Systems | Development | Analytics | API | Testing

Ep 85 | Enterprise AI Success: What Separates Results from Expensive Experiments

Most enterprise AI use cases still aren't delivering measurable value. So what separates the projects that work from the ones that quietly disappear? For Mark Ritcey, the answer comes down to disciplined execution. AI programs need a clear business problem and an organization prepared for how the technology changes the way work gets done. In this episode of The AI Forecast, Paul Muller sits down with Mark Ritcey, Vice President of AI and Automation Delivery at Latentbridge and lecturer on AI and machine learning, to examine the decisions that shape enterprise AI success.

SQL-Shaped Intent: The Engineering Behind AgentQL

Our CEO recently wrote reaffirming an architectural decision ThoughtSpot made when LLMs first emerged: we do not use LLMs to directly generate SQL. My team has spent the better part of a year building AgentQL: a capability that doubles down on our decision. So let me explain what we actually built, why it doesn't just honor that architectural decision but depends on it, and the engineering choices underneath.

Diagnose Serial N+1 API Calls With Tempo + proxymock

One API request took 302 milliseconds. Nothing failed. CPU was mostly idle. The response was correct. The trace made the problem obvious: eight inventory calls, each waiting for the previous one. But the trace could not tell me why the application made eight calls, or whether changing their execution would preserve the response. It showed the shape of the wait, not the input that created it.

Practice what you Pact : Catch breaking API changes before production in the SmartBear MCP

There’s something satisfying about contract testing the contract-testing tool. The SmartBear MCP Server is the integration layer between AI coding assistants and the PactFlow API, so when we decided it needed Pact consumer tests of its own, we were subjecting our own code to the same standards that we recommend.

Kong AI Gateway Applies NVIDIA NeMo Switchyard Across Model Traffic

Every team running production LLMs has had the same idea: not every request needs the frontier model. Intelligent model routing (or LLM routing)— choosing a model per request on criteria such as task complexity, cost, latency, or quality — enables more efficient model usage.

Avoid the Cloud Token Trap & Secure Your AI | Cloudera AI Inference Service Demo

Relying strictly on public cloud AI APIs often leads to unpredictable token costs and data residency concerns. In this demo, Peter Ableda (Product Lead for Cloudera AI) demonstrates how the Cloudera AI Inference service enables enterprise-grade private AI behind your firewall—whether on-premises or in a Virtual Private Cloud (VPC). Learn how bringing AI directly to your data ensures total model control, cost predictability, and maximum data security.

The Impact of AI and Machine Learning on Real Estate Business

Artificial Intelligence (AI) and Machine Learning (ML) are changing the way the real estate industry operates. From property valuation and investment analysis to customer service and marketing, these technologies are helping businesses process information faster and make more informed decisions.

How Automating Marketing Data with AI Saves Hours

Did you know Cloudera's marketing operations team is using AI to automate workflows and eliminate manual processes? In this video, Kelly Sutter shares how Cloudera empowers marketing teams to unify data, uncover customer insights faster, and optimize marketing analytics with trusted enterprise AI. Discover how bringing AI to your data makes marketing more connected, responsive, and effective.