# American Express Technology

American Express Technology Open Source and Blog

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Smart Retrieval, Trusted Agents

DevFeed: [Smart Retrieval, Trusted Agents](<https://devfeed.tech/articles/smart-retrieval-trusted-agents-107190.md>)

Original publisher: [Read original article](<https://americanexpress.io/smart-retrieval-trusted-agents/>)

Published: 2026-10-29T04:00:00Z

Content type: article

Language: en

Sources: [American Express Technology](<https://devfeed.tech/sources/american-express-technology.md>)

Topics: [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [Factuality scoring in AI](<https://devfeed.tech/topics/factuality-scoring-in-ai.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [hybrid-graph](<https://devfeed.tech/tags/hybrid-graph.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>)

### AI overview

Reliable enterprise retrieval must distinguish a document's relevance, freshness, and authority: a recent, relevant exception may not govern another service. The article proposes separate curated knowledge for owned, reviewed standards and live retrieval for changing tickets, incidents, and design reviews. A router selects either path or both before synthesis; source type, owner, version, timestamp, scope, and expiry inform precedence. When evidence conflicts or is weak, the agent should expose uncertainty and refer the question to a human. The example shows a billing-only shared-token exception does not override the standard for a notifications service. Implementation guidance includes preserving provenance at ingestion, keeping curated guidance small and versioned, starting routing with rules, and evaluating routing, evidence selection, conflicts, unsupported answers, latency, and cost separately. The added complexity may suit governance-heavy questions needing both policy and current context; simpler retrieval may suffice for small or low-governance knowledge bases.

### Source excerpt

How combining trusted enterprise knowledge with real-time information helps AI agents deliver more accurate, reliable answers.

## Intent Intelligence: Building Trust in Agentic Commerce

DevFeed: [Intent Intelligence: Building Trust in Agentic Commerce](<https://devfeed.tech/articles/intent-intelligence-building-trust-in-agentic-commerce-85726.md>)

Original publisher: [Read original article](<https://americanexpress.io/intent-intelligence-building-trust-in-agentic-commerce/>)

Published: 2026-10-13T04:00:00Z

Content type: article

Language: en

Sources: [American Express Technology](<https://devfeed.tech/sources/american-express-technology.md>)

Topics: [agentic commerce fraud](<https://devfeed.tech/topics/agentic-commerce-fraud.md>), [trust](<https://devfeed.tech/topics/trust.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [fake account fraud](<https://devfeed.tech/topics/fake-account-fraud.md>), [fraud signal sharing](<https://devfeed.tech/topics/fraud-signal-sharing.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-commerce](<https://devfeed.tech/tags/agentic-commerce.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [fraud-prevention](<https://devfeed.tech/tags/fraud-prevention.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

The article describes Intent Intelligence, a set of services for capturing and authenticating a customer's purchase intent before an AI agent transacts. It explains how intent constraints and proof tokens can help issuers scope payment credentials, assess fraud and dispute risk, and validate agent purchases against user-approved boundaries.

### Source excerpt

Novel approach is designed to capture, authenticate, and preserve customer purchase intent as AI agents transact on their behalf.

## Advancing Centurion Lounges' Cloud Platform for Enterprise Scale

DevFeed: [Advancing Centurion Lounges' Cloud Platform for Enterprise Scale](<https://devfeed.tech/articles/advancing-centurion-lounges-cloud-platform-for-enterprise-scale-56633.md>)

Original publisher: [Read original article](<https://americanexpress.io/advancing-centurion-lounges-cloud-platform-for-enterprise-scale/>)

Published: 2026-09-21T04:00:00Z

Content type: article

Language: en

Sources: [American Express Technology](<https://devfeed.tech/sources/american-express-technology.md>)

Topics: [Cloud](<https://devfeed.tech/topics/cloud.md>), [migration](<https://devfeed.tech/topics/migration.md>), [Enterprise Architecture](<https://devfeed.tech/topics/enterprise-architecture.md>), [Resilience](<https://devfeed.tech/topics/resilience.md>), [Deployment](<https://devfeed.tech/topics/deployment.md>)

Tags: [acquisition](<https://devfeed.tech/tags/acquisition.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-architecture](<https://devfeed.tech/tags/enterprise-architecture.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [migration](<https://devfeed.tech/tags/migration.md>), [modernizing](<https://devfeed.tech/tags/modernizing.md>), [resilience](<https://devfeed.tech/tags/resilience.md>)

### AI overview

An American Express engineering team modernized the cloud platform inherited through the LoungeBuddy acquisition. The work focused on stabilizing operations, improving resilience and enterprise controls, and migrating applications into a standardized target environment.

### Source excerpt

Modernizing an acquired cloud platform for enterprise scale and resilience.

## Context Inspector: Measuring Context Quality Before the LLM Call

DevFeed: [Context Inspector: Measuring Context Quality Before the LLM Call](<https://devfeed.tech/articles/context-inspector-measuring-context-quality-before-the-llm-call-56637.md>)

Original publisher: [Read original article](<https://americanexpress.io/context-inspector-measuring-context-quality-before-the-llm-call/>)

Published: 2026-08-31T04:00:00Z

Content type: article

Language: en

Sources: [American Express Technology](<https://devfeed.tech/sources/american-express-technology.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [ai evaluation](<https://devfeed.tech/topics/ai-evaluation.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai-evaluation](<https://devfeed.tech/tags/ai-evaluation.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [llm](<https://devfeed.tech/tags/llm.md>), [practical](<https://devfeed.tech/tags/practical.md>), [rag](<https://devfeed.tech/tags/rag.md>)

### AI overview

A practical framework for evaluating the quality of retrieved context in RAG systems before it reaches an LLM. The article describes how to identify missing, stale, conflicting, or otherwise unreliable evidence before an inference call.

### Source excerpt

A practical framework for identifying gaps, conflicts, and quality risks in retrieved context before they reach the model.

## Character Counts: Why "30 Characters Max" Is Usually Wrong

DevFeed: [Character Counts: Why "30 Characters Max" Is Usually Wrong](<https://devfeed.tech/articles/character-counts-why-30-characters-max-is-usually-wrong-56636.md>)

Original publisher: [Read original article](<https://americanexpress.io/character-counts-why-30-characters-max-is-usually-wrong/>)

Author: Michael J. Bailey

Published: 2026-08-18T04:00:00Z

Content type: tutorial

Language: en

Sources: [American Express Technology](<https://devfeed.tech/sources/american-express-technology.md>)

Topics: [Requirements](<https://devfeed.tech/topics/requirements.md>), [User Experience](<https://devfeed.tech/topics/user-experience.md>), [implementation](<https://devfeed.tech/topics/implementation.md>), [test](<https://devfeed.tech/topics/test.md>), [Code](<https://devfeed.tech/topics/code.md>)

Tags: [best-practices](<https://devfeed.tech/tags/best-practices.md>), [counts](<https://devfeed.tech/tags/counts.md>), [limits](<https://devfeed.tech/tags/limits.md>), [test](<https://devfeed.tech/tags/test.md>), [unicode](<https://devfeed.tech/tags/unicode.md>), [user-experience](<https://devfeed.tech/tags/user-experience.md>)

### AI overview

This tutorial explains why text-field character limits become ambiguous with Unicode. It distinguishes code points, code units, glyphs, and grapheme clusters, and discusses how product requirements, clients, and backends can enforce limits consistently.

### Source excerpt

How to define, count, and validate text-field limits with grapheme clusters.

## Improving Correctness in Agentic AI with Execution Guardrails

DevFeed: [Improving Correctness in Agentic AI with Execution Guardrails](<https://devfeed.tech/articles/improving-correctness-in-agentic-ai-with-execution-guardrails-56639.md>)

Original publisher: [Read original article](<https://americanexpress.io/improving-correctness-in-agentic-ai-with-execution-guardrails/>)

Published: 2026-07-30T04:00:00Z

Content type: article

Language: en

Sources: [American Express Technology](<https://devfeed.tech/sources/american-express-technology.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [Orchestration](<https://devfeed.tech/topics/orchestration.md>), [Security](<https://devfeed.tech/topics/security.md>), [Automation](<https://devfeed.tech/topics/automation.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [ai-reliability](<https://devfeed.tech/tags/ai-reliability.md>), [automation](<https://devfeed.tech/tags/automation.md>), [guardrails](<https://devfeed.tech/tags/guardrails.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [prompt-engineering](<https://devfeed.tech/tags/prompt-engineering.md>), [retry](<https://devfeed.tech/tags/retry.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

The article explains why agentic AI systems can perform workflow actions in the wrong order and describes execution-time tool sequence guardrails. These controls validate requested tool calls against workflow rules before actions reach backend systems, complementing prompt engineering, function constraints, and retry logic.

### Source excerpt

Why execution-time validation matters for agentic AI.

