OpenAI’s Joseph Kim talks about the threshold phenomenon at AIE NY today. One of the key themes at the AI Engineer New York conference this week was how to balance agent autonomy with security and safety. Both frontier labs and financial firms focused on this issue in their presentations this week. The main lesson: safe autonomy depends on where you put controls and human judgment, rather than how many restrictions you impose.
Richard MacManus
Verified
Head of editorial at www.latent.space / @latentspacepod
Founded ReadWriteWeb (2003–2012)
Internet historian at cybercultural.com
🥝 in 🇬🇧
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Richard MacManus
How Anthropic’s Dynamic Workflows Coordinate Claude Agents
CJ Avilla and Harrison Stall, Members of Technical Staff at Anthropic, at AI Engineer NYC today. The AI Engineer New York 2026 conference kicked off this morning with a series of workshops, including Anthropic discussing how to orchestrate its Claude Managed Agents. Of particular interest was a brand new feature, announced on Friday, called dynamic workflows — or simply “flows,” as the presenters repeatedly called it.
Building AI for Reliable Execution: Lessons From Industrial Robotics
When you think of robotics and AI, you probably first think of full humanoid robots like Figure’s AI-powered machines and 1X’s NEO home robots. Those may well be the future, but arguably more important in 2026 is industrial robots — which are typically not humanoids.
Can a Cloud-Native Harness Make Agents Reliable Beyond the Desktop?
At a high level, coding agents have a basic architecture: an LLM calls tools in a loop, while carrying forward the required context. Since that’s easiest to implement locally, many coding agents started out as terminal tools and then desktop apps (Claude Code famously began as a CLI tool). But as the open laptop meme illustrates, modern agent harnesses have frustrating limitations if they’re not able to be managed in the cloud.
Inside-Out AI: Rebuilding Airbnb Behind the Scenes and Across the Guest Experience
Prior to joining Airbnb as CTO in January, Ahmad Al-Dahle was head of generative AI at Meta and led the launch of its open source Llama models over 2023-2025. Now Al-Dahle is in charge of turning Airbnb into an “AI-native company”. What that means in practice is using AI internally to speed up product development, then using those same capabilities to transform the customer experience. We’re calling this an “inside-out AI” approach and in this article we’ll dig into the details.
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Earlier this month, world model company Runway introduced GWM Worlds 2, a research preview that “turns high-fidelity video and audio generation into real-time interactive simulation.” Runway calls this an “autoregressive diffusion” model; with autoregressive describing how it generates over time. One new feature in particular caught our eye: WorldPrompt, a proposed input format for specifying a generated world and the actions within it.
Can Skills Learned in Games Transfer to Real-World Work?
“Games have always been these underrated educational tools. They’re super approachable. They’re very human.” Those are the words of Alex Duffy, co-founder and CEO of Good Start Labs, who spoke to Latent Space about why his company is turning games into training material for AI models. The company was spun out of AI media and tools company Every last October, with $3.6 million in funding from General Catalyst, Inovia, Every, and angel investors.
PRs NOT Welcome: How Top AI Open Source Projects Are Managing Thousands of Contributors
GitHub invented pull requests, and for 18 years they have been open by default. But now some of the top AI-native open source projects are shutting PRs off, because they’ve found a better way. These projects, which include Flue and tldraw, refuse to accept PRs from external contributors — in part because they’re usually AI-generated.
The Future of SaaS Is Apps That Agents Can Use
Lovable is well known as an AI-powered platform to build applications. But ironically, it is now moving towards a future where fewer and fewer people will be using conventional apps. That is, of course, because of the growing impact of agents.
The /wayfinder Skill: Navigating the “Fog of War” of Planning
We’re currently developing a new series about skills, with the aim of giving you a regular supply of new skills to use in your projects. We’re kicking things off with an interview — and a super-useful skill — featuring Matt Pocock, whose “AI Skills for Real Engineers” project has over 220,000 stars on GitHub. He also talks about these skills to 347,000 subscribers on his YouTube channel. Pocock recently released a new skill called /wayfinder.
