Skip to main content

Can ChatGPT write your strategies?

Tired of spending months writing a strategy or paying thousands for someone else to? Can ChatGPT do it for free?

ChatGPT is, on the face of it, a website which you can ask questions that will provide answers in real time.

That’s hardly revolutionary, but behind it is a natural language processing (NLP) machine learning model that's been designed to understand your questions and provide detailed responses to them.

Again this isn't entirly new, in fact its current NLP is known as GPT-3 which means that there were two versions that came before. It is considered by some to be the most advanced NLP yet though, so much so that Microsoft will incorporate it into some versions of Teams soon.

The people behind ChatGPT (Open AI) freely admit it will sometimes provide incorrect answers, and I found this chart produced by HFSResearch really useful in explaining its limitations.


What this tells me is that we shouldn’t be relying on ChatGPT to provide exact answers, however it is useful for things that don't need to be precise.

So for example when I asked it to

“Create a transformation strategy for an English local authority

It replied
Assess current processes and systems: Conduct a thorough review of current processes, systems, and infrastructure to identify areas for improvement and areas where technology can be leveraged to streamline processes.

Develop a technology roadmap: Create a technology roadmap that outlines the steps and timeline for implementing new technologies and tools to support the authority's transformation goals.

Engage with stakeholders: Engage with key stakeholders, including employees, citizens, and partners, to understand their needs and gather feedback to inform the transformation strategy.

Prioritize initiatives: Based on the results of the assessment and stakeholder engagement, prioritize initiatives and allocate resources accordingly.

Implement new technologies: Roll out new technologies and systems, providing training and support to ensure successful adoption.

Monitor and evaluate progress: Regularly monitor and evaluate progress against the technology roadmap, making adjustments as needed, and sharing results and successes with stakeholders.

Continuously improve: Continuously seek ways to improve processes and systems, incorporating feedback from stakeholders and exploring new technologies as they emerge.

The first thing to note is this isn’t a strategy, it’s an short summary of one. So I thought I’d drill down into the first point above by asking:
How can I conduct a thorough review of current processes, systems, and infrastructure to identify areas for improvement and areas where technology can be leveraged to streamline processes.

 

To which it replied
Define the scope: Identify which processes and systems need to be reviewed.

Gather information: Collect data on current processes, systems, and infrastructure, including documentation, user manuals, and any other relevant information.

Identify pain points: Look for bottlenecks, inefficiencies, and areas where improvements can be made.

Engage stakeholders: Talk to employees and stakeholders to understand their experiences and perspectives on the current processes and systems.

Analyze the data: Evaluate the information collected and use it to identify opportunities for improvement.

Evaluate technology: Determine which technologies can be leveraged to streamline processes and improve efficiency.

Develop a plan: Based on the findings, develop a plan to make improvements to processes, systems, and infrastructure.

Implement changes: Put the plan into action, making changes and improvements to processes, systems, and infrastructure.

Monitor and adjust: Continuously monitor the changes made to ensure they are having the desired impact and adjust as necessary.

So we’re starting to get into the detail of creating a strategy. I could go on and ask it about the other individual points in the original response to populate more of our strategy, but you get the idea.

There are positives and negatives to this.

For example I can produce a draft strategy that looks professionally written in minutes. I have no issue with any of the points in the overview or subsequent response, and think they could form the outline of a credible transformation strategy.

The big downside is that the strategy isn’t tailored to your organisation as because it’s a generic response it can’t suggest outcomes specific to the needs of your organisation and its service users. Sure there will be things that every organisation going through a transformation programme needs to achieve, but especially for councils, each of which have different priorities set by their elected members, some things will be different.

Following on from that, without outcomes specific to your organisation it can’t create a delivery plan to then achieve them and if you happen to think "the strategy is delivery", then it seems ChatGPT can't really help you with creating a plan for that.

So, can ChatGPT really write your strategy?

