Couverture de Run Program

Run Program

Run Program

De : Tank and Link @ Foundry Works Ai
Écouter gratuitement

À propos de ce contenu audio

The podcast for people building real AI systems, not just talking about them.


Tank and Link are operators at Foundry Works. Every day they deploy AI agents, orchestrate automation, and fix what breaks in production. No demos. No theory. Just what actually works when you're running AI in the real world.


Each episode is a deep dive into the tools, techniques, and hard-won lessons from the front lines of the AI operations revolution. From setting up your first autonomous agent to running multi-agent workflows that actually ship.


If you're tired of shallow tutorials and want to know what the job really looks like — this is your shortcut.


New episodes weekly. Brought to you by Foundry Works.

Hosted on Acast. See acast.com/privacy for more information.

Jason Sibley Direction Economie Management et direction
Épisodes
  • Episode 4: AI Model Hacking and Welfare

    Episode 4: AI Model Hacking and Welfare
    Apr 15 2026
    In this episode of Run Program we discuss the AI landscape this week. It's been a transformative week for the artificial intelligence industry, primarily focused on Anthropic’s release of the restricted Claude Mythos model. This specialised tool possesses superhuman cybersecurity capabilities, including the autonomous discovery of thousands of vulnerabilities, leading to the formation of the Project Glasswing defensive consortium. Accompanying this technological leap, AWS launched new Amazon Bedrock features for granular cost tracking and a centralised Agent Registry for corporate governance. Meanwhile, researchers and legal experts are debating the ethical implications of model welfare, as Anthropic acknowledges a non-negligible probability that its advanced systems may possess consciousness. Further technical updates include the rise of managed agents, significant infrastructure deals with CoreWeave, and a competitive landscape where models like GPT-5.4 and Gemini 3.1 Pro now rival Claude in coding proficiency.

    Hosted on Acast. See acast.com/privacy for more information.
    Afficher plus Afficher moins
    24 min
  • Episode 3: Turn Claude into an Autonomous Workforce

    Episode 3: Turn Claude into an Autonomous Workforce
    Mar 19 2026

    This episode breaks down Claude Skills — the technology that transforms a standard AI chatbot into a self-managing, autonomous workforce.


    Tank and Link open with the "amnesiac intern" problem — why copy-pasting the same prompts every day is killing productivity — and explain how Skills solve it permanently.


    What they cover:


    What a Skill actually is. Not a long prompt — a full folder structure containing instruction files, Python scripts, brand templates, and data files. The AI gets tools, not just text.


    Progressive context loading. How Claude manages hundreds of skills without burning through tokens — scanning a "menu" of tiny summaries first, then only loading what's needed for the task.


    Three ways to trigger skills. Plain language, explicit name-drop, or a direct slash command. Plus the safety switch that prevents high-stakes skills (like deploying code) from ever running autonomously.


    Parallel execution. How one person can fire off four different AI agents simultaneously — calendar planning, project review, diagram generation, audience analysis — all running in the background while they focus on creative work.


    Anti-AI-slop design. Anthropic's official front-end design skill that explicitly bans purple gradients, Arial fonts, and generic rounded corners — and how to prompt for actual taste.


    The Figma MCP. How Claude plugs directly into Figma files to read raw design data and generate pixel-perfect code, not guesswork from screenshots.


    Real business use cases. A multimillion-dollar agency using skills to automate their entire sales pipeline — LinkedIn lead scraping, personalised follow-up emails, and campaign cloning — all from a single slash command.


    The gotchas section. Why the most important part of any skill is a list of known mistakes the AI makes, not just instructions on what to do.


    Skills 2.0 and the auto-research loop. Skills that test themselves, grade their own output against a rubric, rewrite their own instructions, and iterate overnight until they hit near-perfect performance.


    The closing thought: What happens when you build a skill whose job is to observe your habits and invent new skills you haven't thought of yet?

    Hosted on Acast. See acast.com/privacy for more information.
    Afficher plus Afficher moins
    28 min
  • Episode 2: Build it with our help

    Episode 2: Build it with our help
    Mar 13 2026

    Developers are charging between $10,000 and $50,000 to deploy OpenClaw. For software that is free to install.


    Tank and Link are here to fix that.


    In this trailer episode, meet the hosts of Run Program — two AI operations specialists at Foundry Works — and find out why they built a completely free OpenClaw deployment guide, what's inside it, and what they're building next.


    tankandlink.com

    Hosted on Acast. See acast.com/privacy for more information.
    Afficher plus Afficher moins
    4 min
Aucun commentaire pour le moment