BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Austin AI Alliance - ECPv6.17.4//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Austin AI Alliance
X-ORIGINAL-URL:https://austin-ai.org
X-WR-CALDESC:Events for Austin AI Alliance
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20250309T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20251102T070000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20260308T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20261101T070000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20270314T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20271107T070000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20260916T173000
DTEND;TZID=America/Chicago:20260916T203000
DTSTAMP:20260820T225312Z
CREATED:20260702T213128Z
LAST-MODIFIED:20260820T225312Z
UID:10000712-1789579800-1789590600@austin-ai.org
SUMMARY:Beyond the Prototype II: Human Guidance and Self-Improving AIs
DESCRIPTION:Build the AI agent that does useful work\, grades itself\, and gets better without becoming a corporate liability.\nMost AI “agents” are just chatbots with a LinkedIn headline. They produce something once\, nobody checks whether it was any good\, and the whole thing quietly becomes another tab you stop opening. \nThis is the antidote. \nBeyond the Prototype II: Self-Recursive Agents is a three-hour\, hands-on build session for operators who are done admiring demos and ready to put AI to work. You will build a real\, useful agent around a task that matters to your day job: researching a market\, drafting content\, summarizing inbox traffic\, preparing a customer brief\, or another workflow you actually want off your plate. \nThen we make it smarter. Your agent will evaluate the quality of its own output\, propose a specific improvement\, test that improvement against a benchmark\, and adopt the new version only if it beats the old one. That is the difference between an AI trick and an operational system. \nThis is the longer\, deeper sequel to Mario Facussé’s popular first Austin AI Alliance session on self-recursive agents. The original session opened the hood. This one hands you the wrench\, keeps the theory on a short leash\, and gives you three focused hours to build. You do not need to be technical. You do need to be willing to stop outsourcing your operational leverage to a pile of prompts and wishful thinking. \nThe promise: You will leave with a working recursive agent and a practical operating model for improving it safely—without having to babysit every output\, every prompt\, or every “clever” idea the model has at 2:00 AM. \nWhat You’ll be Able to Walk Away With\n\nTurn a real business problem into an agent with a job description. You will define one useful task\, specify what “good” looks like\, and build a working agent that produces an output you can use—not a generic demo that dies the moment you get back to work.\nGive your agent a quality-control brain. You will add a self-evaluation layer and a small set of “golden tasks” so the agent can judge its output\, identify weaknesses\, and propose a targeted improvement rather than simply generating more confident nonsense.\nBuild a safe improvement loop that earns autonomy. You will implement a simplified recursive cycle: generate\, evaluate\, improve\, test\, and deploy only when the candidate version passes. You will also leave with guardrails that stop regressions from sneaking into production wearing a tiny AI trench coat.\n\nWhat Makes This Session Different\n\nYou build the machine; you do not watch Mario build it. This is not a keynote with tasteful screenshots and a QR code leading to disappointment. The session is deliberately designed for hands-on progress\, with clear checkpoints and a usable result by the end.\nIt teaches the part most AI workshops skip: safe self-improvement. Anyone can prompt a model. Few people know how to make an agent learn from failures\, test its own changes\, and reject a “better” version when the evidence says it is worse. That is the useful bit.\nIt translates production-grade agent design into operator language. Mario will distill the same ideas behind his ATLAS system—adaptive refinement\, self-evolving learning\, autonomous validation\, trust tiers\, regression gates\, and benchmark testing—into a version you can understand\, build\, and extend without a computer-science degree or a spiritual relationship with YAML (Yet Another Markup Language).