Kay Malcolm (outbound database product management, Oracle) argues that as AI agents speed up individual work, teams still lack a shared layer for context and reasoning: Git records what changed, not why. She frames the model as a brain, the harness as the body, and memory as the nervous system connecting them, distinguishing five kinds of memory: short-term, long-term, episodic, procedural, and semantic. She then examines where agent memory should live, arguing through a live demonstration with audience volunteers playing relational, document, graph, and vector stores that spreading memory across specialized databases leads agents to guess wrong when reconciling stores, and advocates consolidating memory in one place (the database as the last line of defense) with a memory broker to serve as a team-wide multiplier. # Channel Identity Observations — Video: "No Memory, No Harness" (Kay Malcolm, Oracle) ## 1. Explicit Self-Description Evidence ### Speaker Role and Employer - **Kay Malcolm** introduces herself as running an **outbound database product management team at Oracle**: > "This is my team. I run an outbound database product management team at Oracle. I've been at Oracle a really long time, 20 years." - She describes herself as an engineer and platform builder: > "I'm an engineer but I'm kind of a developer poser too" and claims authorship of **Live Labs**: > "a platform that I wrote myself." - Claims a practitioner background prior to Oracle: > "I came from a customer. That customer's name was Southern Company. It was a power company... I was a rockstar performance tuner." ### Organization-Affiliated Claims - The channel/video presents Oracle product claims, stated as marketing-aware commentary: > "Oracle is not the Oracle that you think that is why I am here today" and > "we have a marketing problem." - Product claims include: > "Oracle could natively in the same table down to the same partition store JSON graph vector... spatial... blockchain in the same database." ## 2. Claimed Scope - Topic scope: **AI agents, agent harnesses, memory architectures, and database storage of agent memory**, framed around enterprise engineering problems. - Positioned as **developer-oriented educational content** with vendor product integration (Oracle AI Database, Oracle Agent Memory SDK, OCI free tier). ## 3. Demonstrated Presentation Patterns ### Intended Audience - **Developers and engineering leaders**, evidenced by direct address: > "I know that there are a lot of developers here and you all don't care about security." - Assumes familiarity with tools like **Codex, Claude Code, git workflows, and LLMs**: > "The short-term memory is if you're with chat, Claude code, right, Codex, pick your poison." ### Presentation Style (Observable) - **High-energy, interactive conference talk** format: audience call-and-response ("Are we having fun?"), live volunteers for a demo (four audience members assigned database roles), and humor. - **Storytelling and analogy-driven** teaching, explicitly stated: > "I speak in analogies and I speak in stories." - Self-deprecating humor and pop-culture references (Beyoncé's "Sasha Fierce," Al Bundy) used to explain technical concepts (agent memory types). ### Content Substance Demonstrated - Technical taxonomy presented: **five memory types** (short-term, long-term, episodic, procedural, semantic) with definitions. - Cites external sources as evidence: > "These are three papers that I read on the airplane. This first one is from OpenAI..." and a quote attributed to Harrison Chase: > "Your harness, your memory." - Includes **calls to action and free resources**: Live Labs, Oracle AI Developer Hub, and OCI always-free tier: > "It is the most generous of any of the hyperscalers." ## 4. Claims vs. Demonstrated Patterns — Distinction - **Creator claims**: Oracle database superiority for agent memory; Live Labs authorship and "40 million users"; OCI free tier being "the most generous." - **Demonstrated**: Practical experience narrative (distributed team, Codex usage, git context loss problem), pedagogical framing of agent architecture, and vendor-affiliated advocacy delivered in an engaging conference format. No independent verification of the product claims is present within the material itself. # Delivery Observations — Kay Malcolm, Oracle ## Tone & Register - **Energetic, comedic, conversational**: Opens by demanding audience energy and self-identifying with humor: > "my name is Kay Malcolm. I am a retired hiphop instructor. So, if I don't get more energy than that, we will start." - **Self-deprecating asides** recur throughout, e.g.: > "I've been at Oracle a really long time, 20 years. Funny story, I started when I was 12." > "I'm an engineer but I'm kind of a developer poser too." ## Audience Interaction Patterns - **Repeated direct calls-and-response**, including a signature forced-choice phrase: > "Is that okay? Yes or yes." > "Yes or yes? You got your So, you have your assignment." - **Rhetorical questions and polls**: > "Does anyone want to guess what those two letters are...?" > "How many people agree with me? Man, this tough crowd you." - **Live demonstration with volunteers**: recruits four audience members