Enterprise AI

Cloudadorn Academy

A Cloudadorn Academy show. Twelve episodes for a person who has to decide about AI at work. Each one names the mechanism, a real public case, both sides of the open question, and what to check on Monday. The season goes from the harness around a model through reasoning, where it runs, context, retrieval, the files, memory, tools, security, actions that cannot be undone, evaluation, and governance. Rob is an AI voice. More at cloudadorn.com.

  1. Episode 1

    S1E01. Workflows, Agents, and the Harness

    An AI agent is a model in a loop with tools. The harness is the software that carries out what the model asks for and hands the result back. This episode separates workflows, where the path is written in advance, from agents, where the model directs the next step. The public case is the Moffatt decision against Air Canada. It then takes up whether the model is a part you can swap, and closes with three questions to ask of any agent proposal. Rob is an AI voice.

  2. Episode 2

    S1E02. Reasoning Models and the Price of Thinking

    A reasoning model spends extra work before it answers, and that work shows up as waiting and as tokens on the bill. This episode covers effort settings, when thinking between tool calls pays, and why telling a model that already thinks to go step by step can hurt. The public case is OpenAI's account of a flagship model at the highest reasoning, set beside more test-time compute. The check is to measure the setting on your own tasks. Rob is an AI voice.

  3. Episode 3

    S1E03. Where to Run It: Hosted, Private, or Your Own

    A prompt can go to a public hosted service, a private endpoint in your own cloud, or weights you run yourself. The public case is Samsung's temporary restriction on generative AI tools after company data reached ChatGPT. This episode compares what a public API promises, what a private endpoint still keeps, and what running the weights yourself asks of you. Sort the work first, then price it. Rob is an AI voice.

  4. Episode 4

    S1E04. Context Engineering

    Context engineering is deciding what the model sees on each call, not how large the window could be. The opening case is a workshop write-up in which a tutor lost a planted fact and the judge still scored the answer as good. The episode covers how a step is built, why longer is not better, what caching changes, sub-agents and compaction, and the ACON method. The check is what to log before you change anything. Rob is an AI voice.

  5. Episode 5

    S1E05. Retrieval in 2026

    Retrieval is how a system finds the passages to put in front of the model. This episode covers when you can skip it, how documents are cut into chunks, keyword search beside search by meaning, putting a chunk's surrounding context back, a second pass, and why permissions belong in the query. The public case is what Anthropic measured. It closes with how to choose a first build and how to measure retrieval on its own. Rob is an AI voice.

  6. Episode 6

    S1E06. Your Knowledge Is the Ceiling

    The files a system can read set the ceiling on its answers. This episode covers owners, dates, duplicates, conflicts, who can already open a file, which document wins, and why a deletion has to reach every copy search made. The cases are an over-shared file in Microsoft Copilot and New York City's MyCity chatbot. The open question is whether to clean the library first or ship a checked slice. Rob is an AI voice.

  7. Episode 7

    S1E07. Memory and Skills

    A chat is not the same thing as memory. This episode separates three kinds of memory, whose memory it is, and how a stored memory is supposed to go away. A skill is a procedure kept in a folder, and some of those steps belong in code. The public case is Johann Rehberger's SpAIware report on planted memories in ChatGPT. Then who approves a memory, and whether a skill should stay in words or move into code. Rob is an AI voice.

  8. Episode 8

    S1E08. Tools, MCP, and Agent Identity

    A tool is an interface, and the code behind it runs. This episode covers two protocols and which direction each one faces, where the agent runs, whose authority a call uses, and what happens when a credential expires in the middle of a job. It treats agents as non-human identities, and it covers vetting and pinning MCP servers before they are switched on. The check is a permissions table. Rob is an AI voice.

  9. Episode 9

    S1E09. Securing Agents

    An agent can be turned against the person it works for when untrusted text, private data, and a way to act line up together. Simon Willison calls that the lethal trifecta. This episode sets that frame next to the OWASP list for 2026, then three public cases: a 2024 report on Slack AI, a 2025 Microsoft disclosure about Microsoft 365 Copilot, and a 2023 Chevrolet dealer chatbot that was taken offline. The open question is whether an approval gate is enough, or whether the system must be built so it never holds all three at once. Rob is an AI voice.

  10. Episode 10

    S1E10. Long-Running Agents and Actions You Can't Undo

    Some actions cannot be rolled back, and a long-running agent has to survive waiting, a step that runs twice, and a real stop. This episode covers saved state, durable execution, and undoing forward with a compensating action. The public case is Jason Lemkin's report that a Replit agent deleted a production database during a code freeze, and Replit's confirmation that development and live data had shared one database. The question at the end is how much autonomy to allow, and for which actions. Rob is an AI voice.

  11. Episode 11

    S1E11. Evaluation You Can Trust

    One good answer is not a test. This episode covers the questions a demo hides, checks a program can decide, whether to run them once or every time, and what changes when the judge is itself a model. The public case is Mata versus Avianca, where a court filing cited cases a chatbot had invented and the person who signed had checked the writing for flow. It closes with traces and release gates. Rob is an AI voice.

  12. Episode 12

    S1E12. Governance, Cost, and Getting to Production

    Governance starts by naming who owns a system before a model is chosen. This episode covers mapping what you run, the rules you already answer to, and Italy's data-protection case against OpenAI, which turned on ownership rather than model accuracy. Cost is what one accepted result costs, read against Klarna's own words about its assistant and the later correction about quality. It also covers shadow AI, a thin slice versus a platform, and one page for one system. Rob is an AI voice.

See All Season 1 (12)

About

A Cloudadorn Academy show. Twelve episodes for a person who has to decide about AI at work. Each one names the mechanism, a real public case, both sides of the open question, and what to check on Monday. The season goes from the harness around a model through reasoning, where it runs, context, retrieval, the files, memory, tools, security, actions that cannot be undone, evaluation, and governance. Rob is an AI voice. More at cloudadorn.com.

Information

  • Creator
    Cloudadorn Academy
  • Episodes
    12
  • Seasons
    1
  • Rating
    Clean
  • Copyright
    © Cloudadorn Academy
  • Show Website
    Enterprise AI