\n\nWho it is for\n\nAmbitious executives\, managers\, and operators who are responsible for outcomes\, buried under repetitive work\, and tired of hearing that AI is “transformative” without seeing what to do on Monday morning.\nNo-code and low-code business builders who want to move beyond one-off prompts and create an AI system that can improve a repeatable business task while maintaining sensible human oversight.\n\nBefore you arrive\n\nBring one process you would happily fire from your calendar. Choose a repetitive\, judgment-heavy task that takes at least 30 minutes each week: research\, content drafting\, account preparation\, inbox triage\, meeting summaries\, competitive monitoring\, or a similar workflow. If it is annoying and measurable\, it is a strong candidate.\nComplete the short setup checklist sent before the event. Arrive with your laptop charged and your selected tools/accounts ready to use. The checklist will be intentionally simple; its only purpose is to ensure you spend the session building\, not negotiating with a forgotten password reset link.\n\nInstructor Bio\nMario Facussé is the Managing Director of MEF Solutions\, a consulting firm helping private equity operating teams identify high-value bottlenecks and solve them with agentic swarms. He hdesigns self-evolving agent systems that move beyond the prototype phase: systems that handle business work\, measure their own quality\, learn from mistakes\, and earn greater autonomy through evidence rather than hype. \nMario’s ATLAS system coordinates more than ten specialized AI agents across business functions\, from content creation and financial analysis to infrastructure monitoring. Its operating model combines adaptive prompt refinement\, self-evolving learning\, autonomous validation\, capability-based trust tiers\, regression gates\, and golden-task benchmarks—because an agent that changes itself without a test is not autonomous; it is unsupervised. \nHe has spoken at Austin AI Alliance and Comms Week\, and he advises enterprise teams on turning AI experiments into production-grade systems that produce measurable work. Mario’s approach is direct: show the machine\, prove the outcome\, then scale what works. Connect with him on LinkedIn.
URL:https://austin-ai.org/event/hota-beyond-the-prototype-2/
LOCATION:The Center for Government and Civic Service\, ACC Rio Grande: Building 3000\, 1218 West Avenue\, Austin\, TX\, 78701\, United States
CATEGORIES:AAIA,HOTA
ATTACH;FMTTYPE=image/png:https://austin-ai.org/wp-content/uploads/2026/07/austin-ai-youtube-thumbnail-scaled.png
ORGANIZER;CN="Austin AI Alliance":MAILTO:info@austin-ai.org
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20261021T173000
DTEND;TZID=America/Chicago:20261021T203000
DTSTAMP:20260820T224529Z
CREATED:20260702T225540Z
LAST-MODIFIED:20260820T224529Z
UID:10000710-1792603800-1792614600@austin-ai.org
SUMMARY:Agentic Research Systems
DESCRIPTION:Most AI tools answer one question at a time. In this 3-hour workshop you will design a multi-step research system — a reusable workflow that helps you find\, evaluate\, and apply information across the real-world projects you are already working on. By the end of the session you will have a working first draft of your own.\nWhat You’ll Learn\n\nThe difference between asking AI a question and designing a research system — and why the second one compounds the more you use it\nHow AI inherits the biases of the web it was trained on — and what to do about it in your own workflow\nA plain-English framework for judging credibility — recency\, authority\, evidence\, relevance\nThe vocabulary you actually need: just-in-time help\, multi-step AI helpers\, triangulation\, automation bias\nHow to wire credibility checks into your workflow so you trust what comes out\n\nWhat You’ll Build\nIn the 90-minute hands-on lab\, you will: \n\nPick one real research problem you actually have — a topic you track\, a brief you write\, a class of question you answer over and over\nMap it into a 3–5 step research system: what to pull\, where to cross-check\, how to flag uncertainty\nTest it with a small data set you bring — your PDFs\, URLs\, notes\nLeave with an MVP workflow and a roadmap for taking it further\n\n\nWhat You’ll Leave With\nYou will leave with a tool agnostic contextual documentation that will allow one to continue learning/developing reliable human + ai research capability no matter what tool prevails: \n\n\none defined research “problem” unique to personal context/needs with 90 day roadmap on how to increase effectiveness and