AI Concepts

An interoperability protocol for connecting AI systems and tools. Here it is described through a public roadmap covering long-running workloads, local-server HTTP, discovery, identities, permissions, and generated SDKs.

MCP is an interoperability protocol that standardizes how AI systems connect to tools, services, and context sources.

Autonomous or semi-autonomous AI systems that use tools, manage context, and complete tasks on behalf of users. The newsletter discusses common blockers such as tool quality, context overload, and system verification.

AI agents are multi-step systems that use tools, memory, and context to complete tasks on behalf of users.

An AI development pattern where models act more like autonomous coding agents. The newsletter uses it to describe both NVIDIA Dynamo’s target workload and GPT-5.5/Codex improvements.

Agentic coding describes AI systems that act more like autonomous software agents than simple code assistants.

An AI-native development approach where builders use AI tools to rapidly create software. The newsletter treats it as a growth and product-building methodology.

Vibe-coding is an AI-native software creation approach that compresses the path from idea to working product.

An agent framework/architecture that separates the agent loop from backend operations like filesystem access and optional sandboxed code execution. Useful for building agents with flexible local/cloud deployment and multiple interfaces.

Deepagents separates the agent loop from backend operations like filesystem access and optional sandboxed code execution.

A security risk in agentic systems where malicious instructions can manipulate model behavior through retrieved or connected content. The newsletter references it as a design and safety concern for agents.

Prompt injection is a core security risk in agentic systems because untrusted external content can override intended model behavior.

RAG is a retrieval-based pattern that injects external context into prompts to improve model responses. The newsletter presents it as often outperforming fine-tuning for practical product work.

RAG retrieves external information at runtime and injects it into prompts so models can answer with fresher, domain-specific context.

The practice of structuring prompts and surrounding context to improve model performance. In this newsletter it is framed specifically for Claude 5 generation models.

Context engineering extends prompt engineering by structuring the full information environment around a model, including retrieval, memory, tools, and tool outputs.

A protocol or capability layer mentioned as part of an open, composable extension philosophy for AI tooling. It is grouped with MCP and Plugins.

Skills emerged as both an open ecosystem for installable AI capabilities and a product pattern for steering agent behavior.

A large language model used as the reasoning core inside agents and tool-calling systems. PMs often evaluate LLMs based on orchestration, context loading, and task execution behavior.

LLMs increasingly serve as the reasoning core inside agents, not just as standalone chat interfaces.

Specialized subordinate agents used to break down and orchestrate tasks. The newsletter mentions them as part of Claude Code steering controls.

Subagents are specialized subordinate agents used to decompose large tasks into smaller, scoped units of work.

Autonomous software agents that write, maintain, and redesign code systems. For PMs, they represent a shift in how engineering and research work gets allocated.

Coding agents go beyond autocomplete by handling multi-step software tasks such as debugging, documentation, refactoring, and redesign.

A research capability embedded into Perplexity Computer as a built-in skill. For PMs, it indicates the packaging of advanced research into agent workflows.

Deep Research packages multi-step research into reusable AI workflows rather than standalone prompts.

A training approach where a model learns behavior from feedback or trajectories. The newsletter references it as part of an enterprise architecture for learning good and bad outcomes from business actions.

Reinforcement learning trains models from outcomes and trajectories instead of relying only on prompts or labeled examples.

Large language models are referenced as capable of writing essays but limited in physical task learning and control. The newsletter uses them as a baseline for comparing future architectures.

LLMs are foundational to many generative AI products but are best understood as powerful language models, not universal intelligence systems.

A pattern that grounds model outputs by retrieving external information at inference time. The newsletter positions it as a stronger default than fine-tuning for many use cases.

RAG grounds model outputs by retrieving external information at inference time instead of relying only on pretrained or fine-tuned knowledge.

Agent Skills are reusable capability modules or instructional patterns for agents. The newsletter references a React best-practices tutorial framed as an agent skill.

Agent Skills package reusable instructions, workflows, and best practices into modular capabilities for AI agents.

A framework for measuring whether AI agents reliably complete tasks across real inputs, edge cases, and version changes. It emphasizes step-level traces and component-level decisions, not just final output quality.

Agent evaluation measures not only final outputs but also the steps, tool calls, and component decisions behind them.

Benchmarking methods for evaluating AI coding agents in realistic software tasks. The newsletter notes that infrastructure variability can materially affect scores.

