Charlie Key

🤝Adding human-in-the-loop to deep agents Many tools that you may want to give to agents will take actions in the real world. For these tools, you will often want to add "human-in-the-loop" steps - require a human user to approve, edit, or respond to their request to execute that tool. In this video, we will see how to add and use human-in-the-loop functionality to Deep Agents Video: https://lnkd.in/gfbjdABH Deep Agents Github: https://lnkd.in/gWpaj88j

560

20 Comments

AI copilots aren’t just for engineers anymore. 300,000+ plumbers, landscapers, and electricians are now using them to run their businesses. I sat down with Forrest Zeisler, CTO of Jobber, to unpack how the trades went from paper invoices and binders to AI copilots that actually get stuff done: - Booked 200,000+ after-hours calls (no more missed opportunities) - Helped pros to win more work with better proposals - Replaced paperwork headaches with workflows that just work - Proved that trust (not hype) drives real AI adoption The big takeaway: AI usage is exploding across the trades, and fast. Forrest’s story is live now - listen wherever you get your podcasts. — P.S. We’re digging into more AI trends in this month’s AI Leaders Lab: Candid, tactical conversations with execs scaling AI where every tool has to prove its worth. Request an invite here: https://lnkd.in/gJT-RZHR

116

9 Comments

Big news: Coplay is now the official steward of the open-source Unity MCP project! 🙌 This project (Unity MCP) started as Justin P Barnett's open-source labor of love to let AI agents control Unity. It grew way beyond what a solo dev can maintain. We’ve been working closely with Justin, and as of this week he’s joining our team so we can build the future of AI-assisted game dev together. By taking over Unity MCP, we’re ensuring this tool stays free and gets even better for all Unity developers. (Quick correction to what the press wrote 😅: our AI has actually grown to complete 3000+ Unity tasks per week for devs, not 750 – that older number already tripled!). Our mission at Coplay is to make game creation as frictionless as playing a game. Gaming is the largest entertainment industry in the world for a reason – people love interactive experiences – and we want to empower everyone to bring their game ideas to life with a little help from AI. This news is a significant step toward that goal, and I couldn’t be more grateful to the community that’s been with us so far. 🙏Special thanks to Justin for kickstarting this project and to Shutong Wu and David Sarno for helping to maintain the repo. What does this mean? • We’re keeping the MCP open‑source indefinitely and committing to regular maintenance. • Justin is now working with us on making Unity faster and easier to use. • Our closed beta is opening up — anyone can now try Coplay. • We’ve launched Orchestrator mode, so you can execute multiple tasks in sequence — think processing an entire game design doc without breaking a sweat. This collaboration gives developers more choice and better workflows. I’d love to hear from you: what multi‑step tasks have slowed you down in Unity, and how would you like to see them automated? Here’s to a vibrant, collaborative future for game developers. 🕹️🚀 #gamedev #Unity #opensource #ai

121

16 Comments

"Get out of the building" isn't just startup advice. It's essential for defense tech founders. Ian Tien learned this building Mattermost into a platform that serves government and defense organizations worldwide. His advice for defense tech startups cuts through the Silicon Valley mythology that government sales take years and aren't worth pursuing. Startup solutions can provide significant value in these environments. More insights from Ian Tien (CEO, Mattermost) on our latest Founders in Arms episode. Link in comments.

55

5 Comments

"User interfaces are gonna go away." : Eric Schmidt He said it out loud on the Moonshot podcast by Peter Diamandis, but it’s something we’ve believed for a long time at Thesys. Traditional interfaces are dumb and rigid. They were built for linear, pre-determined user journeys. They were not built for systems that think, learn, or respond dynamically. Over the past two years, we’ve been heads down building the first practical implementation of Generative UI. Today, our customers use it with the simplicity of integrating an API. Also, Generative UI isn’t just about better user experience and engagement. It also drastically improves execution efficiency of teams as they - ✦ Skip manually building the frontend, saving months ✦ Release faster and reduce time to market ✦ Maintain and scale the UI easily with every new feature or flow Interested in learning more about Generative UI? Dropping a few resources in comments.

50

3 Comments

We teamed up with The Product Folks on mosAIc 2025 - a virtual build a thon for AI builders. As part of the buildathon, there are several hands-on workshop that covers everything from evals, prompting, and agent design to security, infra, and shipping production-ready flows. This is what it actually takes to build a working agentic application. Alongside speakers such as Arvind, Ji Huang, Madhu, Akash, Rohit Khanna, Rahul, Vaibhavi, Eashan, I'll be doing a hands-on workshop as well, to answer questions like: → What truly goes into building an AI agent that can do real meaningful job - layers involved in building it → How do agents work securely on behalf of users and connect with external tools to get the job done. → How should builders think about auth where agents are the primary actors If you’re working on AI infra or products, this is probably the most useful 2 weeks you’ll spend this year. Last few spots left. Link in the comments.

