← Back
AWS ML Blog

How skills and agents work in AWS Quick

•14 min read•
#agents
Level:Intermediate
For:AI Engineers
✦TL;DR

AWS Quick introduces configurable AI agents that execute repeatable tasks by loading skills, acting through connectors, and grounding responses in user‑provided data sources such as spaces, knowledge bases, datasets, and dashboards. The built‑in “Quick” agent has no fixed scope and can access any resources the user can, while custom agents can be scoped to specific instructions, spaces, connectors, and skills for targeted use cases like HR onboarding. Engineers can publish and share these agents within an AWS Quick account, enabling team‑wide automation of routine workflows.

⚡ Key Takeaways

  • Custom agents are scoped to specific instructions, spaces, connectors, and skills, allowing fine‑grained permission control.
  • Agents load required skills at runtime and execute actions via connectors to external services.
  • Quick agents ground their answers in attached data sources, reducing the need to pre‑define required tools for each request.
  • Agents can be shared with other users and groups after testing and publishing within the same AWS Quick account.
  • The default “Quick” agent automatically accesses any resources the user can reach, eliminating upfront data‑tool configuration.
💡 Why It Matters

By encapsulating repeatable workflows into sharable agents, engineers can rapidly automate routine tasks across teams, cutting down on repetitive prompting and manual integration effort while maintaining strict access controls.

✅ Practical Steps

  1. Create a custom agent in AWS Quick, define its instructions, and limit its scope to the required spaces, connectors, and skills for your use case.
  2. Attach a space (curated collection of documents, dashboards, etc.) to the agent so it can ground its responses in relevant data.
  3. Test the agent, then publish and share it with other users or groups in your AWS Quick account.

Want the full story? Read the original article.

Read on AWS ML Blog ↗

More like this

New in AWS Quick: More capable flows, an updated web experience, and agents that work together

AWS ML Blog•#agents

How Google Duplex evolved to also call businesses for you in Gemini

Google Research•#agents

Genie ZeroOps, now in public beta: An autonomous agent that fixes data pipelines, with lessons from 80,000 customer issues

Databricks Blog•#agents

Towards a Science of Capable Autonomous Agents & Provable Safety — Part II

CMU ML Blog•#agents

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING