Product Recommendations Engine

AI agent costs are driven up by inefficient architecture. This guide breaks down five proven patterns, including deterministic workflows, parallel tool calls, and semantic caching, to reduce token usage, improve performance, and scale AI systems more efficiently.

5 Patterns to Cut Your Agent's Token Bill

AI agent costs are driven up by inefficient architecture. This guide breaks down five proven patterns, including deterministic workflows, parallel tool calls, and semantic caching, to reduce token usage, improve performance, and scale AI systems more efficiently.

5 Patterns to Cut Your Agent's Token Bill

AI agent costs are driven up by inefficient architecture. This guide breaks down five proven patterns, including deterministic workflows, parallel tool calls, and semantic caching, to reduce token usage, improve performance, and scale AI systems more efficiently.

5 Patterns to Cut Your Agent's Token Bill

An open-source real-time product recommendation engine built as a Harper component. Combines co-occurrence learning, HNSW vector search, UCB exploration, and category diversity re-ranking on Harper's replicated tables. No vector database, training pipeline, or external ML infrastructure required.

Product Recommendations Engine

TypeScript

Repo

An open-source real-time product recommendation engine built as a Harper component. Combines co-occurrence learning, HNSW vector search, UCB exploration, and category diversity re-ranking on Harper's replicated tables. No vector database, training pipeline, or external ML infrastructure required.

An open-source real-time product recommendation engine built as a Harper component. Combines co-occurrence learning, HNSW vector search, UCB exploration, and category diversity re-ranking on Harper's replicated tables. No vector database, training pipeline, or external ML infrastructure required.

Product Recommendations Engine

An open-source real-time product recommendation engine built as a Harper component. Combines co-occurrence learning, HNSW vector search, UCB exploration, and category diversity re-ranking on Harper's replicated tables. No vector database, training pipeline, or external ML infrastructure required.

Product Recommendations Engine

An open-source real-time product recommendation engine built as a Harper component. Combines co-occurrence learning, HNSW vector search, UCB exploration, and category diversity re-ranking on Harper's replicated tables. No vector database, training pipeline, or external ML infrastructure required.

Product Recommendations Engine

Build a real-time, geofenced promo engine on Harper's agentic runtime. The Nearstore Agent collapses geofence lookup, customer data, campaigns, and AI decisions into a single process. Clone the reference repo and deploy in minutes.

The Nearstore Agent: a reference pattern for low-latency, geofenced, promotional decisions

Blog

Build a real-time, geofenced promo engine on Harper's agentic runtime. The Nearstore Agent collapses geofence lookup, customer data, campaigns, and AI decisions into a single process. Clone the reference repo and deploy in minutes.

Aleks Haugom

Senior Manager of GTM

Build a real-time, geofenced promo engine on Harper's agentic runtime. The Nearstore Agent collapses geofence lookup, customer data, campaigns, and AI decisions into a single process. Clone the reference repo and deploy in minutes.

The Nearstore Agent: a reference pattern for low-latency, geofenced, promotional decisions

Build a real-time, geofenced promo engine on Harper's agentic runtime. The Nearstore Agent collapses geofence lookup, customer data, campaigns, and AI decisions into a single process. Clone the reference repo and deploy in minutes.

The Nearstore Agent: a reference pattern for low-latency, geofenced, promotional decisions

Build a real-time, geofenced promo engine on Harper's agentic runtime. The Nearstore Agent collapses geofence lookup, customer data, campaigns, and AI decisions into a single process. Clone the reference repo and deploy in minutes.

The Nearstore Agent: a reference pattern for low-latency, geofenced, promotional decisions

A Harper reference pattern: customer GPS ping → personalized promo decision via Claude Haiku, all in one Harper runtime. Geofenced with H3, data assembled in-process, pluggable decision layer.

Near Store Agent

TypeScript

Repo

A Harper reference pattern: customer GPS ping → personalized promo decision via Claude Haiku, all in one Harper runtime. Geofenced with H3, data assembled in-process, pluggable decision layer.

Aleks Haugom

Senior Manager of GTM

A Harper reference pattern: customer GPS ping → personalized promo decision via Claude Haiku, all in one Harper runtime. Geofenced with H3, data assembled in-process, pluggable decision layer.

Near Store Agent

A Harper reference pattern: customer GPS ping → personalized promo decision via Claude Haiku, all in one Harper runtime. Geofenced with H3, data assembled in-process, pluggable decision layer.

Near Store Agent

A Harper reference pattern: customer GPS ping → personalized promo decision via Claude Haiku, all in one Harper runtime. Geofenced with H3, data assembled in-process, pluggable decision layer.

Near Store Agent

Explore how a Shopify-based custom tie shop reveals a critical flaw in one LLM agent design strategy, and why context-first architectures with unified runtimes deliver faster, more accurate, and scalable customer support automation.

How a Shopify Custom Tie Shop Exposes a Common Flaw in Agent Architecture

Blog

Explore how a Shopify-based custom tie shop reveals a critical flaw in one LLM agent design strategy, and why context-first architectures with unified runtimes deliver faster, more accurate, and scalable customer support automation.

Aleks Haugom

Senior Manager of GTM