70

5 Comments

Two long years ago, at Movable Ink's Think Summit 2023, I shared how software developers have gained sizable leverage writing code over the past few decades. While there are only 1.6 million developers in the US, there are 160 million workers who haven't witnessed the same advances. But that was about to change! Fast forward to today. We're seeing AI transform companies in three fundamental ways: ⏰ We're nearing the end of humans writing software. Engineers, product managers, and designers are prompting AI to generate code, translate customer interviews into PRDs, and rapidly prototype new designs. 🛠️ We're capturing multi-step, manual, business processes and turning them into agentic workflows. Sales outreach copywriting, data transformation and sharing, prospect research, slide creation, and much more will be things of the past. 💻  And finally, the software that we build will be AI-first. Traditional UIs and user flows can break out of the constraints of human interaction. Think digital agents completing tasks or predictive recommendations eliminating entire steps. An individual contributor role will look more like an agent manager and those who learn how to harness these new tools will 10x their productivity relative to peers who don’t. Every business worker is about to experience leverage first-hand in a way that only developers have and skillfully managing agents will eclipse the ability to manage people. It's both a scary and thrilling time to be alive! 

42

1 Comment

What started as "vibe coding"—fast, loose AI experimentation—has evolved into something much more sophisticated. Simon Willison's concept of "vibe engineering" captures the disciplined approach needed for production development with AI. But as teams scale these practices across entire organizations, we're seeing the emergence of Continuous AI: orchestrated workflows where AI operates continuously throughout the development lifecycle. The journey is familiar to many developers. You start small—letting AI handle minor tasks, building trust gradually. But once you trust an agent to run unsupervised for five minutes, everything changes. You spin up parallel agents, manage multiple workstreams, and suddenly your entire team is doing the same. That's when the need for secure execution, event-driven triggers, monitoring, and seamless transitions between agents and human oversight emerges. Continuous AI isn't about removing developers—it's about working at the right level of abstraction for each task. Sometimes that's hands-on vibe coding, sometimes it's careful vibe engineering, and increasingly it's orchestrating multiple remote agents while staying accountable for what ships. The future of development isn't choosing between human and AI—it's mastering the dance between them. #ContinuousAI #VibeEngineering #AIDevelopment #SoftwareEngineering

56

4 Comments

🚀 New quickstart: build a durable agentic workflow for contract review—with human-in-the-loop—in minutes. What you get: 🧩 Works with OpenAI, Gemini, and Anthropic (swap any LLM client) 🔁 Durable by design: if it stops, it resumes exactly where it left off 👩‍⚖️ Human approval step before changes are applied 🧰 Template code: change the prompts to go from contract review to any review task (RFPs, vendor risk, policy, code, etc.) If you’re exploring agentic patterns + durability, this is a great starting point. Link in the comments 👇

32

1 Comment

It was amazing to have Ken Exner among the panelists at the Seattle AI Fireside Chat this week to give us his perspective and what he's seeing happening in the market. If you weren't able to catch it live, I highly recommend you listen to his full insights. This quote captures one of the most profound shifts underway in software development. For decades, our mental model was: a user interacts with a UI → the UI calls a service → the service does something deterministic. That’s now dramatically changing. Today, agents (agentic AI) are becoming first-class actors in our systems. They reason, act autonomously, adapt, and chain tasks. And they’re not “users” in the traditional sense. They consume APIs differently. They require structured feedback loops. They might even ask questions back. We will need to design systems for AI, not humans, and this change will start nowhere other than the engineers, the builders. We've already made that shift at Edge Delta and the great thing is, AI is also opening up a tremendous amount of opportunity for anyone to be that engineer... that builder.

58

"I don't want to build a better workflow. I want to build something SO exceptionally better than the current options." These words from my recent conversation with Avinash struck a chord. They embody our mission in revolutionizing home services through AI: The difference between incremental improvement and revolutionary change isn't just about scale; it's about mindset. Think about it: • Henry Ford didn't build a faster horse • Netflix didn't create a more efficient Blockbuster • And we're not building just another voice system We're reimagining the entire paradigm of customer service in home services. Too often, companies get caught in the trap of optimization - making existing systems 10% better. But true transformation happens when you step back and ask: "What if we could eliminate the fundamental problems of after-hours support, staff burnout, and missed opportunities?" That's the difference between building a better call center and creating a world where exceptional service is available 24/7, without compromising your team's wellbeing. The result? An AI-native solution that's not just marginally better—it's exceptionally better by design. This is Avinash coding away at 35,000 ft on the way to a customer implementation!!

43

5 Comments