#agentic-ai

#agentic-ai

We are going to chat about architecting systems with agentic AI. What's today's topic? Today's topic is agentic AI that many consider even a buzzword in software architecture. What does it really mean for senior practitioners that have to build today's production system? Panelists will discuss what makes AI agentic and how it differs from traditional AI implementation. My name is Renato Losio.

Agentic AI has become a hot topic amongst software developers in recent months. As usage of LLMs has become increasingly popular, many developers are switching to agentic AI services to build projects. One point of contention with agentic AI is that productivity is always limited without proper context. Solid context is crucial in streamlining agentic AI tools, as it guards against things like hallucinations and inefficiencies with software development.

GitHub Copilot app modernization now is generally available via agentic AI tools for Java and .NET, Github said. For both platforms, the intentions are to help modernize applications and move them to the Azure cloud. In a blog post on September 23, GitHub said that developers using Copilot can access applications, apply code transformations, containerize services, and patch builds, all in days rather than months.

Clinch, the agentic AI platform for omnichannel campaign orchestration, today (25th September 2025) announced the appointment of Tariq Hassan, former chief marketing and customer experience officer of McDonald's, to its global Advisory Board. Hassan, one of the industry's most recognised marketing leaders, brings more than two decades of global marketing, communications, and brand leadership experience to Clinch. Most recently, he led all marketing efforts at McDonald's USA, including digital, media, CRM, brand content and engagement, and consumer insights.

AI agents can be security issues waiting to happen. To ensure they comply with company policy, Nametag is enlisting the help of Okta. Okta research shows how widespread AI agents already are: 91 percent of organizations use them today. According to this research, only 10 percent of these companies have a mature security strategy in this area. That is a considerable risk.

AI agents - autonomous, task-specific systems designed to perform functions with little or no human intervention - are gaining traction in the healthcare world. The industry is under massive pressure to lower costs without compromising care quality, and health tech experts believe agentic AI could be a scalable solution that can help with this arduous goal. However, this AI category comes with greater risk than that of its AI predecessors, according to one cybersecurity and data privacy attorney.

AppZen is the AI-native platform for autonomous finance. Powered by proprietary ZenLM models and the Mastermind AI Automation Platform, AppZen's domain-trained AI Agents streamline end-to-end workflows across T&E, accounts payable, and corporate card programs, transforming finance teams. More than 500 global enterprises, including over 65 of the Fortune 500, rely on AppZen to automate transaction processing and reduce costs, delivering over $2 billion in savings and enabling finance teams to reallocate up to two-thirds of their manual workload to higher-value activities.

Commerce is on the brink of profound change, and PayPal and Google's recent announcement of a multiyear strategic partnership to advance various commerce solutions is evidence of that.

As a self-admitted commerce nerd who has reported closely on e-commerce since 2013 (in tons of articles, yes, but also in book, podcast, and onstage interview form), the rise of companies big and small that are using generative and agentic AI systems to innovate in and around consumer purchasing decisions has been a breath of fresh air. Today, even as a naturally skeptical person allergic to BS, I feel like the sector is on the verge of legitimate widespread disruption.

Security researchers employed ChatGPT as a co-conspirator to plunder sensitive data from Gmail inboxes without alerting users. The vulnerability exploited has been closed by OpenAI but it's a good example of the new risks inherent to agentic AI. The heist, called Shadow Leak and published by security firm Radware this week, relied on a quirk in how AI agents work.

Perplexity's Comet AI browser is meant to act as an AI assistant that works alongside you every step of your browsing experience, even taking actions for you, such as managing your accounts. This makes keeping your credentials secure more important than ever, and Perplexity's new partnership with 1Password aims to do just that. Instantly log in to your saved accounts On Wednesday, the two companies announced their partnership, which integrates 1Password directly into Comet.

The rise of ChatGPT and Perplexity is already starting to chip away at Google's search dominance. Through agentic AI and conversational search, these new browsers promise more personalization and a redefined search experience. Whether they'll truly pull users away from traditional search is still unclear - but brands can't wait to protect visibility. From what we know, both Perplexity's and OpenAI's browsers will focus on personalization, context-aware answers, and agentic AI to deliver more intuitive search experiences.

Basic chatbots get much of the publicity associated with modern AI platforms, but they have limited use cases, providing a simple natural language interface to search tools. It's certainly useful, provided you implement fine-tuning and grounding in your own data, but it is still best thought of as an extension of existing search tools. AI has other uses: embedding the technology inside enterprise IT stacks, providing advanced filtering and summarization, using it for translation and voice recognition, and simplifying interactions through natural language.

It's a very broad question. But, to start, I think it's important to point out that this is in some respects an entirely new form of business logic and a new form of computing. And so, the first question becomes, if agentic systems are reasoning models coupled with agents that perform tasks by leveraging reasoning models, as well as different tools that have been allocated to them to help them accomplish their tasks ... these models need to run on very high-performance machinery.

We have now done about a million and a half conversations with our customers (through the agentic layer) and at the same time ... a million and half conversations also happened through our support agents during that same period. The SEASAT scores were about the same, which was stunning and also I was able to rebalance my headcount on my support - I've reduced it from 9,000 heads to about 5,000 because I need less heads.

Virginia Gov. Glenn Youngkin turned heads last month when he signed an executive order mandating that the commonwealth must use agentic artificial intelligence to further streamline its regulations. The Office of Regulatory Management has already achieved a 26.8% streamlining or reduction of the commonwealth's regulatory requirements, and Youngkin said in a statement that agentic AI "will push this effort further."

Agentic AI programming is what happens when coding assistants stop acting like autocomplete and start collaborating on real work. In this episode, we cut through the hype and incentives to define "agentic," then get hands-on with how tools like Cursor, Claude Code, and LangChain actually behave inside an established codebase. Our guest, Matt Makai, now VP of Developer Relations at DigitalOcean, creator of Full Stack Python and Plushcap, shares hard-won tactics.