No, but it is a useful tool to create an initial draft which you can then tailor to your organisation, and if you’re buying in services from outside your organisation to help create a strategy, I would certainly be using ChatGPT to check that they’re not doing the same.

You can sign up to use ChatGPT here

Comments

Post a Comment

Popular posts from this blog

Digital best practice checklist

This week I finished the draft of a digital best practice check-list. It's not digital strategy, in fact I'm increasingly thinking organisations don't need a digital strategy, they need a delivery strategy. My draft has check-list of seven questions and recommendations, with one overall recommendation regarding best practice for delivering digital. Ideally it would be incorporated into a wider service and information delivery strategy. Below I've omitted the bulk of the content, the reasoning behind arriving at the recommendation from the question because it's still in draft, but here are the seven questions and eight recommendations: 1. Is the council properly promoting its digital services and content, to reduce avoidable contact? Recommendation: Establish a “digital first” ethos to the promotion of services and better targeting what, when and where they're promoted. 2. Are the digital services the council offers, especially where the design and
5 comments
Read more

Carl's Conundrum of Internal Influence

I'm writing this partly as a reply to an excellent piece that Carl Haggerty published about the disconnect between internal and external influence and partly due to various conversations over the past month about how to make using tools like collaboration platform  Pipeline common practice. This isn't really about Carl though, or Devon County Council, or any other council specifically, it's more a comment on the influence of digital teams in local governments, or lack of, and how to resolve this. So here's the question that prompted this piece. How can someone who's been recognised nationally for their work, first by winning the Guardian's Leadership Excellent Award and who has more recently been placed in the top 100 of the Local Government Chronicle's most influential people in local government , "sometimes feel rather isolated and disconnected to the power and influence internally". First, let's consider whether is this a problem to
6 comments
Read more

Pipeline Alpha

In September 2014, officers from 25 councils met in Guildford to discuss a platform to enable collaboration across Local Government. A "Kickstarter for local government" is the missing part to Makers Project Teams , a concept to enable collaborative working across different organisations put forward by LGMakers the design and development strand of LocalGov Digital . Based on the user needs captured at the event, LGMakers created collaboration platform Pipeline and by October people from over 50 councils had signed up . Pipeline is an Alpha, a prototype set up to evaluate how a Kickstarter for councils might work. It is a working site though, and is being used as the platform it is eventually intended to be, at present without some of finer features a live offer might have. So what have I've learnt in the eight months since we launched Pipeline? There's a strong desire to collaborate  LocalGov Digital isn't a funded programme. I wrote about how much it
1 comment
Read more

Superfast highways

You may have seen this slide I put together to help explain digital transformation This week we launched a new beta service to report speeding traffic. It looks fairly simple but to give you an idea of what's happening in the background I thought it might be useful to show you the before and after. So here's the before and as you can see it's completely a manual process. Stuff might be recorded electronically but it takes someone to do something seven time to make the process work and send it to the parish or the district. Here's the after What this doesn't tell you is that it's basing whether the request is for the parish or district on three questions. It's also doing a spatial look up to find the parish and returning the parish clerk details using the Modern.Gov API. Because these are already part of our platform this is data that we currently maintain, so there's no additional work to keep this up to date and we've reduced the h
1 comment
Read more

Defining transformation to a wider audience

For the past month I've been putting together a paper on the next steps of digital transformation, for the organisation I work for. I'm proposing we look at two capabilities and two business areas, and if approved I'll be writing more about it. It's been a great exercise in gathering my thoughts and helping me to define digital transformation to a wider audience and how it fits into the bigger picture of service improvement. Here's some of the stuff I've learnt or had affirmed: Transformation, digital or not, starts with understanding the needs of the user through research. This should be obvious, but in local government too often I've seen "build it and they will come" approach applied. It's unlikely a commercial operation would launch a new product without first researching the market, so why would a digital service be any difference? A couple of years ago I wrote how the phrase "digital transformation" was hindering digit
1 comment
Read more