Prompting Archives | Page 5 of 5

A pre-mortem is a powerful business technique where you take a leap into a future where your project has failed and you discuss where it went wrong. It helps teams identify potential issues and develop solutions before the project has launched. It involves critical thinking and some degree of creativity. But it can also generate some insights that in extreme cases can stop you from working on your project any further. Using ChatGPT for pre-mortems is an very low cost method of doing this without the need to convene any management meetings

Using ChatGPT for Pre-mortems

ChatGPT-4, the latest iteration (as of April 2023) of OpenAI’s powerful language model, is an invaluable business asset that can help reduce project management disasters. By using the right prompts, project teams can simulate failures before a project has started and use the analysis to identify and proactively mitigate potential risks. This method not only saves time and resources but also fosters a wider business culture of proactive problem solving.

Example Pre-mortem Prompt 1 – Product launch

“Assume that our new product launch has been a failure. The product was designed to do x and we developed it because we thought it would sell profitably in the y market. List the top 5 reasons why this might have occurred and suggest ways to address each of these issues.”

Why this works: This prompt encourages ChatGPT-4 to analyze and generate potential reasons for failure, helping the team identify potential risks and their corresponding solutions. By addressing the top 5 reasons, the model provides a focused analysis, ensuring that the most critical aspects are considered. Additionally, the prompt asks for ways to address each issue, allowing teams to develop preemptive strategies for success.

You can also ask ChatGPT to rank the reasons for failure in terms of likelihood, cost impact and so on. Use your description of what the product does to give ChatGPT as much background information as you can. Ask it follow up questions too.

Example Pre-mortem Prompt 2 – Marketing campaign

Prompt: “Imagine our marketing campaign for our new product x failed to achieve the goals we set in terms of sales and customer engagement. Our marketing campaign consisted of social media promotion, geo-targeted Google Ads and local mailshots. Describe four possible flaws in our campaign strategy and provide recommendations on how to improve each of them.”

Why it works: This prompt targets a specific area of the project, the marketing campaign, and directs ChatGPT-4 to evaluate potential shortcomings. Asking for a specific number of possible flaws helps ChatGPT to provide ran analysis that will have four separate elements which you can then rank. The specific request for recommendations for improvement will accelerate the process of finding solutions and help ideation.

Both these examples focus on product launches which is an important business process but there are many other areas where pre-mortems are helpful. Let’s look at one about recruitment.

Example Pre-mortem 3 – Recruitment

Prompt: “Our recent hiring process resulted in a high employee turnover rate within the first six months. Identify four factors that might have contributed to this outcome and suggest improvements for each factor in our hiring process.”

Why it works: This prompt focuses in on the hiring process and its potential impact on employee retention. By asking ChatGPT-4 to explore four contributing factors, the model is encouraged to delve into various aspects of the hiring process that might have led to a high turnover rate. This comprehensive examination helps the HR team pinpoint areas in need of improvement. By requesting suggestions for each factor, the team can develop a more effective hiring strategy to ensure they attract and retain the right talent.

The cost of doing pre-mortems

A typical business pre-mortem involves a meeting of your project team and a lot of discussion which takes time and therefore costs money. Of course, it can also save a lot of money down the line if it results in actionable outcomes that boost the chances of the project’s success. Using ChatGPT and similar tools to do a pre-mortem takes a few minutes and whilst not necessarily as effective as a full-blown pre-mortem management meeting, it can deliver results extremely cheaply. These results may deliver actionable outcomes on their own but just as significantly, they can be used as a business accelerant by acting as briefing notes for your own pre-mortem. Don’t forget too that you can ask ChatGPT to regenerate its response to come up with more ideas and that you can ask it to explain more about any aspects of its answers.

Conclusion

By integrating ChatGPT-4 into pre-mortem exercises, businesses can unlock innovative and efficient ways to identify and address potential project failures for negligible cost. By formulating targeted and focused prompts, teams can extract valuable and actionable insights from the AI, which enables them to make better decisions and reduce implementation risks.

Pre-mortem action point

Managers should do pre-mortems using AI tools like ChatGPT-4 as a matter of habit. Using ChatGPT for pre-mortems should be as habitualised as using Google for search used to be.

Prompting or “prompt engineering “is the skill of the year in 2023. A bad prompt that is poorly worded and gives no context can generate unhelpful responses from LLMs like ChatGPT. Except in trivial cases, the best prompts take some thought, fine-tuning and testing. How can businesses best deal with this? The answer is to create a Prompt Database.

