• Thousands of fake FIFA domains are already waiting for desperate football fans
• Fraudsters cloned FIFA’s login system with near-perfect visual accuracy for credential theft
• Facebook advertisements are driving victims directly into a large-scale World Cup ticket scam

Over six million fans will fill stadiums across the U.S., Canada, and Mexico when the 2026 FIFA World Cup tournament kicks off in June.

The sheer scale of ticket demand has created ideal conditions for sophisticated fraud operations.

As enterprise AI agents move into production, organizations are confronting a growing reliability problem. Many teams are discovering that LLM performance alone does not determine whether agents succeed in production. Long-running AI workflows must survive crashes, preserve state, recover from failures, manage inference costs, and coordinate across APIs, tools, and enterprise systems.

After a first wave focused on rapid deployment, organizations now need to revisit those first-generation implementations, and redesign early agent architectures around workflow orchestration, observability, governance, and recovery, said Preeti Somal, Senior VP Engineering at Temporal Technologies, during the latest AI Impact Series event in New York.

“We do have a lot of customers that come to us where they’re building version 2.0 of the same agent,” Somal said. “They had to move really fast, but they didn’t take care of the plumbing. Things crash and burn, and then they’re back to rebuilding with the reliable foundation.”

For workflow orchestration company Temporal, whose infrastructure predates the current wave of agentic AI, the shift reflects a broader enterprise realization: production AI systems require durable execution, state management, visibility into workflows, and mechanisms to recover when models or downstream systems fail.

Agentic AI has supercharged familiar engineering problems

“These patterns aren’t necessarily new,” Somal said. ” AI just supercharges them.”

Agentic systems introduce additional complexity because they often involve long-running, multi-step processes spanning multiple services, models, APIs, and tools. A single workflow might call several large language models, access retrieval systems, trigger external applications, and manage state over hours or days. The engineering questions, Somal said, often emerge only after deployment.

“People will write agents but haven’t thought about what happens if the agent crashes,” she said. “Am I going to need to run the entire agent flow again?”

For enterprises operating under cost constraints, the answer matters. Restarting workflows after failures can multiply inference expenses, increase latency, and create poor customer experiences.

Somal compared the current moment to an earlier period in enterprise cloud adoption when organizations went straight to migrating workloads before considering that they needed to redesign underlying architectures if they wanted these workloads to weather the long-term.

“This rush to do AI in a world where you haven’t even modernized your application reminds me a little bit of that lift-and-shift that happened in the cloud,” she said. “Everybody realized you’re spending more money on cloud and we haven’t gotten value there.”

Why long-running agents force a new architecture

Enterprise workflows increasingly involve agents executing over long windows, sometimes spanning many hours while interacting with tools and systems. Reliability challenges compound when workflows persist over time, and it impacts both state and memory, two ideas that are often treated interchangeably in AI conversations.

State concerns workflow execution. It includes where an agent is in a process, which actions have already completed, and where recovery should resume after failure. Memory or context captures information an agent carries forward across interactions or tasks.

“The state of the agent is around what step and what actions have been performed, and if something crashes, where do you want to recover from, versus the context and memory piece,” Somal explained.

That distinction becomes increasingly important when enterprises begin moving beyond simple chatbot interactions toward longer-running business processes. Somal pointed to a healthcare example involving customer Abridge, where workflows process physician visits through multiple stages, including audio processing, summarization, model calls, and after-visit generation.

“There’s not just one piece to that flow,” Somal said. “Taking videos and slicing that, taking summaries, calling the LLMs, generating the after-visit summary, all of that is being orchestrated.”

The implication for enterprises is that successful agents increasingly depend on systems that can survive interruptions, coordinate across services, and maintain continuity over time.

The rise of the deterministic spine

A useful framework for enterprise AI design is the deterministic spine, Somal said, which is how they think about Temporal’s role.

“It is denoting the path you want to take,” she said. “It is calling the brain, but if the brain doesn’t respond, it will call it again. If the brain responds but the next step is going to fail, it will pick up from where that failure happened.”

In this framing, the language model acts as a probabilistic system producing variable outputs, while orchestration software maintains execution reliability around it. And the concept matters because enterprise systems increasingly require consistency even when models remain non-deterministic. A procurement workflow, healthcare summary, customer support escalation, or compliance process cannot simply fail silently because a model call timed out or an external dependency crashed.

“What you care most about is making sure that you can recover and that you’re not paying the token tax if something goes wrong,” Somal said.

Reliability, visibility, and the economics of token spend

As enterprise leaders evaluate AI ROI, cost visibility has become a growing concern. Long-running agents frequently make multiple model calls across complex workflows, which can create opaque spending patterns. Somal described one operational advantage of orchestration as visibility into where costs accumulate. Because workflows are observable step-by-step, teams can see where tokens are being consumed across an agent process.

“You’ve got visibility into that entire flow in a single pane of glass,” she said. “You can now see where you’re spending the tokens in an agent that is multiple steps and calling multiple different systems.”

Workflow recovery also shapes cost efficiency. Without durable orchestration, a late-stage failure can force organizations to rerun an entire process from the beginning, including all prior model calls. Somal said systems designed around recovery can resume execution from the point of interruption.

“You pick up from where the crash happened,” she said. “We save you the cost of running the agent from step one again.”

Enterprises need to build paved paths and enlist partner expertise

Governance concerns are another emerging pattern as agentic AI takes hold. Rather than adopting fully managed agent systems wholesale, Somal said enterprises increasingly want standardized internal frameworks that provide guardrails while preserving flexibility, and implementing necessary features like governance controls, model selection policies, identity systems, cost management, and observability.