## From Clicks to Trust: Rethinking Recommendations

DevFeed: [From Clicks to Trust: Rethinking Recommendations](<https://devfeed.tech/articles/from-clicks-to-trust-rethinking-recommendations-56638.md>)

Original publisher: [Read original article](<https://americanexpress.io/from-clicks-to-trust-rethinking-recommendations/>)

Published: 2026-07-14T04:00:00Z

Content type: article

Language: en

Sources: [American Express Technology](<https://devfeed.tech/sources/american-express-technology.md>)

Topics: [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>), [Responsibility & Safety](<https://devfeed.tech/topics/responsibility-safety.md>), [AI Architecture](<https://devfeed.tech/topics/ai-architecture.md>), [AI Strategy](<https://devfeed.tech/topics/ai-strategy.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [engagement](<https://devfeed.tech/tags/engagement.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [goals](<https://devfeed.tech/tags/goals.md>), [governance](<https://devfeed.tech/tags/governance.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [recommendation-systems](<https://devfeed.tech/tags/recommendation-systems.md>), [recommendations](<https://devfeed.tech/tags/recommendations.md>), [responsible-ai](<https://devfeed.tech/tags/responsible-ai.md>), [retention](<https://devfeed.tech/tags/retention.md>), [transparency](<https://devfeed.tech/tags/transparency.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

This article argues that recommendation systems optimized mainly for engagement can gradually reduce discovery, usefulness, and user trust. It recommends evaluating and governing systems with broader objectives such as diversity, novelty, fatigue reduction, and long-term user value.

### Source excerpt

Building recommendation systems that earn trust through relevance, discovery, and transparency.

## When Innovation Meets Discipline: Inside Amex's Patent Strategy

DevFeed: [When Innovation Meets Discipline: Inside Amex's Patent Strategy](<https://devfeed.tech/articles/when-innovation-meets-discipline-inside-amex-s-patent-strategy-56642.md>)

Original publisher: [Read original article](<https://americanexpress.io/when-innovation-meets-discipline-inside-amexs-patent-strategy/>)

Published: 2026-06-30T04:00:00Z

Content type: article

Language: en

Sources: [American Express Technology](<https://devfeed.tech/sources/american-express-technology.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Authentication](<https://devfeed.tech/topics/authentication.md>), [Network](<https://devfeed.tech/topics/network.md>), [Security](<https://devfeed.tech/topics/security.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-ml](<https://devfeed.tech/tags/ai-ml.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [innovation](<https://devfeed.tech/tags/innovation.md>), [inventions](<https://devfeed.tech/tags/inventions.md>), [network](<https://devfeed.tech/tags/network.md>), [patents](<https://devfeed.tech/tags/patents.md>), [process](<https://devfeed.tech/tags/process.md>), [security](<https://devfeed.tech/tags/security.md>), [strategy](<https://devfeed.tech/tags/strategy.md>), [teams](<https://devfeed.tech/tags/teams.md>)

### AI overview

American Express describes a patent strategy that evaluates inventions for novelty, business relevance, patentability, and detectability. A multidisciplinary board prioritizes high-impact innovations across payments, identity and authentication, digital wallets, cryptographic and network security, and AI/ML applications.

### Source excerpt

How American Express transforms promising ideas into strategically protected innovations

## Cell-Based Architecture for Resilient Payment Systems

DevFeed: [Cell-Based Architecture for Resilient Payment Systems](<https://devfeed.tech/articles/cell-based-architecture-for-resilient-payment-systems-56635.md>)

Original publisher: [Read original article](<https://americanexpress.io/cell-based-architecture-for-resilient-payment-systems/>)

Published: 2026-06-11T04:00:00Z

Content type: article

Language: en

Sources: [American Express Technology](<https://devfeed.tech/sources/american-express-technology.md>)

Topics: [cell-based-architecture](<https://devfeed.tech/topics/cell-based-architecture.md>), [distributed-systems](<https://devfeed.tech/topics/distributed-systems.md>), [Microservices](<https://devfeed.tech/topics/microservices.md>), [Scalability](<https://devfeed.tech/topics/scalability.md>), [Availability](<https://devfeed.tech/topics/availability.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>), [data](<https://devfeed.tech/topics/data.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [cell-based-architecture](<https://devfeed.tech/tags/cell-based-architecture.md>), [cloud-native](<https://devfeed.tech/tags/cloud-native.md>), [databases](<https://devfeed.tech/tags/databases.md>), [distributed-systems](<https://devfeed.tech/tags/distributed-systems.md>), [high-availability](<https://devfeed.tech/tags/high-availability.md>), [latency](<https://devfeed.tech/tags/latency.md>), [low-latency](<https://devfeed.tech/tags/low-latency.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [payment-systems](<https://devfeed.tech/tags/payment-systems.md>), [payments](<https://devfeed.tech/tags/payments.md>), [resiliency](<https://devfeed.tech/tags/resiliency.md>), [scalability](<https://devfeed.tech/tags/scalability.md>), [scale](<https://devfeed.tech/tags/scale.md>), [systems](<https://devfeed.tech/tags/systems.md>)

### AI overview

American Express describes how it uses cell-based architecture in a global payments platform to contain failures, reduce blast radius, maintain low-latency processing, and scale capacity without expanding failure domains. The approach groups related microservices, databases, and other components into independent cells.

### Source excerpt

How American Express uses cell-based architecture to deliver resilient, low-latency payments at global scale.

