AI Agents & Automation in Practice

How AI agents and automation work on real processes, written by the engineers who built them.

  1. 16

    Single Agent or Multi-Agent? Start With the Simplest Design

    Anthropic's own guidance on workflows, single agents and multi-agent systems: when extra agents help, what they cost, and how to test before you build.

    AI Agents & Automation in Practice4 min readMudabbir Hasan

  2. 10

    Internal AI Assistant: How to Avoid Leaking the Wrong Data

    Enforce permissions in the retrieval layer, not the prompt. OWASP's guidance for internal AI assistants, plus a short test you can run before launch.

    AI Agents & Automation in Practice3 min readMudabbir Hasan

  3. 06

    Build or Buy an AI Agent? Decide Workflow by Workflow

    Most build-vs-buy AI guides are written by firms that sell builds. A per-workflow test from their shared criteria, and the statistics not to trust.

    AI Agents & Automation in Practice4 min readMudabbir Hasan

  4. 05

    When Should an AI Agent Escalate to a Human?

    Design escalation by what an action can break, not only by model confidence. Risk tiers, trigger signals and logging for AI agents that hand off to people.

    AI Agents & Automation in Practice4 min readMudabbir Hasan