A prompt database is a repository of prompts that have been tried, tested and proven to work well. The reason for having a prompt database is simply to save yourself from reinventing the wheel every time you need to use a prompt in any field. Given that well-crafted prompts can generate highly valuable responses but can take time to develop, it makes sense to re-use them. To do this, you need to find them first and at the moment, ChatGPT for example, makes finding prompts you’ve used hard, especially if you use it a lot.

So what factors do you need to think about when developing a prompt database?

Your prompts need to be organised, accessible, and useful. Here’s a step-by-step guide to help you set up a robust prompt database:

1. Define the Objective for your prompt database

Understand why you’re creating this database. Are you looking to create a knowledge base, store FAQs, document best practices, or something else? Your objective will determine the structure and features of your database.

2. Choose the right platform for your prompt database

Depending on your technical capabilities and resources, you can choose between:

Traditional relational databases like MySQL, PostgreSQL, or SQLite.
NoSQL databases like MongoDB if you expect a varied data structure.
Knowledge base platforms or CMS like Confluence, Notion, or Trello for less technical solutions.
Simpler solutions such as shared Google Docs or Google Sheets or files on Sharepoint.
A company Wiki such as https://www.mediawiki.org/wiki/MediaWiki

3. Design the Structure

For your prompt database to work effectively, you need to make it very easy for users to search and find prompts that are appropriate to their needs. To do this you need to think through how people perform searches. Do they use keywords, do they sort by functional area (marketing, finance, HR, R&D etc.) or do they search by author etc.?

You might consider the following fields in a prompt database:

Prompt title or question
Inputs required: what information will the user have to enter into the prompt?
Example response – not vital and this could need updating from time to time
Category topic
Keywords or tags
Author or creator
Creation date
Last updated date
Related prompts links – similar prompts or follow-up prompts
Usage notes such as known problems, hints, security considerations
Version notes
LLM model(s) it’s for eg. ChatGPT4, Bard, Claude 2 or an internal database etc.

Favorites lists for prompts

You also need to think about making prompt favourites lists available for individual users. For example, if your role is to provide monthly reports and data analysis, you may repeatedly use specific related prompts and you can speed up your access to them by having a shortcut to your favourites, just as you do with a browser.

4. Categorization

Assigning a category to a prompt can make it easier to find. Consider the following:

Broad categories (e.g., “Human Resources”, “Technical Support”, “Sales”, “General Management”, “Market Research” etc.)
Sub-categories within those (e.g., under “Technical Support” you might have “Software Issues”, “Hardware Issues”, etc.)
Tags for more granular categorization (e.g., “Windows”, “Mac”, “Printer”, etc.)

5. Design the Search Process:

Basic Search

Allows users to input a keyword or phrase and returns relevant prompts.

Advanced Search

Offers filters such as category, date range, author, etc.

Search Algorithm

Consider using algorithms that prioritize more recent or more frequently accessed prompts. Implementing fuzzy search can help catch misspellings or alternative phrasings.

6. Input and Update Process

Decide who can add or update prompts. Ensure there’s a review process in place to maintain quality. Consider version control to track changes.

7. User Interface

Make sure the database is user-friendly. Design a clean, intuitive interface. Offer options to sort and filter results. If possible, integrate a feedback system where users can suggest improvements or report inaccuracies.

8. Maintenance

Regularly review and update the database to ensure its relevancy. Remove outdated prompts and add new ones as needed. Assign a formal role to this task and develop suitable procedures.

9. Analytics

Track how often each prompt is viewed, which search terms are used most often, etc. This data can help refine and improve the database over time.

10. Access Control

Determine who can view, edit, or add to the database. Implement user roles and permissions. Ensure data security and confidentiality, especially if the database contains sensitive information.

11. Backup and Recovery

Ensure that the database is regularly backed up. Have a recovery plan in case of data loss.

12. Training

Train your staff on how to use the database efficiently. Offer guidelines on how to add or modify prompts to maintain consistency.

13. Iteration

Based on feedback and usage patterns, continuously refine and improve your database. Regularly revisit its structure, search algorithms, and user interface.

Much of the above applies to medium to large businesses. For small businesses, a simple shared document would be adequate provided it’s searchable. Some knowledge management tools such as Notion, Roam, Trello would work well or indeed a Google Doc.

In summary, setting up a company prompt database requires a clear understanding of the objective, careful design, and regular maintenance. However, don’t let the task of setting up a prompt database deter you from starting to record prompts you have used that work well. You can add them later.