“The enterprises are looking at building these paved paths,” she said. “Taking something off the shelf is maybe not going to work because there are all of these other requirements.”

As organizations revisit first-generation deployments, challenges like this increasingly look less like a model problem and more like a systems engineering problem, and Temporal is positioned to help enterprises take this next step in part because for many organizations, it already existed as part of broader modernization programs before AI became a strategic priority.

“Temporal is already in the enterprise,” Somal said. “Taking that and extending that to AI and agent platforms feels very natural.”

We spotted the Aceii One while wandering the halls at Beyond Expo 2026, and it’s hard to slot it neatly into the usual “ball machine” category.

The Aceii One positions itself as a smart tennis partner rather than a feeding device, combining ball launching, AI vision tracking, coaching tools, and gamified training modes into a single mobile platform. The pitch is ambitious: replace predictable drills with something closer to a live rally that adapts to your level.

At the core is a dual-stage launch system that fires balls at intervals of up to 0.5 seconds, with speeds up to 80 mph (129 km/h). That alone puts it in serious training territory, but the differentiator is how it behaves between shots.

Thanks to its vertical dual-camera vision system, Aceii One tracks both player movement and ball trajectory in real time. It claims detection of shots up to 130 mph, using 1080p cameras and a 100° field of view. In practice, this lets it reposition, adjust feeds, and simulate rally patterns instead of just firing fixed sequences.

At 620 million monthly users, calling a frontier model for every image recommendation isn’t a strategy — it’s a bill. Pinterest CTO Matt Madrigal solved it by gutting Qwen3-VL’s vision layer and rebuilding it with proprietary embeddings, cutting costs 90% and boosting accuracy 30%.

Madrigal’s team has been heavily investing in customizing open-source models “foundationally in-house.”

“If you’ve got really unique data that you can then fine-tune an open source model with, data quality will, frankly, outweigh or overcome model size,” Madrigal explained in a recent VB Beyond the Pilot podcast. 

How Pinterest customized Qwen for visual discovery

Pinterest, which has around 620 million monthly active users, has long applied open source models for visual search and discovery, going back to Google’s BERT and OpenAI’s CLIP. The company fine-tuned its own Pin CLIP on the latter, incorporating proprietary visual embeddings and image metadata. 

Pinterest’s conversational shopping assistant, Navigator 1, was built on Qwen3-VL and customized in “pretty significant” ways. Madrigal’s team essentially “ripped out” Qwen’s vision encoder layer and fine-tuned the model on proprietary multimodal embeddings. This has allowed them to capture metadata around pins and images that can then be precomputed offline and regularly retrained on new information to deliver personalized experiences. 

“Open-source models, especially with open Apache licenses where you can truly tweak a lot of open weights and customize for unique use cases — that’s where we’ve found open source to be so powerful for us,” Madrigal said. 

Bringing their own embeddings allows his team to gain context around metadata, pins, and images; also, notably, the model performs better at runtime and inference. Without these embeddings, devs would have to call and encode each image returned at runtime, one at a time. That results in a latency “20 times worse” from an inference perspective, Madrigal said. 

“If it’s something that’s going to be critical for our end users, that’s going to drive engagement, that will have to scale to over 600 million monthly active users, we’re going to either probably build it or we’re going to leverage open source and customize the heck out of it,” he said. 

How a taste graph captures evolving interests

To guide users from inspiration to purchase, Madrigal’s team built a “taste graph”: a dynamic representation of what individual users actually like, not just what they click on. “It’s this representation of billions of people’s evolving tastes,” he said. 

People go to Google or other search engines when they have a clear picture of what they want; Pinterest is for when they’re still in the discovery phase, Madrigal said. Pinterest’s goal is to encourage “lateral exploration” and transform discovery to intent (that is, clicking through ads or making purchases). 

Under the hood, the architecture combines a graph structure with representational learning. User embeddings capture a user’s evolving tastes. These are constantly updated based on activity and new content and signals. “It’s not a social graph,” Madrigal said. “It’s much more of a preference graph: What’s going to inspire you? What are you trying to do next?” 

For instance, one user may be into mid-century modern designs; another may prefer a Nantucket aesthetic. Those preferences will be captured in user embeddings, and the taste graph will deliver up specific, relevant products as a result. 

“You go from the upper funnel, inspiration discovery, all the way through lower funnel intent,” Madrigal said. 

Listen to the full podcast to hear more about:

• How Pinterest uses sandboxes to encourage creativity in a way that is secure and contained; 

• Why a continuous feedback loop can prevent visual AI slop; 

• The importance of constant benchmarking to gauge user engagement, performance, latency, and other factors. 

You can also listen and subscribe to Beyond the Pilot on Spotify, Apple or wherever you get your podcasts.

These days, it’s not uncommon for phones to share two big selling points: a partnership with a trusted photography brand and flashy AI features. The Xiaomi 17T Pro, launched this week in Vienna, is no different, boasting Leica-tuned cameras and fresh new AI skills from Google‘s text-to-video tool, Gemini Omni.

Of course, Leica is a storied brand with 157 years of history — so how does Omni’s presence on the Xiaomi 17T Pro sit with this photography heritage?

At a post-launch roundtable attended by TechRadar, the German camera giant — which has been collaborating with Xiaomi since 2022 — shared its take on the utility of generative AI, and its remarks were decidedly diplomatic.

For context, at the launch itself, Google made a cameo appearance to reintroduce Gemini Omni, which debuted at Google I/O 2026 earlier this month and is available on compatible Android phones, including the Xiaomi 17T series.

Latest Videos From