Research

Applied AI research from building real systems.

These white papers capture the architectural patterns, product decisions, and engineering lessons behind CitronLab's work: how to make AI faster, more reliable, more private, more contextual, and more useful inside real workflows. This is applied research, not abstract AI commentary.

01

Consensus-Based AI Pre-Processing

Learning on the Fly, the Fast Way

A pattern for combining deterministic rules and consensus validation before LLM analysis, so the AI receives verified facts and uses its reasoning capacity for context rather than guessing.

AI architectureNick Brandt & Leo Gestetner12 minAugust 2025
02

Temporal Memory

Why AI Systems Need to Forget

A time-aware memory architecture where facts have relevance, half-lives, reinforcement, anchors, and decay — helping AI systems handle changing context more like humans do.

AI architectureNick Brandt & Leo Gestetner14 minNovember 2025
03

Two-Phase Streaming

Why Users Should See Results Before AI Finishes

A streaming architecture that shows deterministic results quickly while AI enrichment continues in the background, making AI products feel faster and more useful.

AI architecture · UXNick Brandt & Leo Gestetner11 minSeptember 2025
04

Cold Start Zero

Why Rust is Replacing Python for Real-Time Serverless

A practical look at when Rust can reduce cold-start latency and cost for real-time serverless workloads where every millisecond affects the user experience.

Serverless architectureNick Brandt & Leo Gestetner10 minAugust 2025
05

On-Device LLM

The End of Cloud AI Dependency

A privacy-by-architecture argument for running capable AI locally on modern devices, especially for sensitive personal, financial, professional, or proprietary data.

AI architecture · privacyNick Brandt & Leo Gestetner13 minJuly 2025
06

Proactive AI

Surfacing What You Need Before You Ask

An architecture for AI that monitors context and surfaces relevant information before the user asks — using knowledge graphs, temporal relevance, and privacy-aware context awareness.

AI architecture · context-aware systemsNick Brandt & Leo Gestetner12 minJune 2025
Research in practice

Research that shows up in the products we build.

Our white papers describe patterns we use when building real systems: pre-processing facts before AI reasoning, streaming useful results before LLM calls finish, designing memory around time and relevance, choosing private or on-device architectures for sensitive data, and building proactive systems that surface useful context without becoming intrusive.

Book a call to discuss your AI project