITA/chapters/chapter03.tex:31
- EN · What an agent actually observes
- W011 · The Productivity-Reliability Paradox: Specification-Driven Governance for AI-Augmented Software Development
- EN · Agent capability as a testable hypothesis
EN/chapters/chapter03.tex:177 - ITA · Le capacità dell'agent come ipotesi verificabili
ITA/chapters/chapter03.tex:177
- EN · Agent capability as a testable hypothesis
- W012 · Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale
- EN · From suggestion to a permission-bounded agent
EN/chapters/chapter03.tex:16 - EN · A bounded propose–act–observe loop
EN/chapters/chapter03.tex:82 - ITA · Dal suggerimento a un agent con permessi delimitati
ITA/chapters/chapter03.tex:16 - ITA · Un loop delimitato propose–act–observe
ITA/chapters/chapter03.tex:82
- EN · From suggestion to a permission-bounded agent
- W013 · Quantifying the Expectation-Realisation Gap for Agentic AI Systems
- EN · Agent capability as a testable hypothesis
EN/chapters/chapter03.tex:177 - ITA · Le capacità dell'agent come ipotesi verificabili
ITA/chapters/chapter03.tex:177
- EN · Agent capability as a testable hypothesis
- W034 · Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance
- EN · The task envelope
EN/chapters/chapter03.tex:39 - ITA · Il perimetro del task
ITA/chapters/chapter03.tex:39
- EN · The task envelope
- W060 · Your AI, My Shell: Demystifying Prompt Injection Attacks on Agentic AI Coding Editors
- EN · From suggestion to a permission-bounded agent
EN/chapters/chapter03.tex:16 - ITA · Dal suggerimento a un agent con permessi delimitati
ITA/chapters/chapter03.tex:16
- EN · From suggestion to a permission-bounded agent
- W071 · Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study
- EN · Common failure modes in real changes
EN/chapters/chapter03.tex:74 - ITA · Modalità di fallimento frequenti nelle modifiche reali
ITA/chapters/chapter03.tex:74
- EN · Common failure modes in real changes
- W079 · Correlated Errors in Large Language Models
- EN · When parallel agents help and hurt
EN/chapters/chapter03.tex:147 - ITA · Quando gli agent paralleli aiutano e quando peggiorano il risultato
ITA/chapters/chapter03.tex:147
- EN · When parallel agents help and hurt
- W095 · Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle
- EN · Agent capability as a testable hypothesis
EN/chapters/chapter03.tex:177 - ITA · Le capacità dell'agent come ipotesi verificabili
ITA/chapters/chapter03.tex:177
- EN · Agent capability as a testable hypothesis
- W101 · Articulate but Wrong: Self-Review Failures in LLM-Based Code Modernization
- EN · Stopping rules versus acceptance authority
EN/chapters/chapter03.tex:157 - ITA · Regole di arresto e autorità di accettazione
ITA/chapters/chapter03.tex:157
- EN · Stopping rules versus acceptance authority
- W111 · Many SWE-bench-Passing PRs Would Not Be Merged into Main
- EN · Stopping rules versus acceptance authority
EN/chapters/chapter03.tex:157 - ITA · Regole di arresto e autorità di accettazione
ITA/chapters/chapter03.tex:157
- EN · Stopping rules versus acceptance authority
- W151 · Blueprint First, Model Second: A Framework for Deterministic LLM Workflow
- EN · A bounded propose–act–observe loop
EN/chapters/chapter03.tex:82 - ITA · Un loop delimitato propose–act–observe
ITA/chapters/chapter03.tex:82
- EN · A bounded propose–act–observe loop
- W152 · Agentic Software Engineering: Foundational Pillars and a Research Roadmap
- EN · When parallel agents help and hurt
EN/chapters/chapter03.tex:147 - ITA · Quando gli agent paralleli aiutano e quando peggiorano il risultato
ITA/chapters/chapter03.tex:147
- EN · When parallel agents help and hurt
- W158 · Should I Give Up Now? Investigating LLM Pitfalls in Software Engineering
- EN · Common failure modes in real changes
EN/chapters/chapter03.tex:74 - ITA · Modalità di fallimento frequenti nelle modifiche reali
ITA/chapters/chapter03.tex:74
- EN · Common failure modes in real changes
- W191 · Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub
- EN · What an agent actually observes
EN/chapters/chapter03.tex:31 - EN · The task envelope
EN/chapters/chapter03.tex:39 - EN · Common failure modes in real changes
EN/chapters/chapter03.tex:74 - EN · A bounded propose–act–observe loop
EN/chapters/chapter03.tex:82 - ITA · Che cosa osserva realmente un agent
ITA/chapters/chapter03.tex:31 - ITA · Il perimetro del task
ITA/chapters/chapter03.tex:39 - ITA · Modalità di fallimento frequenti nelle modifiche reali
ITA/chapters/chapter03.tex:74 - ITA · Un loop delimitato propose–act–observe
ITA/chapters/chapter03.tex:82
- EN · What an agent actually observes
- W193 · MirrorCode: Evidence that AI can already do some weeks-long coding tasks
- EN · The task envelope
EN/chapters/chapter03.tex:39 - ITA · Il perimetro del task
ITA/chapters/chapter03.tex:39
- EN · The task envelope
Editorial reading mappings
Broader topical suggestions can overlap the cited sources. A mapping does not add a citation to the published edition or establish that a practice is effective.
