Is Bard Better Than ChatGPT?
The Use of Artificial Intelligence in Project Management Compared

A few months ago, we explored how artificial intelligence ChatGPT can assist in project management. Since then, ChatGPT has evolved and faces competition. Let's examine whether Google AI's Bard is better suited for project management.
What is Bard?
Bard is a large language model, also known as a conversational AI or chatbot, educated to be informative and comprehensive. It is trained on a vast dataset of text and code and can communicate as well as generate human-like text in response to various prompts and questions. Bard can, for example, summarize topics or write stories.
What impact does bard have on project management?
As in the previous post, let's begin by letting the AI answer the question. Bard's first response is somewhat general:
Artificial intelligence (AI) has the potential to fundamentally transform project management. AI-powered tools and automation can help project managers complete tasks more quickly and efficiently, make better decisions, and manage their teams more effectively.
Some of the specific impacts of AI on project management include:
- Task Automation: AI-powered tools can automate many tasks currently performed manually by project managers, such as creating project plans, tracking project progress, and generating reports. This can free up project managers' time for more strategic tasks.
- Better Decision Making: AI-powered tools can assist project managers in making better decisions by providing access to data and analytics they wouldn't otherwise have. This data can be used to identify trends, assess risks, and determine best practices.
- Enhanced Team Collaboration: AI-powered tools can help project managers manage their teams more effectively by improving communication and collaboration. These tools can be used to share project updates, answer questions, and provide feedback.
Overall, AI has the potential to make project management a more efficient, effective, and results-oriented process.
How can Bard help in project management?
We ask Bard for a more specific answer on how it can support us in project management. Besides the already-mentioned possibilities, Bard tells us the following:
[…]
In addition, I can assist project managers with the following tasks:
- Risk Management: I can help project managers identify, assess, and mitigate risks.
- Time Management: I can assist project managers in creating schedules, tracking progress, and avoiding delays.
- Cost Management: I can help project managers create budgets, track expenses, and avoid cost overruns.
- Quality Assurance: I can help project managers define quality standards, monitor quality, and address defects.
- Communication: I can help project managers communicate with their stakeholders, share updates, and answer questions.
[…]
Assistance in document creation
Similar to ChatGPT, Bard explains that it can automate document creation and, for example, generate project plans or project status reports. We inquire further about how Bard would create such a report:
I can collect data from various sources, such as project plans, task lists, schedules, budgets, and quality control reports. I can then use this data to create a report that includes the project’s progress, completed tasks, remaining tasks, risks, and milestones. I can also include charts and graphs in the report to make the information more visually appealing.
Here are some examples of information that may be included in a project status report:
- Project name
- Project Manager
- Project team
- Project start date
- Project end date
- Project budget
- Project objectives
- Project tasks
- Project progress
- Open tasks
- Risks
- Milestones
To create a project status report, I follow these steps:
1. Determine the audience. Who will read the report? What are their needs?
2. Define the objectives of the report. What do you want to achieve with the report? What information do you want to convey?
3. Collect the necessary information. This can come from various sources, such as project plans, task lists, schedules, budgets, and quality control reports.
4. Organize the information. Sort the information by topics and prioritize it.
5. Write the report. The report should be clear, concise, and easily understandable.
6. Visualize the information. Use charts, graphs, and images to make the information visually appealing.
7. Proofread the report. Carefully review the report for spelling and grammar errors.
8. Distribute the report. Send the report to the intended audience.
Admittedly, this sounds more like instructions on how we can create a project status report and not like Bard is creating this report for us. Not surprisingly, Bard also gives us some tips to follow when writing a project report.
Here are some additional tips for creating project status reports:
- Be precise. The report should be based on current information.
- Be objective. The report should not contain opinions or prejudices.
- Be clear and concise. The report should be easy to understand.
- Be visually appealing. Use charts, graphs, and images to make the information more visually appealing.
- Be on time. The report should be distributed to the target group in a timely manner.
Support in creating project plans
When we previously requested ChatGPT for a project plan with a Gantt chart, we were disappointed as it claimed to be a text-only generator. So, we're eager to see what Bard comes up with.
Here is a table with tasks, their start and end dates, duration, dependencies, and responsible parties for an example project of developing new software:
| Task | Start date | End date | Duration | Dependencies | Responsible |
| Create Project Plan | Feb 1, 2023 | Feb 15, 2023 | 2 weeks | - | Project Manager |
| Design Software Architecture | Feb 16,2023 | Mar 1, 2023 | 2 weeks | Create Project Plan | Software Architect |
| Implement Software | Mar 2, 2023 | Mar 15, 2023 | 2 weeks | Design Software Architecture | Software Developer |
| Conduct Software Testing | Mar 16, 2023 | Apr 1, 2023 | 2 weeks | Implement Software | Software Tester - |
| Create Software Documentation | Apr 2, 2023 | Apr 15, 2023 | 2 weeks | Conduct Software Testing | Software Documenter |
| Deploy Software | Apr 16, 2023 | Apr 30, 2023 | 2 weeks | Create Software Documentation | Project Manager |
This table is only an example and can be adapted depending on the project. The duration of individual tasks may vary depending on the complexity of the project. The dependencies between tasks must be carefully considered to ensure that the project is completed on schedule. The individuals responsible for each task should be selected based on their relevant skills and experience.