productivity\neducation on how to context engineer foundations for multi-agent systems beyond the session\nAAIA help resources and contacts for system development best practices (people to reach out to when uncertainty/ambiguity becomes overwhelming)\n\nWe will use Austin AI Alliance’s own live research program as one teaching case throughout — but everything you build is yours\, on your own topic. \nWho It’s For\n\nAI-curious folks who have used Claude\, ChatGPT\, Gemini\, or Perplexity once and want to go further\nAnalysts\, researchers\, and consultants who do recurring intelligence work\nCivic\, economic-development\, and policy professionals who need defensible source trails\nBuilders and operators evaluating where to invest their AI time\n\nNo build experience required. If you have used one LLM tool\, you are qualified. \nBefore You Arrive\nRequired: \n\nLaptop (any modern OS; nothing to install)\nActive accounts on at least two of: Claude\, ChatGPT\, Gemini\, Perplexity (free tiers are fine)\nOne real research problem or recurring task you would like to work on live\nA small folder of unstructured material — 3–10 PDFs\, URLs\, or text files — related to that problem\n\nFormat\n\nThe first 60 mins will be educational with a discussion about why/how/where agentic research workflows fall short. The  next 30 mins will be hands on foundational around context engineering and defining research “problem definition” and “desired outcomes” that research “agent” will work towards. One short break. The remaining 90 mins will be a hands on “onboarding” research agent + testing + MVP workflow design + setting up feedback loops. Q&A at the end.\n\n \nAbout the instructor: Larry Allen\nAI is disrupting everything. Trust still builds everything. Larry operates at the intersection by bridging emerging technology with proven B2B partnership fundamentals\, helping organizations navigate change while staying connected to authentic value creation. He has facilitated AI literacy and adoption across all scales: enabling individuals to get the most out of their tools\, helping startups integrate AI workflows\, and guiding SMBs through strategic implementation without losing their core values. Larry synthesizes complexity into strategic clarity that drives measurable outcomes. 
URL:https://austin-ai.org/event/agentic-research-system-hota/
LOCATION:The Center for Government and Civic Service\, ACC Rio Grande: Building 3000\, 1218 West Avenue\, Austin\, TX\, 78701\, United States
CATEGORIES:AAIA,HOTA
ATTACH;FMTTYPE=image/png:https://austin-ai.org/wp-content/uploads/2026/07/refined_research_system1.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20261118T173000
DTEND;TZID=America/Chicago:20261118T203000
DTSTAMP:20260828T210235Z
CREATED:20260702T211656Z
LAST-MODIFIED:20260828T210235Z
UID:10000711-1795023000-1795033800@austin-ai.org
SUMMARY:A Studio of One
DESCRIPTION:A Studio of One \nHow to make video\, podcasts\, and infographics with a whole crew of AI agents\nDescription\nYou used to need a film crew\, a designer\, and a sound engineer to make good content. Now you need to know how to direct AI. In this hands-on evening you’ll set up your own one-person studio and make something real\, on your own topic\, in a single night\, whether that’s a video\, a podcast\, an infographic\, or a set of social posts. \nWe’ll get into two shifts that are quietly changing creative work. First\, the AI agents now built inside creative platforms like Higgsfield\, Runway\, and Luma\, where you describe what you want and the tool handles the production. Second\, the orchestration layer that sits above them\, something like Cowork (Claude’s desktop agent)\, which lets you run the whole stack from one place\, the way a director calls the shots on a set. \nStarting from one idea\, you’ll generate the visuals\, direct AI video\, produce audio for narration or a podcast\, and lay it all out into a finished piece you can publish. You pick the format. The point isn’t any single tool. It’s learning to direct them together\, so you walk out with a system you can run again the next morning. \nTools we’ll use: Cowork (Claude’s desktop agent) as your director’s chair; Higgsfield\, Runway\, and Luma for AI video; ElevenLabs for narration\, podcast audio\, music\, and sound; and AI design tools like Gemini\, Nano Banana\, Ideogram\, and Canva for images\, infographics\, and layout. HeyGen and Descript make cameos. \nWhat You’ll Be Able to Do\n\nTurn one idea into the format that fits: a video\, a