Agentforce | Read the latest blogs, news and views from Infomentum.

Last night’s Digital Revolution Awards brought together organisations tackling real, practical challenges with technology. For our team, it was a brilliant evening to be part of.

It was great to reconnect with familiar faces, meet some new ones, and see first-hand the impact being made across so many different sectors. Moments like that are a good reminder of how much meaningful work is happening in this space.

And while we’ll try to stay modest about it… it made the night all the more special to be named winners of the ‘Excellence in Salesforce’ award for 2026!

As more organisations explore how AI can actually work inside Salesforce, Agentforce is quickly becoming a favourite. Unlike generic AI chatbots, Agentforce uses an organisation’s own internal knowledge base, including files, CRM data, case records, and process logic, to deliver answers that are accurate, contextual, and trusted. This allows you to build conversational experiences that feel natural to users while drawing on the full depth of your operational knowledge.

For this article, I wanted to go beyond the theory.

Writing MUnit tests is something I do regularly as part of my MuleSoft development work, and like many engineers, I'm always looking for ways to work more efficiently without cutting corners. So when AI-powered features started making their way into the MuleSoft ecosystem, I was genuinely curious to see what they could do in practice. Test creation felt like the natural place to start, as it's a workflow I know well, which meant I could quickly spot where the tooling added value and where it still needed work.

One of those tools is the MuleSoft Dev Agent, which introduces a new way to create tests, using natural language prompts to generate MUnit tests directly from your MuleSoft projects. So in this walkthrough, we put the Dev Agent straight to work on a simple Hello World API and see how far it can take us, from generating MUnit tests in seconds to revealing where it really adds value.

Introducing AI-driven solutions like Agentforce into UK policing is not a decision to take lightly. These powerful technologies have the potential to completely transform the way forces operate, from back-office efficiency through to frontline support. But with this power also comes new risks, particularly in how sensitive personal data is processed, stored, and interpreted. While these risks are real, the potential to deliver faster, fairer, and more effective policing outcomes makes their careful navigation worthwhile.

In an environment governed by high standards of public accountability, ethical scrutiny, and strict legal obligations under the UK GDPR, Data Protection Act 2018, and Law Enforcement Processing provisions, a Data Protection Impact Assessment (DPIA) is not just a formality - it's essential. It provides a defensible framework for making informed decisions, protecting officers and the public alike.

Every public sector leader I speak to wants to unlock the promise of artificial intelligence (AI). The ambition is clear: to deliver services faster, give staff back precious time, and improve experiences for citizens. The challenge is that budgets are tight, scrutiny is high, and no one wants to waste money on the wrong investment.

That tension often leads to the question… how much should we actually spend on AI?

When people reach out to the police, it’s often at a moment of vulnerability, when something has happened that has shaken their sense of safety and left them unsure what to do next. They may feel anxious, overwhelmed, or uncertain about whether they are using the right channel, sharing the right information, or even raising the right issue at all. At the same time, forces are managing rising volumes of calls, messages, and digital contact under sustained pressure, yet every interaction still represents a person looking for reassurance and support. Meeting these moments in a way that feels timely, confident, and compassionate has become one of the most important challenges facing UK policing today.

But a more supportive, intelligent approach is beginning to take shape.

Salesforce events always bring a unique buzz. Whether it’s Dreamforce, World Tour or a specialist showcase, there’s an energy in the room that reminds you how fast the ecosystem moves and how much innovation is happening behind the scenes.

The Agentforce World Tour 2025 at ExCeL London carried that same momentum. Crowds, conversations and excitement aside, the real draw was seeing just how quickly Agentforce is evolving and what that means for both technical and business teams alike.

As a developer, I went in hoping for real implementation stories, deeper technical insight and the latest updates on Agentforce Vibes. The day delivered on all of that. I left with useful takeaways, fresh ideas to test and a stronger sense of where enterprise AI is heading next. To help set the scene and share what the day revealed, I've put together some key moments that stood out.

When people talk about artificial intelligence (AI) today, the conversation often drifts into mystique. We hear phrases like 'thinking machines' or 'AI replacing humans,' as if a spark of magic has suddenly entered our world. But history shows a different story: every wave of automation, whether industrial, digital, or now intelligent, has been shaped not by magic, but by clear thinking, human analysis and precise understanding of what needed to be achieved.

To see this, it helps to trace automation through three phases: achieve what I achieve, do what I do, and think what I think.

The past few weeks at Infomentum HQ have been nothing short of amazing. New projects launched, fresh qualifications earned (more to come on this!), and to top it all off - we’ve been named the winner of a 2025 Salesforce Partner Innovation Award in the Public Sector and Government category. This award celebrates our work with UK police forces to transform victim support through smarter, more connected technology. It’s safe to say the team couldn’t be prouder!

I’m sure we are all aware that AI is advancing at an unprecedented rate. With every breakthrough comes both a new set of opportunities and a group of risks. While the potential of AI is huge, the reality is clear: without security and compliance at its core, innovation can quickly turn into exposure.

A recent discovery of a vulnerability in Salesforce's Agentforce is a timely reminder that even the most established platforms aren't invincible. And whilst Salesforce quickly resolved the issue, it raises important questions about how we manage AI responsibly, protect sensitive data, and keep trust at the heart of every solution.