AI Exchange

AI Exchange June Ft. Cato Networks, Coralogix & WeBuild-AI

Thu, Jul 9 · 6:30 PM BST

Coralogix, Building 6, Devonshire Square, EC2M, London, GB

*The date for this event has now changed, and will take place on Thursday 9th July*

Join us on Thursday 9th July for our next AI Exchange event, hosted by Coralogix at their London HQ in Devonshire Square.

Cato Networks are applying AI to one of cybersecurity's most overlooked problems: the hidden risks buried within complex security policies. WeBuild-AI, kindly stepping in at short notice (again!) are using everyones favourite Simpsons character, Ralph Wiggum, to cut code afk, and why the human isn't going anywhere anytime soon.... Finally our hosts Coralogix are addressing a challenge many engineering teams are beginning to face: AI coding agents are becoming part of everyday development, but very few organisations have visibility into how they're actually performing.

As always, doors open at 6:30pm and talks start at 7pm sharp. We have another tight capacity for this event, so please RSVP as soon as you can to secure your space.

Agenda:

Lewis Isaac @ Coralogix
Who’s Watching the Agents? Observability for AI-Assisted Development

Code agents are already in your engineering workflow. The problem is that most organisations still have no visibility into what those agents are actually doing.
How many tokens are they consuming? How long are tasks taking? Are they introducing regressions? Are they measurably improving delivery, or just creating the feeling of progress? The gap between “we have AI tooling” and “we understand our AI tooling” is where most teams are stuck right now.

In this talk, I will show you how OpenTelemetry can be used to instrument code agent workflows end-to-end, and how Coralogix Code Agents Observability brings all of those signals -token usage, cost, task duration, and code quality impact - into a single view.

Bio: Our speaker will be Lewis Isaac, Dev Relations @Coralogix bio Lewis is a Developer Advocate at Coralogix, where he works closely with developers to explore smarter approaches to observability and how deep technical telemetry can be connected to meaningful business and user outcomes. Prior to joining Coralogix, he was a Tech Lead at IBM, where he led the technical delivery of mobile application projects for clients including BP and a major UK bank.

Elena Vilimaite @ WeBuild-AI
Cutting code afk - How Ralph Wiggum can help you do the work for you.

About the talk:
The Ralph Wiggum loop is a deceptively simple idea: point an agentic coding pipeline at a plan and let it cycle, implement, review and fix on repeat, with no hands on the keyboard. In this talk I'll walk through three real runs of Ralph on my own codebase, from a 24 minute one-shot that shipped subtle bugs to a two and a half hour run where the agents actually caught and fixed their own mistakes. You'll see what made the difference (spoiler: it wasn't the loop), and why the human still isn't going anywhere just yet.

Avidan Avraham @ Cato Networks
Autonomous Policies Using LLMs to Sweep Up Misconfigs

Security policies and engines today are complex ecosystems - not just defined by rigid, structured configurations but also by many layers of free-text and meta-data that tell the real story behind a rule or a configuration. Traditional configuration analysis can flag obvious issues, yet it often overlooks the contextual “crumbs” left behind by temporary fixes, ad-hoc tweaks, or legacy testing exercises. These remnants, much like orphaned data in a software system, can create unexpected vulnerabilities that attackers are eager to exploit.

In this talk, I introduce a pioneering AI-driven strategy inspired by the concept of a software Garbage Collector. Just as a Garbage Collector continuously cleans up memory leaks, our AI agent proactively sifts through the meta-configuration, analyzing unstructured fields—free-text names, descriptions, annotations, and even multilingual notes—to identify contextual misconfigurations before they evolve into high-risk liabilities.

Advanced NLP is key: semantic analysis decodes the intent behind free-text entries, while contextual classification organizes policy components by interpreting diverse cues. This integrated approach detects anomalies that traditional tools may miss, shifting policy management from static settings to dynamic, context-rich narratives that reveal hidden security gaps.

We hope to see you there for another great AI filled evening!

Sponsors...

The AI Exchange is brought to you in partnership with LinuxRecruit and AWS.

LinuxRecruit is building the next wave of Tech Unicorns in Europe.
Whether you're hiring or exploring your next opportunity, get in touch.