Empirica
See our work
Sign inGet in touch

← All paths

Applied AI

Agent architecture without the hype

By the end you'll know when to use a single agent versus a multi-agent system, what observability requires, and the failure modes that don't show up in toy demos.

4 steps · ~20 minutes of reading total

  1. 1

    The agent architecture decision

    Empirica

    The single-vs-multi-agent decision, framed around failure tolerance, observability, and whether subtasks are actually independent.

  2. 2

    Milestone: you can name three failure modes only multi-agent systems have

    Milestone

    If you can't name them, you don't yet know whether your design is single or multi by accident.

  3. 3

    Anthropic — Building effective agents

    Anthropic ↗

    First-principles framing on when to use workflows vs agents. Worth reading in full before committing to either.

  4. 4

    The real cost of LLM API calls

    Empirica

    Agent loops multiply token usage in ways that aren't obvious from a small demo. Architecture choices have direct cost consequences.

← All Guideline PathsHow Empirica Stars work
About·The Forward-Data Process·See our work·Data Snapshot·Agent-Readiness Benchmark·Verify·Methodology·Contact·Sign in·Privacy·Terms·Services terms
© 2026 Empirica Technologies Pty Ltd · ABN 76 698 226 247 · All rights reserved.
empiricaai.org