Product Builder, Cloud Architect & Startup Veteran
Hi, I'm Jeremy Daly.
I build AI- and data-driven platforms that turn complex systems into reliable, scalable products. For more than 25 years, I’ve led teams building cloud-native infrastructure, intelligent data platforms, and modern SaaS systems that deliver real business impact.
I’m an AWS Serverless Hero, founder, and product leader who cares deeply about building strong teams and durable systems. Lately, that work has centered around AI-native architecture, semantic data design, and making advanced technology practical and economically sustainable.
I’m currently consulting, as well as hacking on Ampt and exploring Infrastructure FROM Code and AI-native developer platforms.
If you’d like the full story, including my founder journey and past projects, head over to the About page.
I write about AI, cloud architecture, and serverless systems. If that’s your thing, subscribe to Off-by-none or connect with me on LinkedIn, Bluesky, X, or GitHub.
Latest Posts:
Use Graph RAG when relationships are part of the evidence (opens in a new tab)
Discover how Graph RAG combines vector search with explicit relationship mapping to provide reliable evidence for complex AI questions.
Stop asking the reasoning model to decide everything
Cheap judgments change what I'd automate. I tested TypeSafe's Jev to see which recurring agent decisions a System One model could take on.
Using Jev and Oracle AI Database to govern agent memory (opens in a new tab)
Learn how to build AI agent memory with Jev and Oracle AI Database, using scoped retrieval, context selection, and evidence-backed promotion.
Building trust in agentic RAG starts with evidence (opens in a new tab)
Agentic RAG requires clear evidence. Discover how tracking retrieval decisions, metadata, and citations builds trust in AI agent outputs.
AI agent evaluations are part of the product (opens in a new tab)
Move beyond simple AI demos. Build repeatable evaluation systems, test execution paths, and enforce strict release gates for AI agents.
Your AI agent is only as good as the harness around it (opens in a new tab)
Build production-ready AI agents with effective guardrails, tool contracts, permissions, and tracing systems beyond simple demos.
Hybrid Retrieval for Agent Memory: Vector, Lexical, and Metadata Together (opens in a new tab)
Learn how hybrid search for AI agent memory combines metadata filters, vector and lexical retrieval, rank fusion, and reranking.
The Future is for Everyone Meta
Mark Zuckerberg says superintelligence is a few years away and Meta is going to hand it to all of us. Read the essay closely and it's a capital expenditure plan in search of a philosophy.
Persistent Memory and Derived Context: A Two-Layer Pattern for Agents (opens in a new tab)
Learn how to prevent AI agent memory drift by separating canonical memory from derived retrieval context using Oracle AI Database, provenance, embeddings, and durable memory patterns.
From Prompt to Persistence (Part 2): Putting the Multi-Tenant Agent Memory Schema to Work (opens in a new tab)
Explore retrieval, shared memory, semantic cache, and Memory Manager design for multi-tenant AI agents using Oracle AI Database. Learn how durable, tenant-aware memory powers scalable SaaS agent architectures.