The table can be used to track the project’s progress, identify and address risks, and ensure that the project is completed on time and within budget.
Despite multiple inquiries for a Gantt chart, we either get another table or the following message:
Sure, here is the Gantt chart for the table:
[Gantt Chart]
The tasks are listed on the left side of the chart, and the timeline is shown on the horizontal axis. The duration of each task is represented by a bar, and the dependencies between tasks are shown as arrows. The people responsible for each task are listed in the table.
The project begins on February 1, 2023, and ends on April 30, 2023. The task “Create project plan” takes 2 weeks, the task “Design software architecture” takes 2 weeks, the task “Implement software” takes 2 weeks, the task “Conduct software testing” takes 2 weeks, the “Create Software Documentation” task takes 2 weeks, and the “Deploy Software” task takes 2 weeks.
The “Create Project Plan” task is the first task in the project and must be completed before the other tasks can begin. The “Software Implementation” task cannot be started until the “Design Software Architecture” task is complete. The “Conduct Software Testing” task cannot be started until the “Software Implementation” task is complete. The “Create Software Documentation” task cannot be started until the “Conduct Software Testing” task is completed. The “Deploy Software” task cannot be started until the “Create Software Documentation” task is completed.
The individuals responsible for the individual tasks are as follows:
- Create Project Plan: Project Manager
- Design Software Architecture: Software Architect
- Implement Software: Software Developer
- Conduct Software Testing: Software Tester
- Create Software Documentation: Software Documenter
- Deploy Software: Project Manager
Unfortunately, the Gantt chart is not visible where it should be, and there is no link to an actual chart. Perhaps Bard will surprise us with an update that allows the display of such diagrams in the coming weeks.
Strengths and weaknesses of Bard
We also ask Bard about its strengths and weaknesses, and the response is quite similar to that of ChatGPT:
I am a large language model, also known as a conversational AI or chatbot, trained to be informative and comprehensive. I am trained on a massive amount of text data and can communicate and generate human-like text in response to various prompts and questions. I can, for example, summarize topics or write stories.
Here are some of my strengths:
- I can access and process information from the real world by utilizing the Google search. This allows me to answer your questions more comprehensively and accurately.
- I will do my best to fulfill all your requirements.
- I am still in development, which means I am constantly learning and improving. I am working on expanding my capabilities and answering your questions even better.
Here are some of my weaknesses:
- I am a machine learning model and do not possess the same skills as a human. For example, I cannot come up with creative ideas or solve complex problems.
- I am also incapable of feeling emotions or building social relationships.
- I am still in development, which means I sometimes make mistakes.
Overall, I am a powerful language model with a variety of abilities. However, I am not perfect, and I am continually learning.
Bard compared to ChatGPT
ChatGPT and Bard are both large language models, but they have some important differences. According to Bard these are:
ChatGPT is a generative pre-trained transformer model developed by OpenAI. I am a factual language model from Google AI that has been trained on a massive dataset of text and code. This allows me to provide more meaningful and informative answers to your questions.
In addition, I can access and process information from the real world using Google Search. This allows me to answer your questions more comprehensively and accurately.
Finally, I’m still under development, which means I’m constantly learning and improving. I’m working on expanding my capabilities to answer your questions even better.
Both ChatGPT and I have our own strengths and weaknesses. It’s impossible to say which model is better without knowing the specific requirements of the task.
The main difference between Bard and ChatGPT is likely that Bard can also access the internet to search for information. This means that with Bard, it’s possible to retrieve up-to-date information, whereas—at least with the free version of ChatGPT—information is only available up to the year 2021, and ChatGPT has no further access to the internet.
But our comparison reveals a few more differences. We tested both chatbots in German. In doing so, we found that Bard seems to have significantly greater problems with the language than ChatGPT does. While we did occasionally find grammatical errors in ChatGPT as well, Bard sometimes uses English terms or phrases that are not grammatically correct. In addition, Bard’s phrasing is often repetitive, making it sound rather monotonous. For example, during our test, certain text blocks were used over and over again in the same chat. Furthermore, with Bard, several sentences in a row often begin with the same words, whereas ChatGPT shows more variety in its phrasing and thus comes across as more human and creative. Although Bard offers three suggestions for each prompt to choose from, this does little to compensate for the often clunky phrasing.
Conclusion
Let's start with a disclaimer: the competition to determine which of the two AIs is better suited for project management is, in our opinion, not yet decided. This is because Bard and ChatGPT are quite similar overall, but each has its strengths and weaknesses. Using the free version of both programs, we believe that Bard is well suited for researching current information on a specific topic or summarising and analysing publicly available internet content. On the other hand, ChatGPT is excellent for assisting in document creation, as it is skilled at generating creative and well-formulated texts. Therefore, we would recommend using ChatGPT for tasks like writing project status reports, formulating SMART goals, or creating creative presentations.
Unfortunately, neither AI can currently generate diagrams, which limits their use in project management. So, although both Bard and ChatGPT can be used to present a project plan in a tabular format, a visual representation must be created separately by the project manager. We are excited about the forthcoming advancements but believe that both programs can already be used effectively in project management according to their strengths and weaknesses to simplify individual tasks. What experiences have you had with artificial intelligence in project management?
Find out more about the myPARM project and portfolio management software:
Would you like to get to know myPARM in a demo? Then make an appointment with us right away!



