Finding Analogies with AI

I saw this article on using AI to help that included a few prompts. I decided to try one.

This is part of a series of experiments with the ChatGPT and other AI systems. Lots of Copilot lately.

The Prompt

Here’s what I wrote, since I was reading piece on cloud migration and writing an editorial:

I am currently learning about cloud migration. Convert the key lessons from this topic into engaging stories and metaphors to aid my memorization

The Response

1. The Cloud Island Adventure:

Imagine your business as a group of settlers on a remote island. They’ve been working with outdated tools and limited resources, making progress slow and inefficient. One day, they hear about a magical cloud island that’s full of modern technology, abundant resources, and a vibrant community.

The settlers decide to embark on a journey to this cloud island, symbolizing your migration to the cloud. As they arrive, they realize they can instantly access powerful tools, scalable resources, and connect with experts from various fields. Just like in cloud migration, your business gains flexibility and efficiency, leaving behind the struggles of managing on-premises infrastructure.

Key Lesson: Cloud migration is like moving to a new land of opportunity, where you can harness advanced tools and resources to grow your business.

2. The Cloud Highway Construction:

Think of your business as a growing city with a bustling population. However, the existing roads and bridges are becoming congested and outdated, hindering growth and causing delays. To expand and flourish, the city planners decide to build a futuristic cloud highway.

This cloud highway represents your migration to the cloud. Construction crews work tirelessly to build this highway, which is scalable, adaptable, and has lanes for various services. As businesses start using the highway, traffic flows smoothly, and they can easily scale up or down as needed. The old congested roads symbolize the limitations of on-premises systems, while the cloud highway signifies the ease of scalability and innovation in the cloud.

Key Lesson: Cloud migration is like building a high-speed highway that allows your business to easily adapt, grow, and efficiently navigate the digital landscape.

3. The Cloud Carnival:

Envision your business as a traditional carnival that’s been running for years. The carnival’s attractions are fixed in place, and changing or upgrading them is difficult and time-consuming. Visitors are getting bored, and the carnival is losing its charm.

Deciding to modernize, the carnival organizers pack up and move to a new location, which represents migrating to the cloud. In this new location, they can easily set up and tear down attractions, experiment with new games, and respond quickly to changing trends. The cloud becomes their dynamic playground, allowing them to create delightful experiences for visitors.

Key Lesson: Cloud migration is like relocating a carnival to a space where you can easily innovate and provide fresh, exciting experiences to your customers.

4. The Cloud Puzzle Factory:

Imagine your business as a puzzle factory, creating intricate puzzles with limited resources and machinery. You’re tasked with making bigger and more complex puzzles, but the factory’s machinery is old and cannot keep up with the demand.

To overcome this challenge, you decide to move the factory to a cloud-powered puzzle factory. Here, you have access to state-of-the-art machines that can quickly produce even the most complex puzzles. You can rent additional machines when needed and return them when the demand decreases. The cloud puzzle factory allows you to efficiently meet demand without being limited by physical constraints.

Key Lesson: Cloud migration is like upgrading your puzzle factory to a cloud-powered version, where you can easily scale resources to meet demand and improve production efficiency.

By associating these engaging stories and metaphors with the key lessons of cloud migration, you’ll find it easier to remember and apply these concepts in your learning journey.

Thoughts

I liked these analogies. They got me thinking about how to explain things to customers, though they are all positive and don’t represent the downsides. However, when I asked to alter this to show how this hinders progress, I got the result below.

Very interesting. Not sure if I think this is that helpful, but it was thought provoking.

1. The Stagnant Island Settlement:

Picture a group of settlers who refuse to leave their old, resource-scarce island. They struggle with outdated tools and limited resources, but they’re unwilling to explore the nearby cloud island that offers modern technology and abundant resources.

As time goes on, the settlers fall behind in their development. They can’t innovate or expand due to their lack of access to advanced tools and resources. The once-promising settlement becomes stagnant and isolated, symbolizing the limitations of staying on-premises instead of migrating to the cloud.

Key Lesson: Choosing not to migrate to the cloud can lead to stagnation and missed opportunities, as your business remains bound by outdated tools and restricted growth.

2. The Congested Road City:

Imagine a bustling city that stubbornly refuses to build a modern cloud highway. The existing roads and bridges are constantly congested, causing delays, frustration, and hampering the city’s growth.

As more businesses and people move in, the traffic situation worsens. Without the scalability and adaptability of a cloud highway, the city’s infrastructure can’t handle the increased demand. This congestion and lack of flexibility mirror the challenges of sticking with traditional on-premises systems.