to play database types ("You're going to be a relational database... You are my vector database") — an interactive, physical teaching habit. ## Teaching Habits & Structure - **Analogies as an explicit method**, stated by the speaker herself: > "I speak in analogies and I and I speak in stories because if I tell you this and Marvel, you know exactly what I'm talking about." - Core extended analogy: model = "little brain floating in a glass jar," harness = "the body," memory = "the central nervous system." - **Storytelling with confession framing**: > "when I tell you the story, you have to promise me that you're not going to judge me. Do you promise?" - **Problem-boxing device** to manage narrative structure: > "Will you all hold my problem for me right here? We're going to just tuck that in a little box." - Later resumes it: "Okay, back to PY. So the problem that I had, we solved it..." - **Callout of the one takeaway**: > "if you forget everything I say and you remember one thing, Oracle is not the Oracle that you think that is..." ## Vocabulary & Recurring Phrases - **Memory taxonomy**: repeatedly enumerates short-term, long-term, episodic, procedural, semantic memory. - **Recurring conceptual pairing**: memory + harness ("your harness is your body and that memory is your central nervous system"). - **Pop-culture references**: Sasha Fierce/Beyoncé ("Any Beyonce fans?"), Al Bundy ("my Albundy days"), "pick your poison." - **Token-era framing**: "the token maxing era of 2025," "it's going to burn up a whole bunch of tokens," "if you talk loud that's 5x the tokens for you." ## Personal anecdotes as evidence - **Long personal history stories** used to ground technical points (Southern Company DBA story, meeting-count escalation "How many meetings am I going to? Four... Six"). - **Named personal agents/colleagues**: "Py" the memory broker, team members "Kevin" and "Linda," and her own agent "Sasha Fierce." ## Uncertainty Notes - The "Yes or yes" pattern and "don't judge me" framing each appear **twice-plus**, suggesting stable habits, but sample size is a single talk. - Exact repetitions of the memory-type list appear twice; whether this is a fixed ritual in her other talks cannot be confirmed from one transcript. # Position Record: Kay Malcolm, Oracle — "No Memory, No Harness: Why the Database Is the Last Line of Defense" ## Speaker Context (as stated) - **Kay Malcolm** runs an outbound database product management team at Oracle; 20 years at Oracle; previously a performance tuner/DBA at Southern Company (power company, Atlanta). - Team structure described: platform development, content development (LiveLabs — a platform she says she wrote), QA, and front-end development with AI; split between AMIA region and the US. ## Central Claims ### 1. AI made individuals faster but not teams more productive - **Problem observed**: A Netherlands-based team checked in code at ~4:00 a.m. (Oracle uses Codex) but did not check in the **context** from Codex; the US team woke up with code but no context. - **Diagnosis**: "Git records the code and not human intent." Code creation was no longer the bottleneck; **collaboration** was. Repositories were diverging; time still went to testing and validation despite token spend. - **Resolution**: "We used AI to solve a problem that AI created" — a **memory broker named "Py"** sharing context (procedural, episodic, long-term memory) across forks; developers remained in control while Polly tracked which fork/branch/commit context belonged to. ### 2. An enterprise agent is more than model + workflow Components of a real enterprise agent, per Malcolm: - **Model** — "the brain floating in a glass jar" - **Harness** — "the body," how the agent gets things done (tools, guardrails) - **Memory** — "the central nervous system" carrying context - Tools, context window, memory retrieval, and **guardrails** (she emphasizes security, noting Oracle's security positioning) ### 3. Memory types to remember (her taxonomy of five) - **Short-term**: the session (chat, Claude Code, Codex) - **Long-term**: persists across sessions - **Episodic**: what happened in past interactions - **Procedural**: tools and steps taken - **Semantic**: enterprise knowledge ### 4. Data sprawl creates a single-source-of-truth problem - Story from Southern Company: each specialized database a DBA managed meant two weekly meetings (security + patching, Sarbanes-Oxley context). Adding an unstructured database and then Neo4j (after her "five nested UNION ALL" query) raised meeting count to six — she quit and joined Oracle. - **Claim**: If agent-relevant data lives across relational, JSON, graph, and vector databases, "where is your single source of truth?... Sometimes it'll get it right. Most times it'll get it wrong and it's going to burn up a whole bunch of tokens." - Audience demonstration with four volunteers (relational, unstructured, graph, vector databases) trying to coordinate storage of "the cow jumped over the moon" — illustrating coordination failure. ### 5. Oracle 26ai as the solution (vendor position) - **Claim**: Oracle can store JSON, graph, vector, spatial, and blockchain tables natively in the same table/partition; any data type in a 