agents

DE//AGENT currently lists 2 resources under agents: 2 tutorials. Everything below is derived from the live registry — counts, capabilities, verification state and security posture come from the curated records, never from marketing copy.

Documented learning objectives across these resources:

• Name the four parts of an agent — model, tools, loop, guardrails — via What makes an agent — model, tools, loop, guardrails
• Identify each part in a real registry agent — via What makes an agent — model, tools, loop, guardrails
• Say where DE agents fit — review, triage and planning under guardrails — via What makes an agent — model, tools, loop, guardrails
• Install a registry skill and bind an MCP server with least-privilege credentials — via Wire cloud tooling — registry skills, MCP servers, and one review workflow
• Compose skills and MCP servers into a single review workflow — via Wire cloud tooling — registry skills, MCP servers, and one review workflow
• Keep agent access read-only by default — via Wire cloud tooling — registry skills, MCP servers, and one review workflow

These resources map to stages: Agentic Data Engineering (1), Cloud (1). Follow the four-phase roadmap to place this topic inside a progression instead of learning it in isolation.

Every entry, its shape and its trust state — sorted by the registry's composite score. This table is the honest version of a marketing comparison: no sponsored placements, no unverifiable claims.

How scores are computed: source quality score.

Highest composite score first:

1. What makes an agent — model, tools, loop, guardrails score 34.15 — beginner
2. Wire cloud tooling — registry skills, MCP servers, and one review workflow score 34.15 — beginner

Scores rank provenance, completeness and trust — read how verification works before adopting anything.

Start here if you're new: What makes an agent — model, tools, loop, guardrails, Wire cloud tooling — registry skills, MCP servers, and one review workflow.

• What makes an agent — model, tools, loop, guardrails — Build the map before touching anything: an agent is a model that reasons, tools that act, a loop that iterates, and guardrails that bound it. Meet a real data-engineering agent fro… details
• Wire cloud tooling — registry skills, MCP servers, and one review workflow — Wire the registry's cloud tooling into one agent workflow: install the Glue and Athena review skills, bind the AWS MCP server to a least-privilege profile, and compose both skills … details

Adjacent topics: tutorial (2 shared).

Study path: the roadmap places this topic in a progression · the scoring model explains the numbers · the trust rule catalog shows every security check these entries passed through.