人工智能
Amazon Nova多式嵌入和Amazon Bedrock Agent Core的代理工程情报
当一个合格的航空航天部件过时或达到的周转时间很长时，工程师在记录审查的替代理由之前，要花几天时间在供应商数据表、接口控制文件和资格记录之间相互参照规格。 对飞行关键部分的不正确替换可能导致任务失败，但每项决定背后的证据线索往往分散在电子邮件和没有文件的机构知识中，因此没有正式的、可重复的供审查者检查的套件。
之前的一篇文章，用Amazon Nova Multimodule Embeddings的制造智能，展示了模型如何检索被锁定在工程图，热地图，以及只文本管丢失的数据表图中的解答。 这一帖子收起检索工作所剩之处，将这些能力放在一个收集替代证据的多agent系统中，从检索到起草的评估。
在此帖子中，我们展示了如何构建多agent工程助理，削减使用Amazon Bedrock Agent Core,Amazon Nova多模式嵌入，和开源 Strands Agents SDK等手动交叉参照部分替代评价。 一条规划者路线跨越三个专家agents，搜索一个多模式知识库，根据确定性容忍规则对候选人进行评分，比较部分照片，以及现场网络数据中的地面生命周期声称。 工程师始终是决策者，因为该系统收集证据并起草文件，从未自行批准替代。
解决办法概述
助理是围绕一个设计规则来构建的，即工程师做出每一个决定，系统为此收集证据。 这个规则决定了我们使用大语言模型(LLMs)的地方，以及我们使用决定密码的地方。
三根支柱定义了建筑：
Python 所写的容忍规则代码将每个候选部分比照参考部分和工程师的规定进行评分。 由于同样的投入始终产生相同的传入/旗下裁定，结果可以进入正式的工程审查。
- 多agent 管弦乐 – 一个轻量级规划师每次查询一个或三个专家agents(Catalog, Evaluation, Knowledge)中的一个或一个以上，而一名主管只有在一个以上专家出力的情况下才能综合他们的调查结果。 复杂的问题，例如“检查这道车轮是否即将报废，找到替代品，并给它们打分”，将所有三位专家按顺序排列。
- 人类的无所作为的决定系统为工程审查起草说明备忘录及综合影响评估，每次评价还写出与AS9100第8.4和8.5.6节一致的审计线索条目。
下图显示架构。
Amazon Bedrock Agent Core是一个在规模上构建，连接，并优化agents的平台，拥有任何框架或模型。 在这个解决方案中，来自工程师应用程序的聊天请求流入了Agent Core运行时托管的多agent图：一名计划员(Claude Haiku 5.5)制作出一个路由计划，一名专家(Claude Sonnet 5.5)执行他们的工具，一名主管(Claude Opus 5.5)在不止一名专家跑出时合成他们的结果。 专家从我们与Amazon Bedrock管理知识库一起利用Amazon Nova多式联运嵌入器创建的有管理的知识库中取出，该知识库通过一个Agent Core Gateway(Amazon Bedrock Agent Core)的路由，它具有Amazon Bedrock Agent Core的能力，与现场网络数据网络搜索连接器相接。 对于图像-as-query(上载一个图表来识别一个部分),agent直接称原生的Amazon S3矢量指数，因为所管理的知识库检索API不接受图像输入。 Amazon S3矢量是Amazon简易存储服务(Amazon S3)的一种能力。 单独的固定链(知识、然后是评价、然后是监督)产生正式的一体化影响评估文件。
Amazon Nova多式嵌入式有两个不同的作用：
-多模式检索 – 数据表，ICD和性能图被嵌入了Nova多模式嵌入，因此文本和视觉内容共享一个语义空间。 工程师可以输入“0.06 Nms轮的轨迹曲线”或上传图表图像，检索返回与源属性相匹配的图表。
- 视觉相似性评分当比较两个候选部分时，Nova多式嵌入在其相片之间产生了定量同位素相似性，而Claude分析具体物理差异(挂载模式，连接器放置，住房几何). 分数新增支持证据为定谱比对，这是适配判断的依据。
先决条件
接下来，你需要：
- AWS账户，可访问美国东部(弗吉尼亚州)Amazon Bedrock地区。
- Amazon Nova多式嵌入器的型号访问，Claude Haiku 5.5,Claude Sonnet 5.5,Claude Opus 5.5在Amazon Bedrock. 关于按区域分类的模型可用性，参见AWS区域在Amazon Bedrock的模型支持。
- 与Amazon Bedrock管理知识库建立的管理知识库，使用Amazon Nova多式联运嵌入器件(数据表、光盘、说明)进行文本和文件检索。
- Amazon S3矢量指数，在您的部分相片和数据表图表的收成上，用于图像平整路径。
- Amazon Bedrock Agent Core Gateway，配有Web搜索连接器和管理的知识库目标。
- Python 3.10 或以后和 Jupyter 操作笔记本。
- Docker，如果你调整了笔记本03中的部署食谱，在Agent Core运行时间上托管agent.