Key Lesson: Failing to migrate to the cloud can result in congestion and inefficiency, preventing your business from scaling and responding effectively to changing demands.

3. The Stagnant Carnival Grounds:

Consider a carnival that’s stuck in its old location, unable to adapt to changing times. The attractions become outdated, and visitors start losing interest. Despite the need for innovation, the organizers resist moving to a cloud-enabled carnival.

As a result, the carnival fails to attract new visitors and struggles to create exciting experiences. The reluctance to embrace the cloud leads to a decline in customer satisfaction and revenue, as the competition adopts modern approaches.

Key Lesson: Not migrating to the cloud can result in a decline in customer engagement and revenue, as your business fails to adapt to changing market demands and deliver innovative experiences.

4. The Inefficient Puzzle Factory:

Visualize a puzzle factory that clings to its old machines and refuses to transition to a cloud-powered system. The factory can’t keep up with the demand for larger and more complex puzzles, leading to delays and frustrated customers.

Without the ability to scale resources on demand, the factory struggles to meet production goals. The reluctance to modernize impedes efficiency and profitability, as competitors who utilize cloud resources outpace them.

Key Lesson: Neglecting cloud migration can lead to production inefficiencies and missed business opportunities, as your organization struggles to scale and respond to market needs.

By exploring these scenarios that depict the hindrances of not moving to the cloud, you can gain a better understanding of the potential pitfalls and disadvantages of staying with traditional, on-premises systems.

Posted in Blog | Tagged , , , | 4 Comments

Restore with Standby–#SQLNewBlogger

A customer had a question about restoring with standby, so I wrote a quick post to explain how this works.

Another post for me that is simple and hopefully serves as an example for people trying to get blogging as #SQLNewBloggers.

The Scenario

Sometimes you want to restore part of your data, but you still want the option to continue restores. A classic example of this is when you are restoring a number of transaction logs and want to check the data to find a place where certain values haven’t been changed.

Suppose someone deletes a bunch of data between 10am and 11am from the supplier table. You know that they added “Acme” to this table before the delete. You might restore up to 10am and check the supplier table for the old data and look for Acme. If it’s not there, maybe you restore the 10:05am log backup and check again. If it’s not there, then the 10:10am log, etc.

SQL Server lets you query a restored, but not recovered database with the STANDBY option. If you use NORECOERY, you can’t query the data. I won’t delve into the technical process in this blog, but for now, this is what we want to do: query a restored db, but not prevent future restores.

Setup

First, create a database and then take a backup. I created the “sandbox” database in my system and backed it up. I won’t cover that. Now, let’s set up a restore. I’ll choose a new name, since I’m looking for data. Here’s the statement I picked:

USE [master]
RESTORE DATABASE [sandbox4] FROM  DISK = N'D:\SQLBackup\New folder\sandbox_20210308.bak' WITH  FILE = 1,
   MOVE N'Sandbox' TO N'D:\SQLServerData\SQL2017\Sandbox4.mdf',
   MOVE N'Sandbox_log' TO N'D:\SQLServerData\SQL2017\Sandbox4_log.ldf',
   STANDBY = N'D:\SQLBackup\New folder\sandbox_RollbackUndo_2023-08-07_11-51-39.bak',  NOUNLOAD,  STATS = 5
GO

This is complex, and I haven’t memorized this syntax. Plus I don’t want to type all those paths. Instead, I use SSMS. I’ll set up the restore there. Here are the three screens. Note in the first, one I’ve pointed to the “Script button”, which is what I pushed to get this command.

I’ve picked the device here and changed the restore to database name.

2023-08-07 12_56_32-Zoomit Zoom Window

File options. Make sure the filenames don’t conflict with existing ones.

2023-08-07 12_56_53-Restore Database - sandbox4

Set the standby option and remove the tail log backup if this is the same instance as the original database.

2023-08-07 12_56_47-Restore Database - sandbox4

Restoring and Querying

When I run this command, I’ll get this type of output. I like getting stats, in case something sticks.

2023-08-07 12_59_24-SQLQuery10.sql - ARISTOTLE_SQL2017.master (ARISTOTLE_Steve (63))_ - Microsoft SQ

In the object explorer, I’ll also see the database as standby/read-only.

2023-08-07 12_59_47-Zoomit Zoom Window

If I open a query window, I can get data from this database.

