Unlocking the Data Layer for Agentic AI with Simba Khadder

88 snips

Apr 21, 2026

Simba Khadder, AI strategy lead at Redis and FeatureForm co-founder, explains why context is now the core challenge for agentic AI. He breaks down context engines: on-demand retrieval, fresh data, fast access, and evolving memory. They cover materialized views, semantic layers over Redis, async memory compaction, and how teams must change engineering practices for AI-driven systems.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

INSIGHT

Context Is The New Bottleneck For Agents

Context is now the bottleneck for agentic AI rather than model attention or raw capability.
Simba Khadder explains agents can run unsupervised for ~1 hour today and will extend, so systems must enable on-demand context retrieval instead of preloading everything.

ADVICE

Build A Four Pillar Context Engine

Build a context engine with four pillars: navigable retrieval, always-up-to-date data, low-latency access, and improving memory.
Prioritize fast materialized context views and a memory loop that makes the context better over time.

ADVICE

Use Materialized Views Not Direct DB Access

Avoid giving agents direct access to production systems; instead create materialized views as the context surface.
Simba describes using ETL (Redis RDI) to sync systems of record into Redis and add a semantic retriever layer on top.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

AI agents are increasingly capable of reasoning and performing autonomous work over long periods. However, as agents take on more complex, longer-horizon tasks, keeping them supplied with the right information becomes the core engineering challenge. The industry is moving away from pre-loading context upfront toward a model where agents dynamically navigate and retrieve the data they need, when they need it.

Redis is approaching context management using a context engine, which is an architecture built around four pillars: on-demand context retrieval, data that is always current, fast retrieval, and a memory layer that improves over time. In practice this means building materialized views of data with a semantic layer on top, rather than giving agents direct access to production databases. A memory system sits alongside this, extracting and compacting information asynchronously as the agent works.

Simba Khadder leads AI strategy at Redis, and he previously co-founded the feature store platform FeatureForm, which was acquired by Redis in 2025. In this episode, Simba joins Kevin Ball to discuss why context has become the defining challenge in agentic AI, how context engines differ from traditional RAG architectures, how materialized views underpin reliable agent data pipelines, how memory systems can improve through async extraction and compaction, and how engineering teams need to adapt their practices as AI-driven development accelerates.

Full Disclosure: This episode is sponsored by Redis.

Kevin Ball or KBall, is the vice president of engineering at Mento and an independent coach for engineers and engineering leaders. He co-founded and served as CTO for two companies, founded the San Diego JavaScript meetup, and organizes the AI inaction discussion group through Latent Space.

Please click here to see the transcript of this episode.

Sponsorship inquiries: sponsor@softwareengineeringdaily.com

The post Unlocking the Data Layer for Agentic AI with Simba Khadder appeared first on Software Engineering Daily.