Frontier Model Cost and Open-Weights Popularity is Driving Demand for Model Routing
With the intense competition among frontier model companies, together with ever-increasing power of open-weight models like Kimi K3 and Qwen3.8-Max, model routing has become a key part of AI deployment. We’ve just seen Stripe buy OpenRouter for over $7B, but the trend is equally hot in enterprises. Glean, co-founded and led by ex-Google Distinguished Engineer Arvind Jain, specializes in bringing AI to large organizations. It was last valued at $7.2B after a $150M Series F fund raise last June.
OpenAI Releases GPT-5 and Why Barndoor is APIs 2.0
This week I interviewed Oren Michels, who ran API company Mashery in Web 2.0 (a long-time ReadWriteWeb sponsor!). He's back now with a modern twist on API management: Barndoor, a control plane for agentic AI. "If you take APIs and you take the ‘P’ out, it’s a whole lot more interesting." - Oren Michels But of course the big AI news this week was OpenAI releasing GPT-5 on Thursday (Techmeme).
React for Agents: Astro Creator Brings Hooks to his Meta-Harness, Flue
Agent frameworks for developers are still at an early stage, with the likes of Vercel’s eve and Fred Schott’s Flue — both launched this year — setting the early template. Schott is the creator of the web framework Astro, which led to his company being acquired by Cloudflare in January. He’s just released version 2 of Flue, its first stable release, which has as its foundation React-style “Agent Hooks.” In Flue, an agent is represented by a JavaScript function.
Ontologies Are So Back: Why AI Agents Are Reviving the Semantic Web
One of the most watched videos from the recent AI Engineer World’s Fair is a 20-minute talk by Frank Coyle, a professor of computer science who currently teaches generative AI and LLMs at UC Berkeley. Drawing on his decades of experience, Coyle re-introduced the concept and practice of ontologies to today’s AI engineers.
Browsers in agents, WebMCP momentum, and AI engineering lessons
This week I published 5 Trends That Defined AI Engineering at World’s Fair 2026 on Latent Space. As previously noted, I attended the AI Engineer World's Fair in San Francisco earlier this month — where I learned that the state of the art in AI engineering looks a lot like the state of the art in software engineering.
5 Trends That Defined AI Engineering at World’s Fair 2026
swyx’s note: thanks to Richard for covering AIE while I was working on the conference itself! Make sure you have opted into the AINews feed to get our weekday updates. AIE next returns to NYC, Oct 12-14, with a heavy focus on AI in Finance this year. AI engineering has come a long way in three years. When swyxcoined the term “AI engineer” in June 2023, he was giving a name to a new kind of developer emerging from the big bang of large language models.
5 Trends That Defined AI Engineering at World’s Fair 2026
swyx’s note: thanks to Richard for covering AIE while I was working on the conference itself! Make sure you have opted into the AINews feed to get our weekday updates. AIE next returns to NYC, Oct 12-14, with a heavy focus on AI in Finance this year. AI engineering has come a long way in three years. When swyx coined the term “AI engineer” in June 2023, he was giving a name to a new kind of developer emerging from the big bang of large language models.
My week at the AI Engineer World's Fair
Last week I was in San Francisco covering the AI Engineer World's Fair for Latent Space, the blog of AIEWF co-founder swyx. It was a thrill being on the ground in SF again, and for me it evoked memories of the glory days of Web 2.0. The excitement around AI technology, the speed at which it is evolving, the number of startups being built, and (yes) the hunt for revenue and riches — it's all very reminiscent of two decades ago.
AIEWF Daily Dispatch: The great loops debate and the state of AI engineering
One of the highlights of the final day of the AI Engineer World’s Fair was a debate about loops. It nicely captured an argument running through the whole conference: are autonomous software factories viable now, or is the engineering discipline lagging behind the ambition?