Agentic coding evals test AI coding agents on realistic software tasks such as debugging, editing files, and running tools.

A model adaptation technique using task-specific training data. The newsletter frames it as often inferior to RAG for many PM and product use cases, though useful for format, tone, and some reasoning tasks.

Fine-tuning adapts a base model using task-specific examples, but it is not always the best first move for product teams.

A workflow for using AI agents to plan, build, test, and update software with minimal manual intervention. The newsletter treats it as a practical product-development paradigm.

Agentic engineering is a software development approach where AI agents help plan, build, test, and update products with minimal manual intervention.

A plugin/pattern used to manage build loops and goal-driven agent workflows. Here it is tied to Codex Desktop and the LFG loop for prototype completion.

Compound Engineering turns AI coding from one-off prompting into a repeatable loop of planning, execution, assessment, and codified learning.

A security risk pattern where AI agents have private data access, ingest untrusted content, and can exfiltrate data. For AI PMs, it is a key framework for designing safe agent features.

The lethal trifecta describes the high-risk combination of private data access, untrusted content ingestion, and data exfiltration capability.

AGI refers to broadly capable artificial general intelligence. Here it is discussed as becoming usable in 2026 and requiring contextual systems around it to be effective.

AGI is presented here as an emerging practical capability in 2026, not just a long-term research concept.

A collection of techniques and patterns for building agentic systems. The newsletter frames it as a guide page for AI builders.

Agentic Engineering Patterns is a guide that collects practical techniques for building and operating agentic systems.

An approach to AI systems where agents perform tasks autonomously with tools and browser interaction. The newsletter frames 2026 as a year focused less on novelty and more on trust in deployed agentic systems.

Agentic AI describes systems that autonomously plan, use tools, and complete multi-step tasks rather than only generating outputs.

A test-driven development pattern adapted for coding agents. It emphasizes an iterative failure/success loop that can make agentic coding more reliable.

Red/green TDD adapts traditional test-driven development into a structured workflow for coding agents.

Reusable Claude-based skill modules that package agentic workflows into portable components. The newsletter frames them as a way to avoid building AI agents from scratch.

Claude skills turn repeatable AI workflows into portable modules that can be reused instead of rebuilt.

A lexical retrieval ranking function used here to select relevant tool definitions. In PM tooling, it helps improve retrieval accuracy and reduce context-window bloat.

BM25 is a lexical ranking function that helps AI systems retrieve the most relevant documents or tool definitions.

A paradigm that treats cloud infrastructure as autonomous coding agents to automate deployment and operations. For AI PMs, it reframes infrastructure as an agentic workflow rather than a static system.

Agentic Infrastructure reframes cloud operations as autonomous coding-agent workflows rather than static systems.

A standard endpoint/protocol for agent-to-agent or agent interoperability, mentioned here alongside MCP as a supported interface. It matters to PMs as part of agent connectivity and integration strategy.

A2A is a pattern and protocol framing for how multiple AI agents communicate and collaborate.

A concept covering how organizations evaluate large language models consistently and meaningfully. The newsletter frames standardization of benchmarks as a major enterprise challenge.

LLM benchmarks give organizations a repeatable way to compare model performance on real product tasks.

A software architecture paradigm where engineers orchestrate agents instead of hard-coding decision trees. For PMs, it suggests product teams may design systems around LLM behavior rather than deterministic logic.

Agent-first software design shifts software building from hard-coded decision trees to orchestrated agent behavior.

A product and engineering concept describing the hidden cost of AI-accelerated development when teams lose shared understanding of the system. It reframes debt from code maintenance to team cognition and system comprehension.

Cognitive debt describes how AI-accelerated development can shift costs from code maintenance into lost team understanding.

A programming language commonly used for building AI systems and agent workflows. The newsletter references it in the context of constructing multi-agent systems from scratch.

Python is the dominant implementation layer for modern AI experimentation, orchestration, and agent workflows.

OpenTelemetry is an observability standard for traces, logs, and metrics. The newsletter mentions Codex exporting agent-aware telemetry through it for auditing and monitoring.

OpenTelemetry is a standard for collecting traces, logs, and metrics across software and AI systems.

A memory architecture pattern for AI agents that separates different memory layers to improve context retention and task performance. It is presented as part of the design of autonomous coding assistants.

Layered memory separates short-term, task-level, and longer-term memory to improve AI agent performance.

The process of updating legacy COBOL systems, often for enterprise migration and maintenance. AI agents are increasingly positioned as tools to accelerate this high-friction modernization work.

