Library

You Shouldn't Be Prompting Coding Agents Anymore — Design Loops

@steipete · Jun 21

Peter Steinberger's Jun 8 tweet (6.5M views) seeded the loop-engineering naming wave: stop prompting agents, design loops that prompt your agents. The origin post that Osmani's essay, Cherny's post, and the entire June 2026 discourse cite.

autoresearch: Remove Yourself as the Bottleneck

@karpathy · Jun 21

Andrej Karpathy on his autoresearch loop: a single-file nanochat where an agent loops on a git branch to lower validation loss. Remove yourself as the bottleneck, put in few tokens, huge amount happens.

Inspect: Ramp Background Coding Agent (75% of Code)

@rahulgs · Jun 21

Rahul Sengottuvelu reports that Inspect, Ramp's background coding agent, now produces 75%+ of Ramp's code. What got them there: sustained loop infrastructure — every repo agent-ready, every command performant, every feedback fast and truthful.

2026 AI Software Architecture Predictions

Dan Shipper 📧 · May 31

Dan Shipper predicts four major shifts in software development by 2026: agent-native architectures where apps are prompts to general AI agents, empowered designers who can build without engineers, agentic engineering as a new no-code discipline, and AI training focused on autonomous self-direction rather than human-pleasing. These changes stem from AI making software development dramatically cheaper and more accessible.

AI Output Evolution: Text to Interactive Visual Media

Andrej Karpathy · May 17

Andrej Karpathy argues that AI-human interaction is evolving from text-based outputs toward visual and interactive formats. He suggests a progression from raw text to markdown to HTML, eventually reaching interactive neural videos/simulations generated by diffusion models.

AI Context Persistence Problem in Development

Taelin · May 17

Working with AI agents is frustrating because each new session requires re-explaining domain knowledge. Existing solutions like AGENTS.md, RAGs, and skills don't solve the 'unknown unknowns' problem where the AI can't search for knowledge it doesn't know it needs.

AI Impact on Small Business Valuation Models

M&A Focused CPA · Apr 7

Traditional SMB valuation uses five levers: cash flow, owner compensation, durability, transferability, and growth rate, typically yielding 3-5x EBITDA. AI is disrupting this by enabling businesses to break through the $2-3M revenue ceiling that previously required risky system investments, while dramatically improving margin structures by replacing labor costs.

Neofirms: AI-Era Professional Services Evolution

Ryan Daniels · Apr 6

Professional services firms must transform from traditional partnerships focused on human talent to 'Neofirms' that blend practitioners with AI researchers. These new firms use corporate structures enabling R&D investment, bill for outcomes rather than hours, and continuously redefine the human-machine frontier.

AI Disruption of BigLaw Economic Model

Zack Shapiro · Apr 6

BigLaw firms' economic model relies on leverage - partners distributing work to numerous associates who bill high rates for labor-intensive tasks. AI threatens this by enabling complex legal work to be done with radically fewer human hours, making the associate-heavy pyramid structure economically unsustainable.

AI Job Impact: Production vs Judgment Tasks

Zack Shapiro · Apr 6

AI is rapidly commoditizing skilled production work (research, drafting, analysis) but cannot replace judgment-based tasks that require contextual decision-making and strategic thinking. A two-person law firm example shows how AI handles 90% of document analysis but cannot make strategic decisions about deal dynamics or client relationships.

LLM-Managed Personal Knowledge Base System

Andrej Karpathy · Apr 3

Andrej Karpathy describes a workflow where LLMs automatically build and maintain personal wikis from raw documents, creating structured markdown files with summaries, backlinks, and categorized concepts. The system uses Obsidian as an IDE frontend and enables complex Q&A against the knowledge base without traditional RAG systems.

Processing failed

ashu garg · Apr 3

Could not process content automatically.

AI Agent Evolution and Market Implications 2026

logan bartlett · Mar 30

AI is progressing from productivity copilots to autonomous task agents, expanding addressable markets from $0.5T software spend to potentially $6.2T knowledge worker compensation. Current software selloffs affect horizontal SaaS (-35%) more than vertical SaaS (+3%) due to different defensive moats against AI disruption.

Enterprise AI Adoption: Four Stages Framework

ashu garg · Mar 28

Enterprise AI adoption follows four stages: no AI usage, pilot sprawl without strategy, measurable productivity gains, and full process redesign. Most enterprises remain stuck at stage two with many pilots but no clear outcomes. Success requires picking real business problems, building proper data infrastructure, and organizational commitment to process change.

Plan-First Development with AI Agents

Matt Van Horn · Mar 23

A development methodology that inverts traditional coding: spend 80% of time planning with AI agents and 20% executing, using structured plan.md files as persistent context. Multiple AI research agents analyze codebases, past solutions, and external docs in parallel to create grounded, specific plans before any coding begins.

Claude Code Skills Categories and Best Practices

Thariq · Mar 18

Skills in Claude Code are flexible extension points that go beyond simple markdown files - they're folders containing scripts, assets, and data. At Anthropic, hundreds of skills cluster into four main categories: Reference (library/CLI usage), Verification (testing code correctness), Data (connecting to monitoring stacks), and Workflow (automating repetitive tasks).