2023-08-07 13_01_07-SQLQuery10.sql - ARISTOTLE_SQL2017.sandbox4 (ARISTOTLE_Steve (63))_ - Microsoft

However, I can’t update tables.

2023-08-07 13_01_34-SQLQuery10.sql - ARISTOTLE_SQL2017.sandbox4 (ARISTOTLE_Steve (63))_ - Microsoft

Summary

This is a quick look at how to get a database in standby. I covered one use case above, but not all the ways in which you use standby or what’s happening behind the scenes. If you need to query a database in the middle of the restoring state, use the standby option.

SQLNewBlogger

This post took me about 15 minutes to assemble. I set this up and tested it for a client, then I had to redo the work with screen shots and add the text. It’s not too long, but this is a good example of how I set up a post that leads to others. I need to create these posts:

  • what happens with the standby option
  • restoring more backups to this database with standby
  • restoring more backups to this database without standby
  • coming out of standby mode
  • automating this to look for a data change

You could do this and showcase your knowledge of this feature and how you might use it

Posted in Blog | Tagged , , , | 1 Comment

The IT Jobs AI Can’t Do

This was a provocative title: 6 ITOps Skills That Will Never Be Automated. In a time when AI use is growing quickly and many people fear for their jobs, it’s nice to see someone writing about areas that AI will struggle to handle.

Ironically, lots of these articles are written by writers without much technical expertise and who are more likely than others to struggle in the age of AI. If a computer can mimic styles, less writers will be employed. That might be fitting with so many journalists hyping technologies without really understanding them, doing so in a way that creates stress among actual IT professionals.

The article lists 6 jobs: policy config, incident response, complex scaling, app feedback, ITOps tool deployments, and end-user support. Of these, I’m not sure that app feedback and end-user support are good-paying jobs that many people want, but I know there certainly are people working in these areas who depend on those jobs.

The others are often jobs that few people do. I do think that these are complex jobs where a computer can’t really take in enough information to do a great job here, but I do think that one smart worker could learn to guide an AI that does a lot of the busy work. Someone could specify a policy from an AI and then ask the AI to tweak it as holes or gaps are identified. I think over time a lot of quick incident response items could be handled by an AI, albeit with a human guiding it. Again, that reduces the need for humans in these roles.

To me, that’s where the AI revolution becomes scary. AI is a lever to get a lot done. Fewer humans can be used to accomplish tasks with the aid of AIs, which reduces a lot of the labor needed. After all, we know that in any area, there are lots of beginners and advanced beginners doing work. If we can use an AI assistant to help one or two humans, we might remove the need for a dozen others.

Maybe that’s what a future 10x engineer looks like. Someone that’s way more productive than many others because they’ve leveraged the computer (in the form of an AI) to get a tremendous amount of work done.

I do think there are likely jobs that AIs can’t easily do, but I also think that a lot of the work in these areas might get copy/pasted between organizations. Policies, scaling choices, and more are things that one human might learn from others and mimic those efforts. With better judgment than an AI, but not as much as if a true expert were coming up with the best solution for a particular situation.

Unfortunately, most of us don’t come up with optimal solutions, and our organizations run fine with sub-optimal code/policies/decisions/whatever. Will companies get by with very few highly paid people or a few more low ones and accept mediocre software?

That already happens far too often already. I suspect like most trends, we’ll see quite a few organizations move in this direction. However, I think the human ingenuity will win out and as a few companies realize that the creativity of humans can better target their goals than an AI that merely summarizes other work, the pendulum will swing back.

Unfortunately, a lot of people will get caught in bad situations as this happens. Work on your skills, technical and soft, and be sure that you are in the best position you can be in as the world embraces and evolves with AI technology.

Steve Jones

Listen to the podcast at Libsyn, Stitcher, Spotify, or iTunes.

Posted in Editorial | Tagged , | Comments Off on The IT Jobs AI Can’t Do

Chicago Database DevOps in a Day Workshop

I’m heading to Chicago today for the Redgate Database DevOps in a Day workshops. This is the first of many on the US tour. I’ll be at 5 of them, but there will be another 5 where Ryan, Grant, or our Solutions Engineers will run the show.

If you’ve registered, please say hi, introduce yourself, and ask lots of questions. Hopefully you’ll enjoy the day.

Just a quick trip for me, coming back tomorrow, which is good. I head to the UK Roadshow Friday night..

Posted in Blog | Tagged , , , , | Comments Off on Chicago Database DevOps in a Day Workshop