Build SLM-Powered Agents with Arcee AI & AWS
- Date
- 2025-05-06
- Location
- To get to the AWS GenAI Loft (right above Chipotle), take the flight of stairs behind the fountain., San Francisco, CA, USA
- Host
- Personal
About this event
If you’re actively building with AI and want to move beyond demos into practical agent systems, this meetup is designed for you. Build SLM-Powered Agents with Arcee AI & AWS brings together people who care about real-world autonomy, model efficiency, and hands-on implementation in a room built for conversation as much as learning. This is an in-person San Francisco gathering for builders, technical teams, and curious practitioners who want a clearer view of what small language model-powered agents can actually do today. Expect useful ideas, grounded discussion, and the chance to meet others working on similar problems. About the Event This event centers on a timely question: how do you build capable AI agents without assuming that bigger models are always the best answer? By focusing on SLM-powered agents, the evening points attention toward systems that can be faster, more efficient, and better suited to specific workflows when designed well. With Arcee AI and AWS at the center of the conversation, the meetup is positioned for people who want to understand both the model side and the infrastructure side of agent development. That makes this especially relevant if you’re thinking about deployment, orchestration, performance, or how to turn promising prototypes into systems that can hold up in practice. The format is a meetup, which means this won’t feel like a distant conference talk track. It’s meant to be a more direct, community-oriented setting where you can learn, ask questions, compare notes, and meet people who are also building in AI, autonomy, and adjacent technical areas. Whether you come with an active project, a rough idea, or simply a desire to get sharper on where agent architectures are heading, the event is built to give you substance rather than abstraction. What to Expect You should expect a mix of technical insight, practical framing, and community interaction. The focus is not just on AI in the abstract, but on what it takes to build agents powered by smaller language models and supported by a strong cloud environment. The evening will likely be most valuable if you arrive ready to think in systems: model choice, task design, inference tradeoffs, orchestration, and the gap between a chatbot-like interface and a more autonomous workflow. Even if you’re early in your exploration, you’ll leave with a better sense of the moving parts. A meetup like this typically works well because it gives you several modes of value in one place: Context on why SLMs matter in current agent design Discussion around practical implementation choices Exposure to how others are approaching autonomy and agent workflows Networking with engineers, founders, and AI practitioners in San Francisco Space for questions that are hard to answer through blog posts alone Because this is in person, expect the hallway conversations to matter. Some of the most useful takeaways often come from comparing architectures, tooling choices, and product constraints with people who are a few steps ahead, a few steps behind, or solving the same problem differently. Why Attend There’s a lot of noise around agents right now. This event is valuable because it narrows the conversation to a more actionable layer: what can you build with SLM-powered agents, and how do you make those systems useful? That focus helps cut through vague claims and brings attention back to architecture, tradeoffs, and execution. If you’ve been weighing latency, cost, control, or reliability in your AI stack, this meetup should give you stronger intuition for where smaller models fit. Not every agent needs the largest possible model, and understanding when a smaller model is the right tool can unlock more practical and scalable designs. You should also attend for the people in the room. San Francisco has no shortage of AI events, but the best meetups create a real exchange between builders rather than a one-way presentation. This one is well positioned for exactly that: a focused topic, a relevant venue, and a community likely to include people working directly on AI products and infrastructure. A few concrete reasons this may be worth your evening: You want to sharpen your understanding of agent design with real constraints You’re curious about small language models as a serious building block, not just an alternative You want to meet others working across AI, autonomy, product, and infrastructure You learn best by combining live discussion with peer conversation You’re looking for practical insight you can bring back to your own team or project Practical Details This is an in-person event in San Francisco, USA on Monday, May 5 at 5:30 PM PDT. If you’re local, it’s a straightforward after-work time slot; if you’re traveling in from elsewhere in the Bay Area, plan your route so you can arrive with a few minutes to settle in and connect before things get going. The venue is the AWS GenAI Loft. To get there, use this location note: to get to the AWS GenAI Loft (right above Chipotle), take the flight of stairs behind the fountain. That detail is worth reading twice so you don’t lose time searching once you arrive. A few useful planning notes: Format: in-person meetup Topic: building SLM-powered agents with Arcee AI & AWS Location type: hosted at the AWS GenAI Loft in San Francisco Best for: people who want both technical learning and community interaction Arrival tip: give yourself a little buffer to find the entrance and get oriented If you’re deciding whether to go, the simplest test is this: are you actively interested in how modern AI agents get built, especially with an eye toward efficiency and deployment? If yes, this is the kind of focused, high-signal meetup that can make your next few weeks of building a lot clearer.
Who should attend
This is for people who want sharper, more practical conversations about agent building than you usually get from generic AI events. - You’re an **engineer, ML practitioner, or technical builder** exploring how to design and deploy AI agents with real constraints around latency, cost, and reliability. - You’re **curious about small language models** and want to understand when SLMs are the better choice for agent workflows instead of defaulting to the largest available model. - You’re building a **product, internal tool, prototype, or automation system** and want ideas you can apply to architecture, orchestration, or infrastructure decisions. - You work in or around **AI, autonomy, cloud, or developer tooling** and want to hear how others are thinking about practical implementation. - You’re a **founder, product leader, or technical operator** who needs a better grasp of what’s feasible today with agent systems and where the tradeoffs actually show up. - You value **meeting other serious builders in person** and want conversations that go beyond surface-level networking into real exchange about tools, approaches, and lessons learned. If you want a room full of people who are actively trying to make AI systems useful, efficient, and deployable, you’ll likely feel at home here.