How to build reliable AI agents: Test Driven Development is back!
Loading the Elevenlabs Text to Speech AudioNative Player… One of the top questions on the lips of teams building AI agents is ‘when is it ready to go live?’ It’s no wonder this is a concern because most businesses are making go-live decisions based on vibes. They don’t have any evidence to point to that […]
The trust layer banks need for an agentic future with Mathias Fanschek, Raiffeisen Bank International
We discuss why banks need a trust layer for AI agents, and what headless banking means for the future of finance.
Your AI agent is already live. But is it working?
Most enterprise AI assistants are already live. Most have never been properly tested. Watch this VUX Consulting webinar on how to test your conversational AI before it fails in production.
Testing for trust in the age of AI agents with Amitha Pulijala and Christoph Börner, Cyara
Discover how leading teams are testing AI agents in a world of non-deterministic systems, covering trust, cost and scale.
Testing the future: How Klearcom is powering the voice AI revolution
As businesses move from legacy IVRs to conversational AI, one company powers the testing tech that keeps everything running smoothly.
From IVR to AI: The future of voice testing in contact centres with Satish Barot, Klearcom
As generative AI redefines the contact centre, ensuring consistent performance across complex telephony networks becomes mission-critical.
Responsible AI, Real Results with Citizens Advice
In this episode on the VUX World podcast, we chat all about the innovative AI journey of Citizens Advice with Stuart Pearson.
Bridging the Generative AI Gap: Governance, Quality, and Enterprise Adoption
Every big tech company is working on foundational generative AI models and promises that the future will be different. Yet…
Is it safe to use LLMs in a healthcare setting?
You may be tempted to say no. There’s two obvious reasons why; LLMs hallucinate (which could mean that nonsense or simply incorrect health advice would be generated) and they can be compromised by injection attacks (which would mean that private medical data could be extracted). Is that the end of the story though? Can’t we […]
Counteracting the risk of LLMs
As of now, using LLMs in high-stakes enterprise customer interactions could be considered a risk. Although there are more robust ways of mitigating the hallucination issue emerging, it’s never going to be a 100% solved problem. If LLMs have direct access to private data, without an intermediary platform in between the model and the user, […]