If you're building production-grade AI apps, you may know an uncomfortable truth: reliable model outputs require far more than clever prompting. You must orchestrate tool calling, implement memory and retrieval pipelines, and dynamically manage token consumption while maintaining consistency at scale.
This is where context engineering comes in. Context engineering is an emerging discipline that treats the context sent to your models as an architectural resource to be designed, optimized, and managed. In this session, we'll go beyond the concept and into implementation: how do you build memory systems that actually persist what matters across interactions? How do you retrieve the right information at the right time without flooding the context window? And how do you manage token consumption without sacrificing the coherence your application depends on?
Using a real-world example, we will discuss the architectural changes that turned a naïve app into a fully engineered context pipeline and highlight lessons learned along the way to improve output consistency and project costs in production.
Interview:
What is your session about, and why is it important for senior software developers?
This talk is about moving beyond prompt engineering and treating "context" as an architectural concern. In production systems, reliability depends on how you design retrieval, memory, tool use, and evaluation. Not just the prompt. For senior engineers, this is about building AI systems that behave predictably under real-world constraints.
Why is it critical for software leaders to focus on this topic right now?
Most teams are past the prototype phase. The real challenge now is operationalizing AI: controlling cost, latency, correctness, and risk. Leaders who understand context engineering can guide their teams from impressive demos to dependable systems.
What are the common challenges developers and architects face in this area?
Hallucinations, inconsistent retrieval quality, state management across interactions, evaluation gaps, and unclear observability. The hard part isn't generating text. It's building systems that are measurable, debuggable, and scalable.
What's one thing you hope attendees will implement immediately after your talk?
Start designing explicit context pipelines. Define how context is selected, validated, and monitored. Treat it like any other critical system dependency.
What makes QCon stand out as a conference for senior software professionals?
QCon prioritizes practical lessons from engineers building real systems at scale. It's a place for architectural depth, not surface-level trends.
Speaker
Ricardo Ferreira
Principal Developer Advocate @Redis, Expert in Distributed Systems, Databases, and Software Development, Previously @AWS, @Elastic, and @Confluent
Ricardo serves as Principal Developer Advocate at Redis. He built a successful career in DevRel, working for companies such as AWS, Elastic, and Confluent.
He has more than 25 years of experience in distributed systems, databases, and software development. He began his career focused on software engineering and developer education, then moved into solution architecture, helping customers design, build, and deploy data-intensive applications. Over time, he found his passion in DevRel, where he combines deep technical expertise, teaching experience, and customer empathy to help developers succeed.
Find Ricardo Ferreira at:
Date
Monday Jun 1 / 10:20AM EDT ( 50 minutes )
Location
Metcalf Hall Large