COBOL modernization focuses on updating legacy mission-critical systems for maintainability, integration, and migration.

A lightweight skills-based pattern for packaging agent capabilities in small context-efficient files.

skill.md is a lightweight pattern for packaging agent capabilities into small, context-efficient files.

Leading AI labs that control high-demand model APIs and compute. The newsletter uses the term to describe vendors that might restrict API access to prioritize their own products and customers.

Frontier AI labs control highly demanded model APIs and may prioritize their own products or top customers when compute is scarce.

A workflow framework for building customizable agentic systems. It is highlighted as integrating with ACP.

Agent Workflows is a framework for building customizable agentic systems within the LlamaIndex ecosystem.

Programmable interfaces that let AI agents and software systems access services and complete tasks. The newsletter positions APIs as one of the means for agents to act on behalf of users.

APIs let AI agents access services and take actions on behalf of users.

AI models whose weights or availability are open enough to encourage broad reuse and experimentation. The newsletter frames them as a driver of innovation across the ecosystem.

Open models are framed in the newsletter as a major driver of AI innovation across startups, researchers, students, and industries.

Systems composed of multiple cooperating AI agents, often designed to divide work and collaborate through structured patterns. The newsletter references building these systems with Python and agent-to-agent communication patterns.

Multi-agent systems divide work across specialized AI agents that coordinate through structured communication patterns.

A test introduced by Andrew Ng for evaluating economic utility. It is framed as a way to assess whether AI systems provide meaningful real-world value.

The Turing-AGI Test evaluates AI progress based on economic utility rather than abstract intelligence claims.

A structured-prompt framework for improving the consistency and quality of outputs from Claude Code. It is positioned as a way to turn an AI coding assistant into a more reliable development partner.

SuperClaude is a community framework that uses structured prompts to improve the consistency of Claude Code outputs.

A modular layer that adds tools, guardrails, and custom instructions to AI agents. It is described as a composable harness for production agent systems.

Agent middleware is a modular layer for adding tools, guardrails, and instructions to AI agents.

The practice of connecting agents to external developer tools such as linters and debuggers. It is highlighted here as a building block for effective coding agents.

Tool integration connects AI agents to external developer tools such as linters, debuggers, and test runners.

A defensive technique mentioned as part of Claude Code's strategy to deter model distillation by misleading competitors' training runs.

Anti-distillation poison pills are designed to make model outputs less useful for competitors attempting distillation.

An architecture where multiple specialized agents collaborate instead of one general-purpose agent. The newsletter includes debate over whether this is necessary versus using a single tool-loaded agent.

A multi-agent system uses several specialized agents to collaborate instead of relying on one general-purpose agent.

An agent design pattern where work is split into sub-tasks and assigned dynamically. In the newsletter, it is one of the core ingredients for building autonomous coding agents.

Task delegation breaks complex agent objectives into smaller sub-tasks assigned dynamically across tools or specialized components.

A protocol for connecting AI models to external tools and servers. The newsletter references discovery of MCP servers and reducing MCP token usage.

Model Context Protocol standardizes how AI models and agents connect to external tools, servers, and data sources.

A memory architecture that mimics human memory instead of relying on RAG or vector search. For PMs, it suggests alternative approaches to long-context recall and personalization.

Large Memory Models are described as a memory architecture that mimics human memory rather than relying on RAG or vector search.

A framework for specifying goals, context, and guardrails in multi-agent systems. It helps PMs guide autonomous agents with explicit objectives and stop rules rather than rigid control.

Intent Engineering helps PMs specify objectives, context, and guardrails for autonomous agents.

A search tool mentioned as part of ingesting PM work into Claude Code. It appears to support retrieval over a large personal knowledge base.

QMD appears to be a search and retrieval layer used to access large personal or operational knowledge bases.

A legacy programming language often targeted for modernization and migration efforts. For PMs, it represents enterprise technical debt and transformation risk.

COBOL remains core to many enterprise systems despite being viewed as legacy technology.

A PM framework focused on user value, tradeoffs, and outcomes rather than just technical implementation. Mentioned here as a skill engineers should develop in AI product teams.

Product-thinking emphasizes user value, tradeoffs, and outcomes over pure implementation.

A tool interface used with skill.md to reduce token usage and run MCP commands in a more efficient way.

CRI is a lightweight interface for running MCP commands with lower token overhead.