Agents are the part of AI where the hype runs furthest ahead of what works. Newsletters in this group follow the frameworks, protocols and products that let models plan, use tools and act on your behalf, and the best of them test these systems rather than quoting demos.
Most are written by engineers and founders building agents themselves, so they are practical and opinionated. Pair one with a broader AI newsletter for the wider context.
26 newsletters below, ranked by editorial quality and how recently they published.
Latent.Space is a technical newsletter and podcast covering how leading AI labs build agents, models, inference infrastructure, and AI for science. Recent issues cover open-source inference economics, how AI-native engineering firms structure compensation, and programmable GPU data centers.
DiamantAI is a technical newsletter explaining AI internals through hands-on experiments, such as layer-pruning Mistral 7B and analysing how words steer image models. It also covers new tools and tutorials for building AI agents and RAG systems.
Deep (Learning) Focus is a long-form newsletter by Cameron R. Wolfe that explains important AI research topics in depth, with recent issues covering agent evaluation, NVIDIA Nemotron post-training, and reinforcement learning for LLMs. Readers get structured, reference-style overviews that synthesize research and practical implementation details.
A hands-on newsletter from Pawel for product managers covering practical AI tools, prototyping, and step-by-step playbooks. Readers get actionable tips on Claude Desktop, Grok Bot agent swarms, and new decision models, plus PM frameworks and learning resources.
A daily AI strategy newsletter aimed at practitioners and leaders who want practical guidance on running and building with AI agents, including hardware planning, agent security, and tools for investigating existing software. It mixes executive briefings, step-by-step prompt kits, and walkthroughs of open-source developer tools.
Ben's Bites is a newsletter from Ben Tossell about learning to build with AI agents, covering personal agent setups, prompt and workflow tips, and new agent tools. Each issue pairs a personal write-up or opinion piece with a curated feed of agent-related headlines and tools worth trying.
A practical guide to building an LLM wiki, a Markdown-based memory layer for agents, in three phases from ingesting local files to continual learning. Also covers engineering topics such as context quality checks before LLM calls and multi-agent coding workflows.
A weekly AI and machine learning newsletter that pairs a thematic editorial with deeper explainers on new models, agents, world models and AI safety. Readers get framed analysis of the week's research and industry news, such as open-weight decision models, embedding models, self-improving agents and open-source strategy.
A weekly show and newsletter recapping the past week's AI news, covering model releases, open source, and lab announcements, with a rotating panel of experts and guest interviews. Each issue includes commentary, panel discussion, and a links roundup.
Long-form essays on AI agent developments, such as agent memory research, liability for agentic commerce, and AI sandbox escapes. Readers get narrative-driven analysis that connects current AI events to neuroscience, internet history and infrastructure questions.
Essays and analysis on AI engineering from a developer-experience practitioner at OpenAI, covering agents, harnesses and voice models. It also offers commentary on the fast-moving frontier of AI models and industry events.
A founder's first-person newsletter about building Lazyweb, an MCP-first product, covering hands-on experience with AI agents, growth experiments and MCP practices. Readers get candid results, specific numbers and occasional guest explainers.
This newsletter covers system design for backend engineers, with a recent focus on building reliable AI agent systems. Issues use concrete failure scenarios to explain concepts such as agent state, memory, and observability.
A weekly newsletter that turns new AI tools and trends into practical workflows for busy professionals. Issues include frameworks for AI adoption levels, tested prompts for Meta's Muse agent, and a design lead's account of building shared AI skills for a team.
Long-form articles on AI engineering, covering topics such as monitoring LLM systems, evaluating agentic systems and context engineering. Posts explain concepts mechanically, include diagrams, and are occasionally paired with workshops run by the author.
A practical newsletter teaching business owners, consultants, and solopreneurs how to build and use AI agents, prompts, and agent harnesses for real work. Issues offer step-by-step workflows, copyable prompts for Claude and ChatGPT, and guidance on evaluating and automating business processes.
A newsletter with short, practical lessons on data science, machine learning and LLM engineering, including agents, inference engines and RAG. Issues mix visual explainers, benchmarks and tool walkthroughs, some of them sponsored or promotional.
A practical AI newsletter for builders and busy people, delivering a daily brief on new AI tools, money-related AI developments, and how AI affects work and business. Recent issues cover building autonomous AI agents, reverse engineering software with AI, and organizing multi-model agent teams.
A practical newsletter for full-stack JavaScript developers aiming to think like architects, covering React, Node, software architecture and production AI systems such as LLM agents and evals. Readers get concrete, code-level guidance like testing LLM judges and debugging agent behaviour, plus occasional promotion of a Node.js book and sponsors.
This newsletter offers practical explanations of building and deploying AI systems, including workflow graphs, voice agent failure modes, and security and vendor review gates for agents. It also frames these topics for career and professional readers who want depth over hot takes.
A daily-style AI newsletter that filters model launches, agent tools and industry news down to what matters for practical work, with short items on each development. It pairs headline coverage with sponsored business AI offers and occasional light historical framing.
A practitioner's newsletter showing how to build working tools with Claude Code, such as job-hunting agents, motion video skills and curated NotebookLM notebooks. Each issue walks through a concrete build, often with downloadable skills or links and Upwork market evidence.
A weekly AI newsletter combining curated summaries of top research papers with news on models, tools, and agent development. Each issue walks through selected papers and industry releases with short explanations of results and why they matter.
A practitioner's guide to using iPhone Shortcuts, Apple Intelligence and AI tools to automate daily tasks, plus pieces on AI 'offices' and OpenAI's persistent ChatGPT agents. Readers get concrete setup walkthroughs and an overview of new AI workflow products.
One short email a week with hand-picked newsletters from the index. Free, no spam, unsubscribe anytime.