Vercel's Andrew Qu on why agents are a new kind of software
Vercel’s Andrew Qu on the AIEWF expo floor. Andrew Qu is Chief of Software at Vercel, where he works with the CTO across internal engineering, product experimentation and emerging technologies. He has built libraries for MCP, created skills.sh and led the development of eve, Vercel’s framework for building agents.
The website of the future may assemble itself for every visitor
Adobe Principal Scientist Carlos Sanchez at AIEWF. For as long as I can remember (and I managed websites in the dot-com period), “personalization” has been a holy grail for websites. But up till now, that’s typically meant selecting from a predefined set of options. A retailer might recommend an item based on a previous purchase, or place a visitor into one of several audience segments — that’s been the extent of personalization.
Forward Deployed Engineers and the future of software engineering
Cover Image: Sierra’s Natalie Meurer at the AI Engineer World’s Fair today. Natalie Meurer is Head of Agent Engineering at Sierra, where she leads a global team of more than 120 engineers building conversational AI agents for enterprise customer service. Before joining Sierra, she worked in technology policy, taught herself to code and spent five years at Palantir. Forward deployed engineering (FDE) was one of the tracks running at today’s AI Engineer World’s Fair.
AIEWF Daily Dispatch: Loops, Software Factories & Forward Deployed Engineers
Agents are here to serve you in the software factory. Loops, loops and more loops. That word, loop, dominated conversations on day 2 of the AI Engineer World’s Fair — the first full day of keynotes and sessions. Perhaps knowing in advance what everyone would be talking about, AIEWF cofounder swyx titled his opening talk, “Loopcraft: The Art of Stacking Loops.” @swyx began by commenting on the evolution of AI engineering from 2022: from chat, to tools, to goals.
Ahmad Osman on why local AI is catching up
Ahmad Osman has been advocating for local AI — running models on your own computer, workstation or dedicated hardware — long before it became a major theme at this year’s AI Engineer World’s Fair. He is also the founder of Osmantic, a company building open source software for deploying and operating local AI systems. One of the themes emerging from AIEWF is that open source LLMs are becoming increasingly credible alternatives to large, proprietary frontier models.
Skill engineering and the case against one-shot AI design
Impeccable’s Paul Bakaus at the AI Engineer World’s Fair. Paul Bakaus thinks the emerging discipline of “skill engineering” can make AI agents more capable — but he absolutely does not want to remove people from the creative process. He chats to Latent Space about his approach to design in the AI age. Bakaus is the creator of Impeccable, an open-source design skills system that gives coding agents a vocabulary for improving interfaces.
Warp CEO Zach Lloyd on why software factories are the next phase of coding
I’ve been covering Warp for a couple of years now, and its rapid evolution from a command-line interface tool to a software factory platform has been fascinating to watch. The company began in the pre-ChatGPT days, in mid-2021, as a Rust-based terminal. Then when AI hit, it turned into a terminal with integrated coding agents.
AIEWF Daily Dispatch: Autoresearch and the tension between AI and human agency
“You can’t one-shot design.” Paul Bakaus at AIEWF today. Wednesday was autoresearch day on the AI Engineer World’s Fair main stage. Autoresearch is — you guessed it — a kind of loop. Introspection co-founder Roland Gavrilescu explained it best in an interview with Latent Space this morning. He said autoresearch “allows you to build loops in which agents help maintain the system itself.” He called it an “outer loop” that “studies and maintains” the primary, inner loop.
Autoresearch: The feedback loop behind self-improving agents
Introspection’s Roland Gavrilescu at AIEWF. We’ve heard a lot about loops at the AI Engineer World’s Fair this week. Another buzzword is autoresearch, which involves building an “outer loop” where agents help maintain and improve the primary system, using feedback signals, evals and human input to make progress over time. At least, that was the framing of Roland Gavrilescu, co-founder and CEO of Introspection — a new company building infrastructure for deploying these self-improving systems.
