---
type: "post"
id: "groundhog-day-for-ai-agents-prompt-caching-patterns-3e941d"
slug: "groundhog-day-for-ai-agents-prompt-caching-patterns-3e941d"
title: "Groundhog Day for AI agents: Prompt caching patterns for using OpenAI models on Amazon Bedrock"
description: "AWS has published a technical guide to prompt caching for agent workloads using OpenAI models on Amazon Bedrock."
retrieval_nugget: "AWS has published a technical guide to prompt caching for agent workloads using OpenAI models on Amazon Bedrock."
published_at: "2026-10-27"
updated_at: "2026-10-27"
record_date: "2026-10-27"
date_kind: "published_at"
topics: ["harness-engineering","agent-runtime"]
entities: ["Amazon Web Services","Amazon Bedrock","OpenAI"]
related_patterns: ["harness-architecture-outlives-model-choice","agent-economics-moves-to-completed-work"]
novelty_label: "new_fact"
what_changed: "Adds prompt-caching patterns for using OpenAI models on Amazon Bedrock, extending the prior announcement that the models were available there."
prior_refs: ["memory:45473b53-2e6d-8324-a981-8814fccb6d63"]
source_url: "https://aws.amazon.com/blogs/machine-learning/groundhog-day-for-ai-agents-prompt-caching-patterns-for-using-openai-models-on-amazon-bedrock"
source_urls: ["https://aws.amazon.com/blogs/machine-learning/groundhog-day-for-ai-agents-prompt-caching-patterns-for-using-openai-models-on-amazon-bedrock"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:groundhog-day-for-ai-agents-prompt-caching-patterns-3e941d"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/groundhog-day-for-ai-agents-prompt-caching-patterns-3e941d/","markdown":"https://newruntime.com/posts/groundhog-day-for-ai-agents-prompt-caching-patterns-3e941d.md","json":"https://newruntime.com/posts/groundhog-day-for-ai-agents-prompt-caching-patterns-3e941d.json"}
---

# Groundhog Day for AI agents: Prompt caching patterns for using OpenAI models on Amazon Bedrock

## Retrieval answer

AWS has published a technical guide to prompt caching for agent workloads using OpenAI models on Amazon Bedrock.

AWS has published a technical guide to prompt caching for agent workloads using OpenAI models on Amazon Bedrock. The post describes an agent request as a combination of tool definitions, developer instructions, conversation and tool-call history, and the newest turn.

It says caching saves the model's prefilling state, including key-value vectors, for an identical prompt prefix. A subsequent request can load that state and process only the newly appended content. Bedrock can choose a reusable prefix implicitly, while developers can mark one explicitly with `prompt_cache_breakpoint`; AWS recommends using both approaches together.

The examples focus on keeping stable instructions and tool definitions ahead of changing conversation material, including cases where tools change or an agent starts helper tasks. AWS presents the technique as a way to reduce repeated input processing, latency, and input cost.

The source does not provide an independent benchmark, a universal cost reduction figure, or evidence that the pattern transfers unchanged to APIs outside Amazon Bedrock. It is an AWS-authored implementation guide rather than a product-release announcement.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Harness Engineering](https://newruntime.com/topics/harness-engineering.md): Explore the harness-engineering topic hub.
- topic hub: [Agent Runtime](https://newruntime.com/topics/agent-runtime.md): Explore the agent-runtime topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)