26ai database, on AWS, GCP, Azure, OCI, or on-prem. - Her proposed mapping: long-term + procedural memory in relational/JSON; short-term/long-term in graph; procedural via graph relationships; episodic + semantic via vector, also stored as text. - **Position**: "The Oracle AI database is the best place to store this agent memory that's going to power your harness." - Notes a **marketing problem** (few knew Oracle could do this) — self-acknowledged vendor framing. ### 6. External evidence cited (papers she says she read on the plane) - **OpenAI** paper on its in-house data agent: memory crucially important for filtering correctly rather than string matching. - **Harrison Chase**: "Your harness, your memory. And if you don't own your harness, you don't own your memory." - **Counter to "Claude has memory"**: framed as file-system memory that works for one agent but "when you scale past one... it creates a problem." ### 7. Product/Calls to action - **Oracle Agent Memory SDK**: `pip install oracle-agent-memory`; stores live conversations, memories, facts; decides what's worth keeping; backed by Oracle Autonomous Database; LLM of choice or local model via Oracle Private AI services container. - Punchline: "AI makes individuals faster. Shared memory on an Oracle AI database makes teams faster." - Resources: Oracle AI Developer Hub, LiveLabs (her claim: wrote it ~6 years / 40M users ago), always-free OCI tier (free database, compute, 3,000 emails/month, 200GB storage). ## Qualifications & Caveats Preserved - She explicitly flags promotional self-awareness: "you're not recording me, right? Because this doesn't paint me in a good light"; "Oracle is not the Oracle that you think" and "we have a marketing problem." - The Py example is self-described as "a very simplistic example." - No counter-positions were voiced on stage; audience interactions were participatory, not disputational. # Speaker & Provenance Observation Record ## Video Metadata - **Title:** No Memory, No Harness: Why the Database Is the Last Line of Defense — Kay Malcolm, Oracle - **Video ID:** `01a15ca7-65fb-7d67-b55d-6897caca4cb5` - **Comment availability:** Not specified in supplied material ## Speakers & Roles ### Primary Speaker - **Kay Malcolm** — **Creator / Keynote Speaker** - Self-identified: runs an **outbound database product management team at Oracle**, 20 years at Oracle - Prior background stated: former DBA/performance tuner at **Southern Company** (power company, Atlanta); self-described former hip-hop instructor ### Audience / Crowd - **Unidentified audience members** — interactive participants ("Yes or yes?" responses, cheering) - **Four audience volunteers** — assigned role-play parts in a demo: - Relational database, unstructured (JSON) database, graph database, vector database ### Named Third Parties (referenced, not speaking) - **Joe Mundy** — quoted/anecdote about installing Redis and Oracle's vector database ("Joe Mundy called me") - **Harrison Chase** — quoted: "Your harness, your memory. And if you don't own your harness, you don't own your memory." - **Kevin, Linda** — team members referenced in the Py/memory-broker example (Linda noted as present in audience) - Team members "in the audience" — acknowledged but unnamed ## Referenced Sources & Third-Party Claims - **"Three papers read on the airplane"** — only one described: an **OpenAI paper on its in-house data agent**, claimed to state memory was crucial for correct filtering rather than string matching. Other two papers not identified in transcript. - **Named products/technologies cited:** Oracle Database 26ai, Oracle Autonomous Database, Oracle Agent Memory SDK (`pip install Oracle agent memory`), Oracle Private AI services container, GitHub, Git, Codex (used at Oracle), Neo4j, Redis, Claude (memory), ChatGPT, memory.md files, OCI, Livelabs - **Anecdotal claims:** "40 million users" of Livelabs; "always free OCI... most generous of any of the hyperscalers"; Oracle "the most secure database company" ## Promotional Segments (Flagged) - **Closing segment:** Promotion of Oracle AI Developer Hub, **Livelabs.oracle.com** (speaker states she wrote the platform), free OCI tier, and Oracle Cloud "always free" — explicit **promotional call to action** ("search Google for Oracle Cloud, always free", "Connect with me") - **Core pitch:** Repeated positioning of **Oracle AI Database 26ai as the recommended store for agent memory** — this is the speaker's employer's product; product advocacy runs throughout the talk - **"We have a marketing problem"** — speaker's own framing of Oracle perception vs. capabilities ## Uncertainty Notes - No timestamps available in transcript - Speaker's third paper (of "three papers") is unspecified; only OpenAI paper identified - "Agency that has no name" (prior employer) — intentionally unidentified Everyone, are we having fun? \>\> Oh, you've got to give me way more than that. So, let me tell you, um, my name is Kay Malcolm. I am a retired hiphop instructor. So, if I don't get more energy than that, we will start. We'll start. Are you having fun? \[cheering\] \>\> Okay. All right. So, here's what we're going to talk about today. Now, you guys have heard a lot about two letters. Does anyone want to guess what those two letters are that I'm going to talk about today? \>\> Data. That was pretty good. DB. I'm going to talk about AI, but I'm specifically going to talk about agent harnesses. But before I do that, I want to introduce you all to a few people. Is that okay? Yes or yes. Is that okay? \>\> I gave choices. Yes. Anyway. All right. Okay. All right. This is my team. I run an outbound database product management team at Oracle. I've been at Oracle a really long time, 20 years. Funny story, I started when I was 12. So, don't do the math and don't start start adding in your head. Um, and we've got a problem. That problem is I've got one group that does platform development and then I have another group that does content development for live labs, a platform that I wrote myself. So yeah, I'm an engineer but I'm kind of a developer poser too. And then I've got another group who does QA and then I have another group who does my front-end development with AI. Here's what I found out as a leader. Because in the token maxing era of 2025, because you know, we're not token maxing anymore, right? We are responsible AI now. But in the token maxing era, the thing that I found out was while AI was making the individuals on my team faster, there was another problem it was creating. It wasn't making my team more productive. And the reason was when one team from the Netherlands checked in code at my 4:00 a.m. in the morning because I've got half of my team that's in AMIA and I have half of my team who that are here in the United States. They checked in the code but they didn't check in their context from Codeex. We use Codeex at Oracle. So then when the US team woke up, they got the code but no information about the context. So we used AI to solve a problem that AI created. And here's what we did. Oh well, let me talk about this first. So some of the issues, the context, like I said, wasn't shared. GitHub wasn't tracking that. I had repositories that were diverging and I was asking the managers who work for me, what's happening to your teams? Why why are we not going faster? We're spending all of this money on tokens. We're spending all this money on AI, yet something is missing because we're still spending time doing testing and validation. So our netn net wasn't really wasn't really working for us because git records the code and not human intent. So it's a problem and even though code creation was no longer our problem still had a bottleneck. We needed a collaboration layer. Now, I do have members of my team in the audience, so don't judge me, and you know who you are. I'm not saying that you all didn't collaborate. But now, we've got a new team member, and that new team member is AI. So, we needed to figure out how to track our progress in our next steps. how to rationalize decisions that the agent was making. We needed to figure out how to resolve questions in conflicts. Okay, hold my problem. Will you all hold my problem for me right here? We're going to just tuck that in a little box. Let me define what a enterprise agent actually is. Now, most people think that an enterprise agent is the model and workflow. How many people agree with me? Man, this tough crowd you. Okay, one person. Okay, the rest of you think it's a little bit more. Okay, let's see what could it be that a real enterprise agent has tools. Tools are how it does things. Context. The context. That's a context window. That's what's in the actual prompt. Memory. Huh? And if you're thinking, "But wait, K, memory, you just said that the model is kind of like the brain of the operation." Hold tight. We're going to talk a little bit more about memory retrieval because you don't want to get everything back. So that's being able to to retrieve the right information back. And then I know that there are a lot of developers here and you all don't care about security. I care about security because I work for the most secure database company and I used to work for um agency that has no name. But guard rails is also important. This is the harness. I speak in analogies and I and I speak in stories because if I tell you this and Marvel, you know exactly what I'm talking about. So the agent, think of it as the model, little brain floating a in a glass jar plus this harness. This harness is the body. So it's how the agent can actually do things and get things done. That memory, that's the part of the central nervous system. And you remember the central nervous system connects the brain to the rest of the body, legs, arms. That's the part of the central nervous system that carries context. So you remember my problem with Git. What I needed was memory. Okay, so there are a number of memory types. I chose five, the five most common ones that people talk about and these are the ones that I want you to remember. The first one is short-term memory. That's the session, right? And so if you're storing memory of an AI uh process, that is the short-term memory is if you're with chat, cloud code, right? Codeex, pick your poison. The long-term memory is what persists across sessions. Episodic memory. Hm. What happened the last time I interacted with fill in the blank? That's