How Cursor deploys AI inside the enterprise
Pauline Brunet, VP of Forward Deployed Engineering at Cursor, at AIEWF. Forward deployed engineering has quickly become one of the most prominent roles in enterprise AI. Sitting somewhere between software engineering, product development and customer implementation, forward deployed engineers [FDEs] work directly with organizations to implement AI capabilities. At Cursor, the role is especially ambitious.
Warp CEO Zach Lloyd on why software factories are the next phase of coding
Warp founder Zach Lloyd in the AI Engineer World’s Fair expo hall. I’ve been covering Warp for a couple of years now, and its rapid evolution from a command-line interface tool to a software factory platform has been fascinating to watch. The company began in the pre-ChatGPT days, in mid-2021, as a Rust-based terminal. Then when AI hit, it turned into a terminal with integrated coding agents.
AIEWF Daily Dispatch: Loops, Software Factories & Forward Deployed Engineers
Agents are here to serve you in the software factory. Loops, loops and more loops. That word, loop, dominated conversations on day 2 of the AI Engineer World’s Fair — the first full day of keynotes and sessions. Perhaps knowing in advance what everyone would be talking about, AIEWF cofounder swyx titled his opening talk, “Loopcraft: The Art of Stacking Loops.” swyx began by commenting on the evolution of AI engineering from 2022: from chat, to tools, to goals.
Forward Deployed Engineers and the future of software engineering
Sierra’s Natalie Meurer at the AI Engineer World’s Fair today. Natalie Meurer is Head of Agent Engineering at Sierra, where she leads a global team of more than 120 engineers building conversational AI agents for enterprise customer service. Before joining Sierra, she worked in technology policy, taught herself to code and spent five years at Palantir. Forward deployed engineering (FDE) was one of the tracks running at today’s AI Engineer World’s Fair.
Ahmad Osman on why local AI is catching up
Ahmad Osman at the AI Engineer World’s Fair today. Ahmad Osman has been advocating for local AI — running models on your own computer, workstation or dedicated hardware — long before it became a major theme at this year’s AI Engineer World’s Fair. He is also the founder of Osmantic, a company building open source software for deploying and operating local AI systems.
Agentic web market signals: the agent stack becomes enterprise infrastructure
This week’s market signals provide further evidence of the agentic web stack evolving into enterprise infrastructure. From Vercel to AWS to Okta to Google, the industry's focus is shifting toward the infrastructure needed to build, connect, govern and discover agents inside real enterprise workflows.
Never forget: the web is made of people!
I had a discussion with someone in the industry this week in which the question came up: what makes something web-based in this AI era? Is it just the presence of web technologies?
Nekuda's WebMCP bet: Agentic commerce still needs the website
Interviews 5 min Nekuda is an agentic commerce startup with a refreshing difference: it is betting on websites continuing to flourish, rather than AI chatbots completely taking over the shopping experience. I spoke with founding CEO Ayal Karmi about why the emerging WebMCP open standard underpins its web-based strategy. Before we begin, it's useful to frame the current thinking about the role of a user interface in the agentic web.
The agentic web gets execution rights, from payments to app actions
Market Signals 5 min Apple's agentic vision at WWDC26 — AI based on a user's personal devices, software and apps. One of the characteristics of the agentic web is an increasing ability for AI agents to execute actions on the web on our behalf. This is a key part of the shift from a web of pages to a web of capabilities — but it also introduces significant security, governance and financial risks.
When the user interface moves from pages into agents
This week, my Agentic Web News posts circled around one question: what happens when the web stops being organized only around pages, and starts being organized around machine-readable capabilities, agent interfaces and brand systems? I’ve been writing for a while now about the shift from a web of pages to a web of capabilities. But to me, that has never meant that the human web is going away. Clearly I don’t think that, otherwise I wouldn’t have started a new tech blog.
MCP Apps and the future of software inside AI agents
Interviews 7 min MCP Apps co-creators, Liad Yosef and Ido Salomon; via AI Engineer Europe. Around July last year, I discovered an open source project called MCP-UI — which provided a way to add web-based user interface components to AI agents. The project was brand new, having only been released in May 2025. In early August, I interviewed its two creators, Ido Salomon and Liad Yosef; and then I talked to some developers from Shopify, among the first companies to implement MCP-UI.
