BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//OpenTeams | AI you own - ECPv6.16.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:OpenTeams | AI you own
X-ORIGINAL-URL:https://openteams.com
X-WR-CALDESC:Events for OpenTeams | AI you own
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20250101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20260219T120000
DTEND;TZID=UTC:20260219T130000
DTSTAMP:20260613T125422
CREATED:20260209T102603Z
LAST-MODIFIED:20260223T102840Z
UID:10000017-1771502400-1771506000@openteams.com
SUMMARY:Reducing LLM Costs Through Programmatic Tooling
DESCRIPTION:The Model Context Protocol (MCP) provides a standardized way for large language models (LLMs) to discover and invoke external tools through a client–server architecture. In its most common usage\, MCP tools are called directly by the model during inference\, one action at a time\, via structured tool calls. While effective\, this approach can become limiting when workflows grow more complex.\nIn this session\, we’ll introduce MCP Code Mode\, a paradigm shift in how LLMs interact with tools. Rather than emitting a series of discrete tool calls\, the model generates executable code that invokes\, sequences\, and coordinates MCP tools directly. The result: clearer intent\, tighter control flow\, and more powerful orchestration.\nWe’ll start with a quick tour of MCP’s architecture and the standard tool-calling patterns most of us are familiar with\, then dig into where those patterns begin to creak under real-world complexity. From there\, we’ll explore how Code Mode unlocks a more expressive and efficient way for LLMs to reason about actions by using code as the glue.\nTo make it concrete\, we’ll walk through live demos that compare direct tool calling with code-based orchestration\, highlighting where Code Mode shines in practice and why it can be a game-changer for building robust\, scalable AI systems. \n\nRegister for Free (ZOOM LINK) \nAbout the Speaker \nEric Charles is an active contributor and committer to several open source projects\, including Jupyter and Apache. He is the founder and CEO of Datalayer (https://datalayer.ai)\, a platform for AI-driven data analysis. Prior to founding Datalayer\, Eric collaborated with leading SaaS companies to design and implement innovative open source solutions. \nAbout the Open Source Architect Community \nThe Open Source Architect (OSA) Community is an invitation-only group for seasoned software architects who are passionate about open source technology. Request to join the OSA Community: https://forms.gle/7efbynVzYhhH2LCQ7\nWe review each application carefully. If it’s a fit\, you’ll get an invite to join the space where it all happens.\nFor the latest updates on all things open source\, follow our public feed on LinkedIn.
URL:https://openteams.com/event/reducing-llm-costs-through-programmatic-tooling/
ATTACH;FMTTYPE=image/png:https://openteams.com/wp-content/uploads/2026/01/OSAC-Feb-2026-Webinar.png
LOCATION:https://openteams.com/event/reducing-llm-costs-through-programmatic-tooling/
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20260416T120000
DTEND;TZID=UTC:20260416T130000
DTSTAMP:20260613T125422
CREATED:20260406T115800Z
LAST-MODIFIED:20260406T115800Z
UID:10000018-1776340800-1776344400@openteams.com
SUMMARY:Can AI Agents Extend the Half-Life of Open Source Software? A Conduit Case Study
DESCRIPTION:Open source projects rarely become under-maintained because the architecture stopped mattering. More often\, they drift because maintainers run out of time\, funding\, or energy. \nIn this session\, William Hill invites us to explore whether AI agents can meaningfully help sustain and evolve a lightly maintained open source system by using Conduit\, a Go-based data streaming platform\, as the case study. Rather than treating AI as an autonomous replacement for maintainers\, he will present a human-governed maintenance workflow that combines context retrieval\, task selection\, change generation\, automated verification\, and architectural review before any change is approved. \nThe session will cover the design of a multi-agent workflow built around key maintenance concerns: understanding repository architecture\, selecting appropriate tasks\, proposing narrow changes\, validating correctness\, and reviewing alignment with system boundaries. We will discuss the tradeoffs involved in structuring agent roles\, the kinds of guardrails that matter\, and where human judgment remains essential. \nWilliam will also share a scorecard from the experiment: what kinds of tasks agents can realistically handle today\, what failure modes appear in real repositories\, and what characteristics make an open source codebase more or less suitable for agent-assisted maintenance. \nAttendees will leave with a practical framework for evaluating their own repositories\, a reference approach for human-in-the-loop AI maintenance\, and a grounded perspective on where AI can help open source teams without replacing maintainership. \n\nRegister for Free (ZOOM LINK) \nAbout the Speaker \nWilliam Hill is a Senior Software Engineer at Zocdoc. He previously worked as a Staff Software Engineer at Meroxa\, where he built data streaming solutions and open source tooling in Go. His work spans software architecture\, data engineering\, AI agents\, and developer platforms\, with a focus on turning complex systems into practical workflows teams can use. William has spoken on AI agent workflows\, data systems\, and modern software architecture\, and he is especially interested in how open source projects can remain useful and sustainable as maintainer bandwidth shifts over time. He approaches AI workflows as an engineer first\, prioritizing reliability and governance over novelty\, and combines hands-on experimentation with a grounded view of engineering tradeoffs. \nAbout the Open Source Architect Community \nThe Open Source Architect (OSA) Community is an invitation-only group for seasoned software architects who are passionate about open source technology. Request to join the OSA Community: https://forms.gle/7efbynVzYhhH2LCQ7\nWe review each application carefully. If it’s a fit\, you’ll get an invite to join the space where it all happens.\nFor the latest updates on all things open source\, follow our public feed on LinkedIn.