## Reimagining Software Delivery with AI

DevFeed: [Reimagining Software Delivery with AI](<https://devfeed.tech/articles/reimagining-software-delivery-with-ai-56640.md>)

Original publisher: [Read original article](<https://americanexpress.io/reimagining-software-delivery-with-ai/>)

Published: 2026-05-20T04:00:00Z

Content type: article

Language: en

Sources: [American Express Technology](<https://devfeed.tech/sources/american-express-technology.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [sdlc](<https://devfeed.tech/topics/sdlc.md>), [Software](<https://devfeed.tech/topics/software.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>), [implementation](<https://devfeed.tech/topics/implementation.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [ideation](<https://devfeed.tech/tags/ideation.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [lifecycle](<https://devfeed.tech/tags/lifecycle.md>), [product](<https://devfeed.tech/tags/product.md>), [qa](<https://devfeed.tech/tags/qa.md>), [software](<https://devfeed.tech/tags/software.md>), [software-delivery](<https://devfeed.tech/tags/software-delivery.md>), [spec-driven](<https://devfeed.tech/tags/spec-driven.md>)

### AI overview

AI is presented as a lifecycle-wide partner for software delivery, supporting work from ideation and requirements through implementation, testing, deployment, and feedback. The article argues that meaningful improvement depends on cross-functional alignment rather than simply selecting the highest-performing model.

### Source excerpt

AI is reshaping the lifecycle by reducing ambiguity early, strengthening alignment across teams, and accelerating the journey from ideation to implementation.

## Trust Without Disclosure: Why Zero-Knowledge Proofs Could Help Build Trust in AI Agents

DevFeed: [Trust Without Disclosure: Why Zero-Knowledge Proofs Could Help Build Trust in AI Agents](<https://devfeed.tech/articles/trust-without-disclosure-why-zero-knowledge-proofs-could-help-build-trust-in-ai-agents-56641.md>)

Original publisher: [Read original article](<https://americanexpress.io/trust-without-disclosure-why-zero-knowledge-proofs-could-help-build-trust-in-ai-agents/>)

Author: Pratyaksh Gupta

Published: 2026-05-06T04:00:00Z

Content type: opinion

Language: en

Sources: [American Express Technology](<https://devfeed.tech/sources/american-express-technology.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [trust](<https://devfeed.tech/topics/trust.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [sensitive data](<https://devfeed.tech/topics/sensitive-data.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>), [Math and Logic](<https://devfeed.tech/topics/math-and-logic.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [cryptographic](<https://devfeed.tech/tags/cryptographic.md>), [cryptography](<https://devfeed.tech/tags/cryptography.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [sensitive-data](<https://devfeed.tech/tags/sensitive-data.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

The article explains how zero-knowledge proofs could help AI agents verify permissions and claims without revealing sensitive information. It presents this as a potential approach to building trust in autonomous, cross-system agent workflows.

### Source excerpt

As AI agents begin operating across systems with greater autonomy, ZK proofs may help specific claims or permissions without exposing sensitive data.

## Building Trust in AI-Powered Transactions with Amex Agentic Commerce Experiences (ACE) Developer Kit

DevFeed: [Building Trust in AI-Powered Transactions with Amex Agentic Commerce Experiences (ACE) Developer Kit](<https://devfeed.tech/articles/building-trust-in-ai-powered-transactions-with-amex-agentic-commerce-experiences-ace-developer-kit-56634.md>)

Original publisher: [Read original article](<https://americanexpress.io/building-trust-in-ai-powered-transactions-with-amex-agentic-commerce-experiences/>)

Published: 2026-04-22T04:00:00Z

Content type: article

Language: en

Sources: [American Express Technology](<https://devfeed.tech/sources/american-express-technology.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Transactions](<https://devfeed.tech/topics/transactions.md>), [trust](<https://devfeed.tech/topics/trust.md>), [Authentication](<https://devfeed.tech/topics/authentication.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>), [account](<https://devfeed.tech/topics/account.md>)

Tags: [account](<https://devfeed.tech/tags/account.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-commerce](<https://devfeed.tech/tags/agentic-commerce.md>), [ai](<https://devfeed.tech/tags/ai.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [developer](<https://devfeed.tech/tags/developer.md>), [partner-integrations](<https://devfeed.tech/tags/partner-integrations.md>), [payment](<https://devfeed.tech/tags/payment.md>), [permissions](<https://devfeed.tech/tags/permissions.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

American Express describes its Agentic Commerce Experiences Developer Kit, which enables agents to execute intent-driven transactions on behalf of card members. The article focuses on delegated authority, identity, authentication, permissions, guardrails, and accountability.

### Source excerpt

A model for secure, intent-driven transactions executed by agents on behalf of Card Members.