Agentic web market signals: the machine-readable web becomes a business problem
This year I've been writing about how we're moving from a web of pages to a web of capabilities. To me, that's never meant that the human web we all know and love is going away. Clearly I don't think that, otherwise I wouldn't have started a new tech blog. Rather, the point I've been trying to make is that there's an extra layer of the web emerging — one that is built for our machine helpers.
Who owns that AI agent? DNSid proposes an answer
Since we're moving to a web where both people and agents are active participants, there's a question of identity that we need to answer. And I don't mean whether agents should be treated as first-class citizens of the web (although that is an interesting philosophical question). No, there are a couple of more practical issues we should address about any agent that interacts with your site or app: Who owns this agent? Who is accountable for what it does?
Arcade's bet: the agentic web needs an actions runtime, not just MCP servers
Arcade promotes itself as an "MCP runtime" — basically, middleware that governs how agents execute actions across tools and services. Although the company actually prefers the term "actions runtime," it believes that MCP is becoming the default way for agents to use SaaS apps and, increasingly, website capabilities. To find out why agents need middleware, I spoke with Arcade CEO Alex Salazar. Salazar firstly pointed out that the agentic web is not just about data retrieval.
Agentic web market signals: advertising, commerce & identity layers emerging
In this week's market signals briefing, I focus on how the economic aspects of the agentic web are shaking out. This was always a key part of my analysis of Web 2.0 during my ReadWriteWeb days: how can these new web technologies be harnessed for commercial purposes?
Let’s be careful out there: 2 lessons for businesses adopting agentic AI
Where is the business value in agentic technologies? A lot of people are rightly asking this question, as we continue our journey into the agentic web. This was a big reason why I chose to profile a mainstream web company’s adoption of AI in my first interview post on Agentic Web News, my new tech blog covering this era. RunSignup is a web platform for race organizers and it is deploying AI chatbots and building agentic infrastructure across its product.
How RunSignup is building AI agents into every part of its platform
We're still so early in the agentic web era, so I was surprised when I came across a mainstream web platform already putting AI agents into production. RunSignup is a web technology company that specializes in events management for runners. It describes itself as "the largest registration platform for endurance events," with about 35,000 events using it.
Google's agentic web stack takes shape — but publisher economics remain unresolved
The past week in the emerging agentic web was dominated by Google's annual developer conference, I/O, which was all about this trend. As one Google executive said during the keynotes, "we've entered a new agentic era across Google." Unfortunately, Google didn't address economic incentives for publishers at I/O. But we did get an interesting development in that domain from another company, which I'll discuss in this post. So let's get to it. Here are the key market signals I've identified...
Welcome, Humans and Bots, to the Agentic Web
This week I have been looking closely at how the World Wide Web Consortium (W3C) has been moving to integrate AI into the web platform.
The Fate of the Web in the AI Era
I've been pondering what the fate of the Web will be as we continue to progress into the AI era. I've been wondering if the web is going to survive the AI onslaught — to put it more plainly. On the technology side, I think the web will continue to be the default open platform for internet technology.
WebMCP: A New Standard From Microsoft and Google
WebMCP is a new standard from Microsoft and Google that lets devs control how AI agents interact with websites using client-side JavaScript. I interviewed Kyle Pflug, group product manager for the web platform at Microsoft Edge, for this article on The New Stack.
The New Rock Stars of Web Development
I got to talk to one of the rock stars of frontend development this week. No, not DHH! I mean a young man named Evan You, whose Vite build tool is the backbone of many of the leading frontend frameworks of today: React, You's own Vue.js, SvelteKit, Astro, and others. As I discovered during our interview, this all happened within the space of five years. The version of Vite now used by other frameworks was first released in February 2021.
Show More
loading
Actions
Get in touch with Richard
Contact Richard, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack