---
title: "Hybrid Parallel Retrieval · agent retrieval pattern · Agent Fieldbook"
url: https://agentfieldbook.org/memory/retrieval/hybrid-parallel/
description: "Fan one query across several channels at once, full-text, fact-key, direct-vector, HyDE-vector, raw-message, then fuse the ranked lists."
section: "Memory · Retrieval"
source: Agent Fieldbook — generated from the published page
---

# Hybrid Parallel Retrieval

Fan one query across several channels at once, full-text, fact-key, direct-vector, HyDE-vector, raw-message, then fuse the ranked lists.

Verified against [blog.cloudflare.com](https://blog.cloudflare.com/introducing-agent-memory/)

- [blog.cloudflare.com](https://blog.cloudflare.com/introducing-agent-memory/)

## How it works

## At a glance

| Field | Value |
| --- | --- |
| Stage | Retrieval |
| Phase | Read |
| Used by | Cloudflare Agent Memory (5 channels) |

## Trade-off

More channels = more cost/latency and a fusion step to tune.

## Basis

## Verified against

- [https://blog.cloudflare.com/introducing-agent-memory/](https://blog.cloudflare.com/introducing-agent-memory/)

The corpus does not rewrite vendor documentation. Where copy is quoted verbatim it is marked as such and attributed to its source.