URL:https://openteams.com/event/can-ai-agents-extend-the-half-life-of-open-source-software-a-conduit-case-study/
ATTACH;FMTTYPE=image/png:https://openteams.com/wp-content/uploads/2026/04/OSAC-April-2026-William-Hill.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20260521T120000
DTEND;TZID=UTC:20260521T130000
DTSTAMP:20260613T125422
CREATED:20260508T184134Z
LAST-MODIFIED:20260511T061502Z
UID:10000019-1779364800-1779368400@openteams.com
SUMMARY:AI on Your Own Terms: Practical Guide to Local Models
DESCRIPTION:As large language models make their way into everyday work\, creative projects\, and personal productivity\, more people want to use them on their own terms – with control over their data\, costs\, and how they customize the tools. Hosted services like Gemini\, Claude\, and ChatGPT are convenient\, but a rapidly maturing open source ecosystem now makes it practical to run capable models on the hardware you already own. This presentation surveys that landscape: how to pick a model that fits your machine (with a brief look at model types\, quantization\, and reasoning capabilities); how to run them locally using tools like llama.cpp\, vLLM\, and SGLang; and how to wire those models into real workflows through code editors\, tool-use frameworks\, and agentic systems. We’ll also touch on what to do when local compute hits its limits – from API aggregators like OpenRouter to on-demand cloud GPU rentals – with practical notes on the trade-offs at each step. Regardless of your technical background\, you will walk away with a clearer map of what’s possible today with local AI and a sense of where to begin experimenting in your own work. \n\nREGISTER VIA ZOOM \nAbout the Speaker \nDillon Roach\, Ph.D. is a Sr. AI Research Engineer at OpenTeams\, where he helps organizations navigate the fast-moving GenAI landscape – from prototype to production. With a background in high energy nuclear physics and years in the open source PyData ecosystem\, he specializes in translating emerging AI capabilities into practical\, deployable solutions. Dillon has driven the AI and ML technical work across engagements for major financial institutions and government clients\, building production RAG systems at scale\, developing custom reinforcement learning models\, and standing up end-to-end pipelines around both proprietary and open weight models. His work spans fine-tuning\, agentic architectures\, multimodal systems\, and the messy real-world engineering that sits between a model checkpoint and a governed deployment. \nAbout the Open Source Architect Community \nThe Open Source Architect (OSA) Community is an invitation-only group for seasoned software architects who are passionate about open source technology. Request to join the OSA Community: https://forms.gle/7efbynVzYhhH2LCQ7\nWe review each application carefully. If it’s a fit\, you’ll get an invite to join the space where it all happens.\nFor the latest updates on all things open source\, follow our public feed on LinkedIn.
URL:https://openteams.com/event/ai-on-your-own-terms-practical-guide-to-local-models/
ATTACH;FMTTYPE=image/png:https://openteams.com/wp-content/uploads/2026/05/Website-Announcement.png
LOCATION:https://openteams.com/event/ai-on-your-own-terms-practical-guide-to-local-models/
END:VEVENT
END:VCALENDAR