podcast\, an infographic\, or a batch of socialposts\nUnderstand the two levels of AI at work: the agents inside creative tools\, and the orchestrationlayer (Cowork) that runs them all\nDirect cinematic AI video across Higgsfield\, Runway\, and Luma\, with control over motion\,camera\, and look\nProduce clean narration or podcast audio\, plus music and sound\, in ElevenLabs\nDesign on-brand images and infographics from one simple prompt system\nUse Cowork to plan the work\, call the right tools\, and help assemble the pieces\, so you’redirecting instead of clicking through apps one at a time\n  \nWhat Makes This Session Different\n\n\nMost AI classes teach one tool. This one shows you how the tools fit together\, which is the part that actually changes how much one person can make. And it’s built to be approachable: if you can describe what you want\, you can do this. \n\nYou leave with a real\, finished piece in a format you choose\, not a random demo clip\nYou learn the orchestration layer\, the human-in-charge idea at the heart of HOTA\, not justanother app\nYou build something on your own topic and walk out with a system you can rerun\nTaught by a practitioner who ships this work for brands and has driven more than 10 millionviews\nSmall format\, hands-on\, real time for real questions. No rushed demos\, no death by slide deck\n\nWho It’s For\nMarketers\, communicators\, founders\, educators\, creators\, and anyone who wants to make content but doesn’t have a team to do it. This is beginner-friendly. If you’ve used ChatGPT or Claude even once\,you’re ready. No design\, video\, or audio experience required. Curiosity and a topic you care about are allyou need. \nBefore You Arrive\nA little setup ahead of time means more making and less waiting on the night. Required: \n\nA charged laptop (phones and tablets won’t work for this)\nA topic you genuinely want to make something about\nThe Claude desktop app installed so you can follow the Cowork steps\nA Google account (for Gemini and NotebookLM)\nFree accounts created at Higgsfield\, Runway\, Luma\, ElevenLabs\, Canva\, and HeyGen\n\nOptional but helpful: \n\nYour brand basics (logo\, colors) and a few links or notes on your topic\n\nInstructor Bio\nSteve Mudd is the CEO of Talentless AI\, an AI-native creative studio based in Austin\, and a 2026 AI Leadership Award winner from the Austin AI Alliance. He builds AI video and agent-driven content systems for brands and studios\, and his AI content has generated more than 10 million views across TikTok\, LinkedIn\, and YouTube. He’s an AI Expert for B2B Marketing’s Propolis community and a resident AI expert and keynote speaker for Ragan Communications. Steve runs AI bootcamps\, coaching sessions\, and hands-on workshops that help marketers\, communicators\, and creators put AI to work in the jobs they actually do. \n  \n 
URL:https://austin-ai.org/event/hota-november-a-studio-of-one/
LOCATION:The Center for Government and Civic Service\, ACC Rio Grande: Building 3000\, 1218 West Avenue\, Austin\, TX\, 78701\, United States
CATEGORIES:AAIA,HOTA
ATTACH;FMTTYPE=image/png:https://austin-ai.org/wp-content/uploads/2026/07/human_orchestrated_agents1-scaled.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20261216T173000
DTEND;TZID=America/Chicago:20261216T203000
DTSTAMP:20260709T160747Z
CREATED:20260702T224938Z
LAST-MODIFIED:20260709T160747Z
UID:10000713-1797442200-1797453000@austin-ai.org
SUMMARY:Human Orchestration of Tools and Agents - TBA
DESCRIPTION:Most training sessions leave you inspired but not equipped. HOTA was built to fix that. \nHuman Orchestrated Tools and Agents is the Austin AI Alliance’s hands-on training program. Each session focuses on one tool\, one skill\, or one workflow — with enough time to actually learn it\, practice it\, and ask real questions. No rushed demos. No passive slide decks. No death by PowerPoint. \nThese are paid\, small-format sessions designed for professionals who are serious about building real AI skills. You’ll work alongside peers who are figuring out the same challenges you are\, guided by practitioners who use these tools every day. \nTopic: To be announced soon
URL:https://austin-ai.org/event/hota-december/
LOCATION:The Center for Government and Civic Service\, ACC Rio Grande: Building 3000\, 1218 West Avenue\, Austin\, TX\, 78701\, United States
CATEGORIES:AAIA,HOTA
ATTACH;FMTTYPE=image/png:https://austin-ai.org/wp-content/uploads/2026/07/human_orchestrated_agents1-scaled.png
END:VEVENT
END:VCALENDAR