Urgent.News

What's breaking now, across thousands of outlets.

Tech

Part 29: Agent cards in practice

Part 29 · One Agent, Five Platforms An agent card is a CV for an agent. It tells other agents who it is, what it can do, where to reach it and how to prove who's calling. And like a CV, what you leave off matters as much as what you put on. Part 28 had the supplier-communication agent on Azure read the invoice agent's card before asking about invoice 4471. This part writes both cards. It's based…

An agent card is a self-describing manifest for an agent, containing essential information such as its name, description, version, supported interfaces, capabilities, security schemes, security requirements, default input and output modes, skills, and optional elements like signatures and examples. Each field plays a crucial role in determining how the agent functions and interacts with others.

For the invoice exception agent, which runs on MuleSoft Agent Fabric, the card is concise and informative. It specifies that the agent is a read-only, capable of push notifications but not streaming. The security scheme ensures callers authenticate using their Entra agent identity, with a read scope limited to invoice status. The gateway URL points to Omni Gateway, abstracting the underlying Mule flow and process API.

The only skill offered is to explain an invoice exception, clearly stating it never changes the invoice itself. No sensitive data or internal details are included, aligning with the specification's recommendation to avoid security risks.

Similarly, the supplier-communication agent on Azure Foundry advertises a skill to draft a reply to the supplier once a fix is approved, but the actual sending of the email is handled internally within the supplier agent's process. This separation of concerns prevents the card from suggesting actions that occur outside the agent's control, adhering to the rule that no write skills should be included on a card intended for external calls.

Both cards exemplify best practices in designing agent cards, emphasizing clarity, security, and minimalism to facilitate effective communication between agents while safeguarding sensitive information.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

Keep CSS scroll snap targets visible below a fixed header

A scroll-snap layout can select the correct section and still feel broken: the section heading lands beneath a fixed header. The snap rule is not necessarily wrong.

  • Use scroll-padding-top to reserve space for fixed header.
  • Maintain scroll-snap-align: start and vertical snapping.
  • Verify heading's top edge is at or below header's bottom edge.

Shopify's image_tag already lazy-loads. Here's what it leaves to you.

I used to write my own lazy-loading logic in every Shopify theme. Then I read the image_tag docs properly and deleted most of it.

  • Shopify's imagetag implements lazy-loading but lacks full performance optimization
  • Imagetag adds width, height, srcset, lazy-loading for non-critical images, and uses WebP/AVIF

How to Answer 'Tell Me About Yourself' in a Scrum Master Interview

How to Answer “Tell Me About Yourself” in a Scrum Master Interview The best way to answer “Tell me about yourself” in a Scrum Master interview is to stop listing your certifications and start telling…

  • Focus on optimizing flow and eliminating systemic blockers rather than managing Jira tickets
  • Bridge technical and business perspectives to convert roadmaps into clear, value-driven sprints
  • Cultivate psychological safety through constructive Sprint Retrospectives and inclusive daily syncs

More from Wednesday 18 November →