SE@PoliMi bibliography 52
- W002 — Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows
Chen · 2026 - W005 — Early Adoption of Agentic Coding Tools by GitHub Projects
Raida · 2026 - W011 — The Productivity-Reliability Paradox: Specification-Driven Governance for AI-Augmented Software Development
Farrag · 2026 - W012 — Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale
Liu · 2026 - W013 — Quantifying the Expectation-Realisation Gap for Agentic AI Systems
Lobentanzer · 2026 - W014 — Adoption and Impact of Command-Line AI Coding Agents: A Study of Microsoft's Early 2026 Rollout of Claude Code and GitHub Copilot CLI
Murphy-Hill · 2026 - W031 — More Code, Less Reuse: Investigating Code Quality and Reviewer Sentiment towards AI-generated Pull Requests
Huang · 2026 - W034 — Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance
Pinna · 2026 - W037 — After the Party: Growth, Governance, and Security Scanning in the OpenClaw Agent Skill Ecosystem
Xiong · 2026 - W038 — Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code Generation
Yan · 2026 - W041 — Security Vulnerabilities in AI-Generated Code: A Large-Scale Analysis of Public GitHub Repositories
Schreiber · 2025 - W042 — Security Degradation in Iterative AI Code Generation: A Systematic Analysis of the Paradox
Shukla · 2025 - W043 — We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs
Spracklen · 2025 - W045 — Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks
Zhao · 2025 - W046 — Do Users Write More Insecure Code with AI Assistants?
Perry · 2023 - W048 — Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions
Pearce · 2022 - W049 — The Range Shrinks, the Threat Remains: Re-evaluating LLM Package Hallucinations on the 2026 Frontier-Model Cohort
Churilov · 2026 - W052 — What is the Difference Between Me and You? Benchmarking the Quality Gap Between Human-Written and AI-Generated Code
Improta · 2026 - W056 — A Large-Scale Comprehensive Measurement of AI-Generated Code in Real-World Repositories
Mao · 2026 - W060 — Your AI, My Shell: Demystifying Prompt Injection Attacks on Agentic AI Coding Editors
Liu · 2025 - W061 — 2025 GenAI Code Security Report
Veracode · 2025 - W062 — Vibe Security Radar
Zhao · 2026 - W068 — Behind Agentic Pull Requests: An Empirical Study on Developer Interventions in AI Agent-Authored Pull Requests
Khelifi · 2026 - W071 — Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study
Peralta · 2026 - W075 — Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in LLMs
Tsui · 2026 - W076 — SWR-Bench: Assessing LLM Performance in Real-World Code Review Comment Generation
Zeng · 2026 - W077 — Evaluating and Mitigating the Misguidance Effect of Buggy Code in LLM-Generated Unit Tests
Zhao · 2026 - W079 — Correlated Errors in Large Language Models
Kim · 2025 - W082 — LLM Evaluators Recognize and Favor Their Own Generations
Panickssery · 2024 - W089 — The Role of Domain Expertise in User Trust and the Impact of First Impressions with Intelligent Systems
Nourani · 2020 - W094 — AI Slop is DDoSing Open Source: Understanding the Impact of AI-Generated Contributions on Open Source Sustainability
Afroz · 2026 - W095 — Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle
Bhati · 2026 - W099 — From Code Review to Code Critique: Intent, Drift, and Spotlight for AI-Generated Diffs at Scale
Maddila · 2026 - W101 — Articulate but Wrong: Self-Review Failures in LLM-Based Code Modernization
Purnachandra Reddy · 2026 - W102 — Cross-Model LLM Code Review: Should You Use Claude to Review Codex or Vice Versa?
Xiang · 2026 - W104 — Coding with Enemy: Can Human Developers Detect AI Agent Sabotage?
Ye · 2026 - W106 — Code Review Agent Benchmark (c-CRAB)
Zhang · 2026 - W108 — Do LLM Evaluators Prefer Themselves for a Reason?
Chen · 2025 - W109 — LLM Critics Help Catch LLM Bugs
McAleese · 2024 - W111 — Many SWE-bench-Passing PRs Would Not Be Merged into Main
Whitfill · 2026 - W142 — AI Is Probably Not (Yet) the Reason for Labor Market Weakening
Nunn · 2026 - W148 — SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents
Lin · 2026 - W151 — Blueprint First, Model Second: A Framework for Deterministic LLM Workflow
Qiu · 2026 - W152 — Agentic Software Engineering: Foundational Pillars and a Research Roadmap
Hassan · 2026 - W157 — ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents
Rafique · 2026 - W158 — Should I Give Up Now? Investigating LLM Pitfalls in Software Engineering
Tie · 2026 - W159 — Memory Management and Contextual Consistency for Long-Running Low-Code Agents
Xu · 2026 - W160 — AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents
Anokhin · 2025 - W171 — Revisiting Turnover-Induced Knowledge Loss in Software Projects
Nassif · 2017 - W191 — Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub
Ehsani · 2026 - W192 — AIDev: Studying AI Coding Agents on GitHub
Li · 2026 - W193 — MirrorCode: Evidence that AI can already do some weeks-long coding tasks
METR / Epoch AI · 2026
Addy Osmani 9
- O006 — Practical Loop Engineering
Addy Osmani · 2026-08-14 - O010 — Agentic Autonomy Levels
Addy Osmani · 2026-07-03 - O012 — Loop Engineering
Addy Osmani · 2026-06-08 - O020 — How Good Is AI at Coding React (Really)?
Addy Osmani · 2025-12-29 - O026 — Gemini CLI Tips & Tricks
Addy Osmani · 2025-10-21 - O030 — Coding for the Future Agentic World
Addy Osmani · 2025-07-29 - O038 — What are AI Agents? why do they matter?
Addy Osmani · 2025-04-11 - O046 — Why I use Cline for AI Engineering
Addy Osmani · 2025-01-30 - O047 — AI-Driven Prototyping: v0, Bolt, and Lovable Compared
Addy Osmani · 2025-01-11
The Pragmatic Engineer 10
- P034 — MCP Protocol: a new AI dev tools building block
Gergely Orosz · 2025-04-08 - P062 — How Claude Code is built
Gergely Orosz · 2025-09-23 - P070 — New trend: programming by kicking off parallel AI agents
Gergely Orosz · 2025-10-30 - P077 — Building MCP servers in the real world
Gergely Orosz; Elin Nilsson · 2025-12-09 - P085 — Deepdive: How 10 tech companies choose the next generation of dev tools
Gergely Orosz · 2026-02-03 - P086 — Steve Yegge on AI Agents and the Future of Software Engineering
Gergely Orosz · 2026-02-10 - P087 — How Codex is built
Gergely Orosz · 2026-02-17 - P110 — What is “loop engineering?”
Gergely Orosz · 2026-07-14 - P115 — Why Ramp built its own in-house coding agent, Inspect
Gergely Orosz; Jessica Salmon; Ivan Klaric · 2026-08-25 - P119 — Inside OpenAI’s agentic software factory
Gergely Orosz · 2026-09-15
Martin Fowler’s website 19
- F001 — The toolchain
Birgitta Böckeler · 2023-07-26 - F003 — In-line assistance - when is it more useful?
Birgitta Böckeler · 2023-08-01 - F006 — TDD with GitHub Copilot
Paul Sobocinski · 2023-08-17 - F008 — How to tackle unreliability of coding assistants
Birgitta Böckeler · 2023-11-29 - F010 — Building an AI agent application to migrate a tech stack
Birgitta Böckeler · 2024-08-20 - F011 — Expanding the solution size with multi-file editing
Birgitta Böckeler · 2024-11-19 - F012 — What role does LLM reasoning play for software tasks?
Birgitta Böckeler · 2025-02-18 - F015 — Building TMT Mirror Visualization with LLM: A Step-by-Step Journey
Unmesh Joshi · 2025-04-30 - F016 — Coding Assistants Threaten the Software Supply Chain
Jim Gumbley; Lilly Ryan · 2025-05-13 - F017 — Building Custom Tooling with LLMs
Unmesh Joshi · 2025-05-14 - F018 — Autonomous coding agents: A Codex example
Birgitta Böckeler · 2025-06-04 - F025 — Context Engineering for Coding Agents
Birgitta Böckeler · 2026-02-05 - F026 — Harness Engineering - first thoughts
Birgitta Böckeler · 2026-02-17 - F027 — Humans and Agents in Software Engineering Loops
Kief Morris · 2026-03-04 - F028 — Viability of local models for coding
Birgitta Böckeler · 2026-07-07 - F029 — Experiences with local models for coding
Birgitta Böckeler · 2026-07-08 - F031 — TDD inside the agent loop - theater or actual value?
Birgitta Böckeler · 2026-08-10 - F032 — An Accidental Blackboard
Giles Edwards-Alexander · 2026-09-02 - F033 — Are Harnesses Worth the Cost?
Naresh Jain · 2026-10-13
Earlier Non-Deterministic books 44
- B007 — New Workflows for the AI Era
Enrico Papalini · - B015 — PART III: Team Workflows
Enrico Papalini · - B019 — Tools \& Practices
Enrico Papalini · - B021 — Getting Started: Choosing Your Primary Tool
Enrico Papalini · - B024 — Context Flow Control: Managing Complex Sessions
Enrico Papalini · - B025 — From Single Agent to Multi-Agent Workflows
Enrico Papalini · - B030 — Common Pitfalls to Avoid
Enrico Papalini · - B034 — Implementation Guide and Solutions
Enrico Papalini · - B040 — The Toolkit
Enrico Papalini · - B051 — Anatomy of an AI SDD Framework
Enrico Papalini · - B052 — The Ecosystem: A Map of Public Frameworks
Enrico Papalini · - B053 — The Lightweight Protocols: GSD v1 and GSD-2
Enrico Papalini · - B055 — The Agentic Orchestrators: BMAD Method and AI-RPI Protocol
Enrico Papalini · - B056 — Autonomous Loops and Behavioral Foundations
Enrico Papalini · - B057 — The Comparison: Patterns, Divergences, and Convergences
Enrico Papalini · - B061 — Automation and Extensibility: CLI, Modules, and MCP
Enrico Papalini · - B062 — Autonomous Execution: Modes, Budgets, and Governance
Enrico Papalini · - B066 — Installation and Setup
Enrico Papalini · - B069 — Framework Reference Cards
Enrico Papalini · - B075 — ralph-copilot
Enrico Papalini · - B076 — Spec Loop Engine
Enrico Papalini · - B078 — GSD-2
Enrico Papalini · - B080 — Agent Skills
Enrico Papalini · - B083 — Introduzioni e postfazione — The Autonomous Future
Enrico Papalini · - B084 — Preface
Enrico Papalini · - B085 — The Continuous Development Revolution
Enrico Papalini · - B086 — The Philosophy of Deterministic Failure
Enrico Papalini · - B087 — The Developer Evolution Model
Enrico Papalini · - B088 — The Ralph Loop Pattern
Enrico Papalini · - B093 — Agentic Patterns in Practice
Enrico Papalini · - B094 — Scheduling and Overnight Execution
Enrico Papalini · - B095 — Multi-Agent Orchestration
Enrico Papalini · - B097 — Complete Implementation Guide
Enrico Papalini · - B098 — Tool Reference
Enrico Papalini · - B099 — Troubleshooting and Debugging
Enrico Papalini · - B100 — Ralph Loops with VS Code and GitHub Copilot
Enrico Papalini · - B101 — References and Sources
Enrico Papalini · - B103 — Summary
Enrico Papalini · - B104 — Non-Deterministic Loop Engineering: A Critical Assessment
Enrico Papalini · - B107 — The Ralph Loop: Persistent Progress Through Fresh Context
Enrico Papalini · - B108 — Building a Full Local AI Loop
Enrico Papalini · - B109 — Choosing the Right Loop
Enrico Papalini · - B110 — References — 85 voci bibliografiche
Enrico Papalini · - B111 — Glossary
Enrico Papalini ·
Software Engineering Practices 14
- PAT:001 — Plan-Then-Execute
- PAT:004 — Initializer-Maintainer Dual Agent Architecture
- PAT:011 — Reward Shaping for Tool Use
- PAT:013 — Agent Reinforcement Fine-Tuning
- PAT:021 — Tool Call Budget
- PAT:023 — The External Bash Loop
- PAT:024 — The Stop-Hook Loop
- PAT:025 — The Editor-Native Manual Loop
- PAT:026 — Run Until Done: Retry Against Reality
- PAT:046 — Small Verifiable Chunks
- PAT:065 — Model Switching for Regeneration
- PAT:073 — Multi-Mode Agent
- PAT:081 — One-Item-Per-Cycle
- PAT:083 — Budget-Gated Autonomy