- GitHub仓库的样本代码
解决方案走过
以下各节按查询使用的顺序描述系统的每一部分。 我们从零配件和专家agents开始，然后涵盖路线，定点分数，助理使用Nova多式联运嵌入的两种方式，生成正式文件的固定链，以及部署到Core代理运行时间。
完整的代码样本是GitHub寄存器中由5个Jupyter笔记本组成的一组，每个笔记本自行运行。 笔记本从mei core导入自成一册的agent和工具模块在同一文件夹中，它们包括自己的部件数据，图表收成，和评价查询集。 您可以从笔记本中运行本文中的每一个片段，而无需其他应用程序代码。
部件结构
样本数据集是一个虚构制造商(AnyCompany)的七个反应轮，跨度为0.003–5. 动力存储。 每个部分都是一个文件夹，将结构化的数据与工程师实际读取的源文件相配，而这种组合使得本体多模式化。 specs.json文件持有驱动决定性评分的机器可读字段，而ICD，产品相片，并提供了数据表页面则带有结构化字段所遗漏的可视和叙事细节。
specs.json文件既能捕捉工程规格，又能捕捉出一个生命周期剖面图，这使得助手们能标出过时和前置时间的风险，同时能捕捉到光谱。
对每一部分都明确说明了供应商领域。 由于目录文件夹ID和文件名在数据集之间被再用，所以每个专家迅速将gee part specs返回的结构化供应商值视为权威，并禁止从ID，文件名，相片，或网络搜索结果中猜测出制造商。 将制造商从结构化数据中取出，使得助理不会将一部分归属于错误的供应商，因为模型认为它能识别出硬件。
每个部分文件夹还包含两个仅文本索引无法使用的资产。 产品相片输入了视觉相近性的评分，制成的数据表页载有torque-box和torque-curve图解答无OCR文本层捕获的性能问题。 Amazon Nova多模式嵌入同时嵌入与文本相同的向量空间，因此一个查询可以匹配一个光谱值，一个段落，或者一个图。
以下样本显示四个数据表页来自本体，覆盖了三等的动力存储。
模板在整个家族中重复，但产品相片和一对性能地块随每个部分而变化。 这些区域显示了内在几何、上升图案、扭矩信封和电源绘图，这些光谱字段没有直接说明，所以我们把它们和文本一起嵌入其中。
界定具有范围工具的专家
每个专家都是斯特兰德斯·agent(英语：Strands agent)，带有狭义的快取并仅需要它所需要的工具。 每个专家的扫描工具保持了行为的可预期性，因为知识专家无法获得目录发现工具，目录专家也无法获取评价工具。 以下代码创建了评价专家。
下图显示规划师如何向专家查询，以及主管何时综合结果。 后面的列表描述了每位专家的工作。
- Catalog – 通过知识库搜索和详尽的光谱过滤(kb search, filter parts by spec, get part specs, get sultition requiments)来发现部分。
评分评分评分评分评分评分评分评分评分评分评分评分评分评分评分评分评分
- Knowledge – 回答来自数据表和ICD的问题，检查活的报废状态，并检索可视内容(get part specs,web search eol, refer visual content).
使用一个小型的路由模型和一个大型的合成模型
校对：Soup 一个基于海库的规划师在几秒钟后返回一个编号的路由计划。 Opus主管只在两个或两个以上专家出力时才运作，因为合成一个专家已经完全的回答新增大约8秒的空闲时间，没有质量收益。
将工作分为三个模式层面，与每个阶段的成本和耐久性相匹配。 Haiku对查询进行分类，Sonnet运行工具，而Opus则写出综合答案，这是回应质量最重要的一步。
保持评分定分
spec-fit评价以普通的Python代码运行，与手写要求相抗衡。 计划定义了每个组件类别的关键规格和耐受性规则，并得分替代 fit 比较了每个规格，计数通过和旗帜，表面存在周期风险。 因为判决必须可以复制到工程审查套件，所以没有LLM参与这一步骤。
工具返回一个结构化的判决，并附有明确的免责声明：
但无法改变判决。 审计线索遵循相同的分工。 在每一次评估之后，管弦乐层都会读取专家的工具调用历史
与 Amazon Nova 多式联运的分数视觉相似性
形式因素涉及替代物必须符合现有括号的情况。 视觉- simility- score 工具同时嵌入了 Nova 多式联运嵌入和计算相容性相近的部分相片，然后要求 Claude 描述具体的可观测差异。
嵌入式相似性具有决定性并可再出产，回回相距为0.84左右，为同一种产品家族的两个轮子取出，为不同等级的轮子取出0.40. Claude的视觉分析随后解释了是什么驱动了这种差异，例如，它指出，一个住房的直径大约是另一个住房的两倍，在另一个住房有四个住房的地方，它有一个6个洞的上升模式。
获取带有两个图表的图表
本文由 AI宝库自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
Artificial Intelligence
Agentic engineering intelligence with Amazon Nova Multimodal Embeddings and Amazon Bedrock AgentCore
When a qualified aerospace component goes obsolete or hits a long lead time, an engineer spends days cross-referencing specifications across vendor datasheets, interface control documents (ICDs), and qualification records before documenting a substitution justification for review. An incorrect substitution on a flight-critical component can cause mission failure, yet the evidence trail behind each decision is often spread across email and undocumented institutional knowledge, so there is no formal, repeatable package for a reviewer to check.
A previous post, Manufacturing intelligence with Amazon Nova Multimodal Embeddings, showed how the model retrieves answers locked inside engineering diagrams, thermal plots, and datasheet charts that text-only pipelines miss. This post picks up where that retrieval work left off, putting those capabilities inside a multi-agent system that assembles substitution evidence, from retrieval to a drafted assessment.
In this post, we show how to build a multi-agent engineering assistant that cuts the manual cross-referencing behind part substitution evaluation using Amazon Bedrock AgentCore, Amazon Nova Multimodal Embeddings, and the open source Strands Agents SDK. A planner routes work across three specialist agents that search a multimodal knowledge base, score candidates against deterministic tolerance rules, compare part photos, and ground lifecycle claims in live web data. The engineer remains the decision-maker throughout, because the system assembles evidence and drafts documents without ever approving a substitution on its own.
Solution overview
The assistant is built around one design rule, which is that the engineer makes every decision and the system assembles the evidence for it. That rule determines where we use large language models (LLMs) and where we use deterministic code instead.
Three pillars define the architecture:
- Deterministic spec-fit evaluation – Tolerance-rule code written in Python scores each candidate part against the reference part and the engineer’s stated requirements. Because the same inputs consistently produce the same pass/flag verdicts, the results can go into a formal engineering review.
- Multi-agent orchestration – A lightweight planner routes each query to one or more of three specialist agents (Catalog, Evaluation, Knowledge), and a supervisor synthesizes their findings only when more than one specialist contributed. Complex questions such as “Check if this wheel is going end-of-life, find alternatives, and score them” chain all three specialists in sequence.
- Human-in-the-loop decision – The system drafts justification memos and Integration Impact Assessments for engineering review, but it doesn’t recommend or approve a substitution. Every evaluation also writes an audit trail entry aligned with AS9100 sections 8.4 and 8.5.6.
The following diagram shows the architecture.
Amazon Bedrock AgentCore is a platform to build, connect, and optimize agents at scale, with any framework or model. In this solution, chat requests from the engineer’s application flow into a multi-agent graph hosted on AgentCore runtime: a planner (Claude Haiku 5.5) produces a routing plan, specialists (Claude Sonnet 5.5) execute their tools, and a supervisor (Claude Opus 5.5) synthesizes their results when more than one specialist ran. The specialists retrieve from a managed knowledge base that we created with Amazon Bedrock Managed Knowledge Bases using Amazon Nova Multimodal Embeddings, routed through an AgentCore Gateway, a capability of Amazon Bedrock AgentCore, alongside the Web Search connector for live web data. For image-as-query (uploading a chart to identify a part), the agent calls a native Amazon S3 Vectors index directly, because the managed knowledge base retrieval API doesn’t accept image input. Amazon S3 Vectors is a capability of Amazon Simple Storage Service (Amazon S3). A separate fixed chain (Knowledge, then Evaluation, then Supervisor) produces the formal Integration Impact Assessment (IIA) document.
Amazon Nova Multimodal Embeddings appears in two distinct roles:
- Multimodal retrieval – Datasheets, ICDs, and performance charts are embedded with Nova Multimodal Embeddings so text and visual content share one semantic space. An engineer can enter “torque curve for the 0.06 Nms wheel” or upload a chart image, and retrieval returns the matching diagram with source attribution.
- Visual similarity scoring – When two candidate parts are compared, Nova Multimodal Embeddings produces a quantitative cosine similarity between their photos, and Claude analyzes the specific physical differences (mounting pattern, connector placement, housing geometry). The score adds supporting evidence to the deterministic spec comparison, which is what the fit verdict is based on.
Prerequisites
To follow along, you need:
- An AWS account with access to Amazon Bedrock in the US East (N. Virginia) AWS Region.
- Model access to Amazon Nova Multimodal Embeddings, Claude Haiku 5.5, Claude Sonnet 5.5, and Claude Opus 5.5 in Amazon Bedrock. For model availability by Region, see Model support by AWS Region in Amazon Bedrock.
- A managed knowledge base created with Amazon Bedrock Managed Knowledge Bases, using Amazon Nova Multimodal Embeddings over your parts corpus (datasheets, ICDs, descriptions) for text and document retrieval.
- An Amazon S3 Vectors index over your part photos and datasheet chart crops, for the image-as-query path.
- An Amazon Bedrock AgentCore Gateway with the Web Search connector and a managed knowledge base target.
- Python 3.10 or later and Jupyter for running the notebooks.
- Docker, if you adapt the deployment recipe in notebook 03 to host the agent on AgentCore runtime.
- The sample code from the GitHub repository.
Solution walkthrough
The following sections describe each part of the system in the order a query uses it. We start with the parts corpus and the specialist agents, then cover routing, deterministic scoring, the two ways the assistant uses Nova Multimodal Embeddings, the fixed chain that produces formal documents, and deployment to AgentCore runtime.
The complete code sample is a set of five Jupyter notebooks in the GitHub repository, and each notebook runs on its own. The notebooks import from mei_core, a self-contained copy of the agent and tool modules in the same folder, and they include their own parts data, chart crops, and evaluation query set. You can run every snippet in this post from the notebooks without other application code.
Structure the parts corpus
The sample dataset is seven reaction wheels from a fictional manufacturer (AnyCompany) spanning 0.003–5.0 Nms of momentum storage. Each part is a folder that pairs structured data with the source documents an engineer actually reads, and this mix is what makes the corpus multimodal. The specs.json file holds the machine-readable fields that drive deterministic scoring, while the ICD, product photo, and rendered datasheet page carry the visual and narrative detail that structured fields leave out.
The specs.json file captures both the engineering specifications and a lifecycle profile, which is what lets the assistant flag obsolescence and lead-time risk alongside spec fit.
The vendor field is stated explicitly for every part. Because catalog folder IDs and file names are reused across datasets, every specialist prompt treats the structured vendor value returned by get_part_specs as authoritative and is forbidden from guessing a manufacturer from an ID, a file name, a photo, or a web search result. Taking the manufacturer from structured data keeps the assistant from attributing a part to the wrong supplier because the model thinks it recognizes the hardware.
Each part folder also carries two assets that text-only indexing cannot use. The product photo feeds visual similarity scoring, and the rendered datasheet page carries torque-box and torque-curve plots that answer performance questions no OCR text layer captures. Amazon Nova Multimodal Embeddings embeds both into the same vector space as the text, so a query can match a spec value, a paragraph, or a plot.
The following sample shows four datasheet pages from the corpus, spanning three orders of magnitude of momentum storage.
The template repeats across the family, but the product photo and the pair of performance plots change with every part. These Regions show the housing geometry, mounting pattern, torque envelope, and power draw, which the spec fields don’t state directly, so we embed them alongside the text.
Define specialists with scoped tools
Each specialist is a Strands agent with a narrow prompt and only the tools it needs. Scoping tools per specialist keeps behavior predictable, because the Knowledge specialist has no access to the catalog discovery tools and the Catalog specialist has no access to the evaluation tools. The following code creates the Evaluation specialist.
The following diagram shows how the planner routes a query to the specialists and when the supervisor synthesizes their results. The list after it describes what each specialist does.
- Catalog – Discovers parts through knowledge base search and exhaustive spec filtering (kb_search, filter_parts_by_spec, get_part_specs, get_substitution_requirements).
- Evaluation – Scores candidates deterministically and compares parts visually (score_substitution_fit, compare_parts, visual_similarity_score, check_qualification_status, generate_substitution_memo).
- Knowledge – Answers questions from datasheets and ICDs, checks live end-of-life status, and retrieves visual content (get_part_specs, web_search_eol, retrieve_visual_content).
Use a small model for routing and a large model for synthesis
Routing is a classification task with no tool calls, so it doesn’t need a large reasoning model. A Haiku-based planner returns a numbered routing plan in a couple of seconds. The Opus supervisor runs only when two or more specialists contributed, because synthesizing a single specialist’s already-complete answer adds about 8 seconds of latency with no quality gain.
Splitting the work across three model tiers matches cost and latency to each stage. Haiku classifies the query, Sonnet runs the tools, and Opus writes the combined answer, which is the step where response quality matters most.
Keep the scoring deterministic
The spec-fit evaluation runs as ordinary Python code against a hand-written requirements schema. The schema defines the critical specs and tolerance rules for each component category, and score_substitution_fit compares each spec, counts passes and flags, and surfaces lifecycle risk. Because the verdict must be reproducible for an engineering review package, no LLM is involved in this step.
The tool returns a structured verdict with an explicit disclaimer:
The specialist presents this table and explains the flags, but it can’t change a verdict. The audit trail follows the same division of work. After every evaluation, the orchestration layer reads the specialist’s tool-call history and writes the audit entry itself, so logging doesn’t depend on the model remembering to do it.
Score visual similarity with Amazon Nova Multimodal Embeddings
Form factor matters when a substitute must fit an existing bracket. The visual_similarity_score tool embeds both part photos with Nova Multimodal Embeddings and computes cosine similarity, then asks Claude to describe the specific observable differences.
The embedding similarity is deterministic and reproducible, returning around 0.84 for two wheels of the same product family and 0.40 for wheels of different classes. Claude’s vision analysis then explains what drives the difference, for example noting that one housing is roughly twice the diameter of the other and has a six-hole mounting pattern where the other has four.
Retrieve charts and diagrams with two
Auto-fetched and translated by AI Gem Box. All rights belong to the original author.