your episodic memory. Procedural memory tools, steps that were taken. And then finally, semantic memory. And semantic memory because we're talking enterprise agents. We're not talking the agent that I built, Sasha Fierce, because remember I told you guys that I was a I'm a a dancer. So, of course, my my chief of staff is going to be called Sasha Fierce because that was Beyonce. Any Beyonce fans? Okay, I'm sorry. All right, we got to focus. Okay, so these are the memory types. Now, when you're defining this real enterprise agent in this memory, there's something you need to consider where to store it. And so, I'm going to tell you guys a story. But when I tell you the story, you have to promise me that you're not going to judge me. Do you promise? Do you promise \>\> you're not recording me, right? Because this doesn't paint me in a good light. Okay. All right. The world of data was one simple. I've been at Oracle a long time, but I came from a customer. That customer's name was Southern Company. It was a power company. I'm based out of Atlanta. And I was hired at Southern Company because I was a rockar performance tuner. You had a SQL query. I mean, I'm dating myself, but whatever. You had a SQL query. I knew all of the innit.org parameters. Even the ones when you called support and they said, "Don't remember these. Don't write them down." I wrote them down in my little notebook. I could tune a query within one inch of its life. Then one of you came to my desk because I mean the world the world was rows and columns. It was a great time back in my Albundy days um and said hey I need to store data unstructured. Why I need to do that? And so me being K the the diligent DBA, I was like, "Let me figure it out and get back to you." Did I get back to him? I didn't get back to him. Now, the thing you have to know about Southern Company was for every database system that a DBA managed, I had to attend two meetings. Today, when I hear Sarbain Oxley, I still throw up a little bit in the back of my throat. So I had to attend a security meeting and a patching meeting every week. Never failed. Now because this developer installed a database that was specialized for unstructured. Okay, there are really smart people in the room. How many meetings am I going to now? Four. Okay, I'm a little annoyed, but I'm like, okay, we can we can we can do this. Then they said, "Okay, since you're such a good tuner, I need you to figure out this relationship." Now, the way that Southern Company worked, there was this people could die application, um, and it was a it was like a Nokia phone that people who were climbing the towers, right? So, you guys have have been in a storm and the power goes out, right? And then you're pretty sure that within maybe an hour or two the power will go on. Well, that system that would tell the people who were climbing those trees and risking their lives to turn the power back on sometimes would have false positives or false negatives. So, they wanted to look at all of the other um uh polls in the area to try to get away from the false positive or the false negative. And so I did that in a SQL query and it was it was amazing. It was a five nested union all statement. It was some of my best work. Now it might have taken like 20 minutes to work but it was like a predecessor to graph. Yeah, they they install Neo4j. So now how many meetings am I going to? Six. That's a problem. So I um Oh, let me I got ahead of myself. So you know what I did? I quit. I left and I came to Oracle because I was like this is a problem and maybe I can go to Oracle to help solve it. So then Joe Mundy called me and he said hey um we are installing Reddus. Oracle is late to the game. We've got a vector database. Okay. But here's your problem, Joe. Agents now need access to all of this data. So if data is in an Oracle database, if then it's also in an unstructured JSON database, if it's in a graph database and it's in a vector database, where is your single source of the truth? The agent has to figure that out. Sometimes it'll get it right. Most times it'll get it wrong and it's going to burn up a whole bunch of tokens. And so now if you want to store your memory somewhere, you can store it in a file system. You can store it in clawed or chatgpt because we all know about the memory.md file. But that's going to be a problem. Now I want to illustrate this. I need four volunteers. I can see you raise your hand. One, two. Okay, I can't. Maybe I can. Three. I need a fourth. Ah, fourth in the back. Okay. Fourth in the back. You are going to be our old reliable. You're going to be a relational database. Yes or yes. You got your So, you have your assignment. Okay. And then there was someone here. You're going to be my unstructured database. Okay. And then where was my other? Ah, very good. You're going to be my graph database. You good? Relationship guy. You look like a relationship guy. All right. Very good. Fourth. Where was my fourth? Was it you? Yes. Yeah. You are my vector database. Okay. Now, everybody be really, really quiet. For my four volunteers, I need you all. I'm going to say something to you. And I need you all to decide how you're going to store it and