Some practical tips for using Ai from Section CEO, Greg Shove

Some practical tips for using Ai from Section CEO, Greg Shove

There has been a huge amount of noise around Ai since ChatGPT started getting mainstream traction about two years ago. Every tech platform, consulting firm and agency seems to be touting Ai as a silver bullet to whatever problem a customer might have. There’s an incredible level of hyperbole that can make the whole area seem like snake oil. But when used in some specific ways, Ai can really increase the efficiency of certain tasks.

Greg Shove, CEO of Section had some great practical tips on the No Mercy / No Malice blog this week that show you how Ai can be used to really help you in some specific areas.

  1. Ask for ideas, not answers. If you ask for an answer, it will give you one. As a thought partner, it’s better equipped to give you ideas, feedback, and other things to consider. Try to maintain an open-ended conversation that keeps evolving, rather than rushing to an answer.
  2. More context is better. The trick is to give AI enough context to start making associations. Having a “generic” conversation will give you generic output. Give it enough specific information to help it create specific responses and then take the conversation in different directions.
  3. Ask AI to run your problems through decision frameworks. Massive amounts of knowledge are stored in LLMs, so don’t hesitate to have the model explain concepts to you. Ask, “How would a CFO tackle this problem?” or “What are two frameworks CEOs have used to think about this?” Then have a conversation with the AI unpacking these answers.
  4. Ask it to adopt a persona. “If Brian Chesky and Elon Musk were co-CEOs, what remote work policies would they put in place for the management team?” That’s a question Google could never answer, but an LLM will respond to without hesitation.
  5. Make the AI explain and defend its ideas. Say, “Why did you give that answer?” “Are there any other options you can offer?” “What might be a weakness in the approach you’re suggesting?”
  6. Give it your data. Upload your PDFs — business plans, strategy memos, household budgets — and talk to the AI about your unique data and situation. If you’re concerned about privacy, then go to data controls in your GPT settings and turn off its ability to train on your data.

Greg uses a great analogy of Ai as a superpowered management consultant:

“McKinsey consultants are smart, credentialed people. But they can only present you with one worldview that has a series of biases including how to create problems only they can solve with additional engagements, and what will please the person who has a budget for follow-on engagements. AI is a nearly free expert with 24/7 availability, a staggering range of expertise, and — most importantly — inhumanity. It doesn’t care whether you like it, hire it, or find it attractive, it just wants to address the task/query at hand. And it’s getting better.”

Posted by Rob in Tech
Speaking at this month’s UK Sitecore User Group in London

Speaking at this month’s UK Sitecore User Group in London

I was delighted to speak at this month’s UK Sitecore User Group in London, hosted at our very own Sagittarius HQ in Shoreditch.

It was a pleasure to welcome the London Sitecore community to our home patch for another catch-up, this time focusing on XM Cloud implementation and Content Hub with the wonderful Dan Vella from Sitecore and Peter Clisby from SoftServe. The evening was MC’d by Remarkable Group CEO, Nick Towers.

Find out more about the event here.

Posted by Rob in Sitecore, Speaking
The genius of the historical framing of the Moleskin notebook

The genius of the historical framing of the Moleskin notebook

A great piece of copy can be foundational for a brand giving it extra heft and a context in the grand scheme of things. Moleskin notebooks are a great example of this.

With each notebook comes a small piece of paper lodged in the folder at the back that sets the scene for how it fits in with a history of creativity.

The Moleskine is an exact reproduction of the legendary notebook of Chatwin, Hemingway, Matisse. Anonymous custodian of an extraordinary tradition, the Moleskine is a distillation of function and an accumulator of emotions that releases its charge over time. From the original notebook a family of essential and trusted pocket books was born. Hard cover covered in moleskine, elastic closure, thread binding. Internal bellowed pocket in cardboard and canvas. Removable leaflet with the history of Moleskine. Format 9 x 14 cm.

After reading this, you’d be forgiven for thinking that the Moleskin company had been around for generations, providing the tools for creatives of the past to produce art and literature that is still around today.

Not so.

In my head, I have always associated the Moleskin brand with Hemmingway and the creatives of the Paris scene in the early Twentieth century. That’s where the brand ‘fits’.

It came as a bit of a shock to discover that the actual Moleskin company was founded in 1997 and simply based it’s product on a generic design from the past.

That bit of copy hidden in the back folder to be ‘discovered’ by the owner is doing a lot of heavy lifting. Like all good copy does.

Posted by Rob in Tech
The London tube station Ai experiment

The London tube station Ai experiment

James O’Malley has written a fantastic piece on the results of a recent Transport for London (TfL) experiment in using AI to improve safety and the passenger experience at the Willesden Green London Underground station.

While the technology was initially implemented with an eye on detecting fare evasion, the experiment has thrown up a host of potential added use cases like the below:

  • Track how crowds move through the station, which could be useful for managing capacity at rush hour or knowing where to deploy staff when there’s a football crowd passing through.
  • If someone steps foot on to the tracks or into an unauthorised areas of the station, the staff can receive an immediate alert.
  • If someone in a wheelchair passes through the station, they can be immediately flagged to staff, so that any assistance they need can be provided.
  • Alert staff if a person is sat on a bench for longer than ten minutes or if they were in the ticket hall for longer than 15 minutes, as it implies they may be lost or require help.

This could be a powerful tool for collecting statistical data and giving management a high-level view of what’s happening at a station, which can lead to improvements in both security and passenger welfare.

Posted by Rob in ai