Institutional AI vs Individual AI Productivity

George Sivulka · Mar 13

AI makes individuals 10x more productive but doesn't translate to organizational value without structural changes. Like electricity in textile mills (1890s-1920s), the technology must be paired with institutional redesign to realize productivity gains. Individual AI creates chaos without coordination layers.

AI-Generated Design Anti-Patterns and Detection

Paul Bakaus · Mar 5

Paul Bakaus identifies common visual and UX patterns that reveal AI-generated or low-effort design work. These include obvious signs like purple gradients and overused fonts, plus subtle indicators like excessive card layouts, redundant copy, and templated design patterns.

Simplicity Over Complexity in AI Agent Development

sysls · Mar 4

An experienced developer argues that maximizing AI agent capabilities doesn't require complex harnesses, plugins, or tools. Instead, simple CLI setups with basic principles work better, as each new AI generation changes optimal approaches and frontier companies incorporate truly useful solutions into their products.

Processing failed

Ashpreet Bedi · Mar 2

Could not process content automatically.

Processing failed

Thariq · Feb 28

Could not process content automatically.

AI Agent Architecture and Design Principles

vas · Feb 27

AI agents are goal-driven systems that take autonomous actions through a loop of observation, decision-making, and action execution, differing from simple automation by handling exceptions and learning from guidance. Production agents require three core components: perception (APIs, databases), decision logic (structured trees plus models), and action interfaces (logged, reversible, permission-gated functions).

Agent Security Architecture Patterns

Larsen Cundric · Feb 27

Browser Use evolved from AWS Lambda to Unikraft micro-VMs using two security patterns: isolating dangerous tools vs isolating entire agents. They chose Pattern 2, running agents in zero-secret sandboxes that communicate through a control plane holding all credentials.

AI Service Pricing Tiers and Delivery Models

Luke Pierce · Feb 26

Luke Pierce outlines a structured progression from $500 AI tool setups to $60K+ enterprise builds, detailing required timelines, team sizes, and deliverables at each tier. Each price point demands different skills: communication for low-tier setups, strategic thinking for audits, and systems architecture for department-wide builds.

Separating AI-Generated Content from Personal Knowledge

James Bedford · Feb 26

James Bedford describes structuring file systems to keep AI-generated content (transcripts, meeting notes) separate from personal knowledge bases like Obsidian vaults. He uses a dedicated Claude folder with subfolders for Github repos, meeting notes, and maintains his Obsidian vault exclusively for personal writing and thinking.

Agent Memory Through Structural Feedback Loops

Atlas Forge · Feb 25

Agents lose all learning between sessions due to context window resets. The solution is building persistent feedback loops into agent files where failures become guardrails, using three levels: reactive (fix what broke), reflective (extract patterns), and generative (system improves itself).

AI Native Vertical SaaS Building Framework

GREG ISENBERG · Feb 25

Greg Isenberg outlines an 18-step framework for building AI-native vertical SaaS products in the Claude Cowork era. The approach focuses on identifying sub-niches, mapping workflows, integrating Claude with existing enterprise tools, and gradually expanding within verticals while building compound memory and context.

Excel AI Agent Architecture Comparison Study

Nicolas Bustamante · Feb 25

Reverse engineering analysis of three production Excel AI agents (Claude, Microsoft Copilot, Shortcut AI) reveals significant architectural differences in tool design, data loading strategies, and verification systems. The study found that tool architecture matters more than the underlying model, with each agent taking different approaches to structured schemas, overwrite protection, and spreadsheet interaction patterns.

AI Agent Orchestration for Parallel Development

prateek · Feb 24

A developer created a self-improving AI orchestrator that manages multiple coding agents in parallel, handling CI failures, PR reviews, and task coordination automatically. The system evolved from bash scripts to 40,000 lines of TypeScript in 8 days, with the orchestrator itself being an AI agent rather than just automation.

AI Agents Disrupting SaaS Business Models

John Rush · Feb 23

AI agents with API connections are collapsing multiple SaaS tools into single chat interfaces, eliminating traditional UI value and switching costs. This commoditizes most SaaS products, forcing a race to the bottom on pricing while creating opportunities for agent orchestration layers.

AI Agents as Business Operating Systems

Nicolas Bustamante · Feb 23

Nicolas Bustamante describes running his company entirely through AI agents that connect to SaaS APIs, eliminating traditional UI interactions. His agent handles banking, CRM, analytics, and other tools through natural language, merging context across systems and maintaining decision logs.

Vertical AI Software Moats Through Process Engineering

George Sivulka · Feb 19

Vertical AI software companies maintain competitive advantages not through code but by deeply understanding specific organizational processes and workflows. While general-purpose AI models serve broad use cases, vertical software embeds opinionated workflows tailored to specific teams' idiosyncratic needs, creating network effects and defensible moats.

AI-Powered Code Review Pipeline with Risk-Based Gates

Ryan Carson · Feb 19

A systematic approach to integrating coding agents and review agents into development workflows using risk-tiered policies, machine-verifiable evidence, and automated quality gates. The system enforces different validation requirements based on code path risk levels and maintains state consistency through commit SHA tracking.

Processing failed

Nicolas Bustamante · Feb 17

Could not process content automatically.

AI Fatigue and Productivity Paradox

Owen Gregorian · Feb 10

AI tools make individual tasks faster but create cognitive exhaustion by increasing task volume and shifting engineers from creative work to constant review/evaluation. The efficiency gains lead to higher expectations and more context-switching, while transforming the satisfying work of creation into draining decision-making about AI output quality.

Agentic Visual Creation Workflow Loop

elvis · Feb 8

A method for AI image generation that uses iterative feedback loops: generate an image, visually annotate what needs improvement, automatically compile feedback into structured prompts, and regenerate until quality standards are met. This replaces single-shot prompting with a continuous refinement process using tools like Claude Code with image generation and annotation plugins.

Compound Engineering for Claude Code Improvement

Peter Yang · Feb 8

A 4-step system to make Claude Code progressively smarter: Plan (sub-agents research codebase), Work (Claude builds features with clarification), Assess (review agents check quality), and Compound (capture learnings to avoid repeating mistakes). This approach creates a feedback loop where each coding session improves future performance.

Recursive Self-Improvement Loops for AI Prompting

J.B. · Feb 7

A prompting technique where AI generates output, evaluates it against specific scoring criteria, diagnoses weaknesses, rewrites, and repeats until quality thresholds are met. The pattern follows: generate → evaluate → diagnose → improve → repeat, with adversarial testing to ensure robustness.

AI Agents Disrupting Enterprise Systems of Record

Zain Hoda · Feb 7

AI agents are undermining traditional enterprise systems of record (like Salesforce, Workday) by copying their data through APIs and becoming the primary interaction layer. While enterprise data is small enough to be easily replicated, the defensible position of being the authoritative data source collapses when agents cache everything locally and users interact primarily with the agent rather than the original system.

AI Prompting as Behavior Engineering

klöss · Jan 30

Effective AI prompting requires treating language models as pattern-completion engines that need complete contracts, not vague requests. Most people fail because they treat AI like a search engine instead of understanding it generates statistically probable outputs based on input quality.

LLM Coding Workflow Transformation and Best Practices

Andrej Karpathy · Jan 27

Andrej Karpathy describes his rapid shift from 80% manual coding to 80% AI-assisted coding in December 2022, highlighting both the power and pitfalls of current LLM coding capabilities. He notes that while models excel at large code actions and tireless iteration, they make subtle conceptual errors, overcomplicate solutions, and need human oversight through IDEs.

AI-Generated Code Security Vulnerabilities

Burak Eregar · Jan 25

AI tools enable rapid app development but create security crises through direct database access patterns. Common vulnerabilities include client-side business logic, inadequate column protection, and self-DDoS attacks via unlimited database queries.

AI Agent Memory as Infrastructure Pattern

Rohit · Jan 18

Traditional approaches to AI agent memory using vector databases fail at scale because they can't handle conflicting information over time or distinguish between outdated and current data. Memory should be treated as evolving infrastructure with checkpointing for short-term state and hierarchical architectures for long-term knowledge retention.

Multi-Agent System Orchestration Patterns

Rohit Ghumare · Jan 17

Multi-agent systems solve single agent limitations through three coordination patterns: supervisor (centralized control), peer-to-peer (distributed communication), and hierarchical (recursive supervision). Each pattern trades off coordination overhead against specialization, parallel processing, and maintainability benefits.

Spec-First Development with AI Coding Agents

Ashpreet Bedi · Jan 14

A structured approach to building complex software features using AI coding agents like Claude, where humans define requirements through detailed specifications and the AI handles implementation. Uses symlinked spec directories with standardized documentation templates to maintain context across development sessions.

Rohit

Rohit · Jan 13

Agent-Native App Architecture Design Principles

Dan Shipper 📧 · Jan 13

Agent-native architecture replaces traditional code-defined behavior with natural language outcome definitions, where agents use atomic tools to achieve goals. Key principles include parity (agents can do anything users can), granularity (features as prompts, not tools), and composability (combining tool calls in novel ways).

AI-Assisted Vibe Coding Development Approach

Ben Tossell · Jan 13

Ben Tossell describes spending 3 billion tokens over four months using AI agents to write code through terminal interfaces, creating numerous projects including personal sites, CLIs, and automation tools. This 'vibe-coding' approach involves reading agent outputs religiously to learn programming concepts without directly writing code, representing a new class of technical learning.

Context Management in Production AI Agents

@vasuman · Jan 12

Most AI agents fail in production because they lack proper context management - they don't remember task history, lose information between steps, or lack domain knowledge. Successful enterprise agents require structured information flow, comprehensive memory of previous actions, and deep domain understanding to operate effectively.