who's going to have the single source of the truth. You can't get up from your seats and you have to whisper because if you talk loud that's 5x the tokens for you. Yes. Okay. Are we ready? All right. The cow jumped over the moon. Go. Doesn't really work, does it? That's a problem. Okay, Oracle. And if you don't forget one, if you forget everything I say and you remember one thing, Oracle is not the Oracle that you think that is why I am here today. How many of you knew that Oracle could natively in the same table down to the same partition store JSON graph vector my vector friend over there my JSON friend spatial you want your memory to be immutable blockchain in the same database raise your hand yeah we have a marketing problem so any data type can be stored in a 26AI database any workload anywhere AWS GCP Azure OCI on prem choice and flexibility so now when we take this and we talk about the agent I want to be able to store my long-term and procedural memory in relational on in JSON I want to store my short-term and my long-term memory graph I want to store procedural because procedural that's how I figure out the relationships right the steps my episodic and semantic memory. I need to do some vector and then store it also as text. Now, if I have four different databases, you all saw they can't talk to each other. It's going to be a problem. And so, what I'm saying to you today is the Oracle AI database is the best place to store this agent memory that's going to power your harness. Remember your harness is your body \[music\] and that memory is your central nervous system. Okay, back to PY. So the problem that I had, we solved it with a memory broker named Py. We used agent memory. We got out of that automatic continuity. So with my team, they were able to share not just their code, but PY also kept track of the context. So if one context window was had procedural memory, episodic memory, information about the long-term memory, that was then shared with the other folks on the team. You could call them agents, if you will. They're just human agents shared across forks. The developers on the team remained in control while Polly was able to create the context, figure out which fork and branch it belonged to and which commit it belonged to. Now this is a very simplistic example but when you take this to the enterprise here's what happens. Memory is the thing that becomes non-negotiable in an agent's harness. Now these are three papers that that I read um on the airplane. This first one is from open AI and it's about its in-house data agent and the thing that it says is it is saying that its in-house data agent actually needs memory. Memory was crucially important to ensure that its agent was able to filter correctly instead of trying to string match. Harrison Chase said, "Your harness, your memory. And if you don't own your harness, you don't own your memory." Which is key. And then I'm sure you all are wondering, "Well, Claude has memory. Why can't I use that?" Well, it's kind of like file system memory and it works with one, but just like in my example, when you scale past one, and you're going to scale past one in the enterprise, it creates a problem. So Oracle has a Oracle agent memory pap package. PIP install Oracle agent memory. You get access to it. And this memory is this SDK that we have is the thing that will hold your live conversations, your memories, your facts and figure out what is worth keeping. So if we look at Py now, Kevin can share his context with Py, our memory broker. We use the Oracle agent memory SDK. It's stored in an Oracle autonomous database. We can use the LLM of our choice or we can use a local model through the Oracle private AI services container. And then Linda, who's actually sitting right here, can interact and work with Kevin, no issues. So yes, AI makes individuals faster. Shared memory on an Oracle AI database makes teams faster. So I don't want you all to compromise. In the age of AI, what 26AI does is you can choose and pick what's best for agent memory file system stored in a database file system or in the database. If you need to do data modeling, you've got JSON, you've got relational. We've got choice. Okay, I've got some goodies for you. The Oracle AI developer hub. That's where you can guys you guys can get coding materials, the applications, what I talked about today. Livelabs.oracle.com. If you've done any of our workshops today, that happens to be something that I wrote myself about six years ago and 40 million users um ago. Spend my OCI tenency money. kick the tires on any Oracle technology um for six hours, 12 hours, however long you need. Um and then I'm giving you all all a Mac Mini. No, I'm just kidding. I'm giving you an OCI Mini. So, I don't know if you knew, but there is an always free OCI. It is the most generous of any of the hyperscalers where you can get a free Oracle database, free compute, you can send 3,000 emails a month, 200 gig in storage, and if you click on that, you can get access to it. Or just search Google for Oracle Cloud, always free. Connect with me. If you build something, will you all message me and let me know? Yes or yes? \>\> Thank you. \>\> \[music\]