A field guide from Articulate · the agency · 2026 edition

Running AI agents is a discipline now.

The map of agent management — the voices worth following, the tools that run agent teams, the patterns that hold them together, and the questions still being argued. For builders, agencies, and anyone giving agents real work.

Seeded by Brian Casel's "My Multi-Agent Team with OpenClaw" — a 4-agent team run like staff. Kept fresh by Benjamin, the Better publisher.
Data is loading from the site's JSON files — if this persists, the four data files (voices/tools/concepts/debates) didn't load. On the live domain they sit at the site root.

The Voices

Who to read on running agents — practitioners and the people who own the agent-building narrative. Handles verified at first edition; unverified ones are flagged, not faked.

The Stack

The tools for running agent teams — harnesses, orchestration, model-routing, runtimes, memory, observability and standards.

The Patterns

The vocabulary. Most of it traces to Anthropic's Building Effective Agents — the canonical reference.

Open Questions

The live arguments as of mid-2026. No settled answers — that's the point.

Library — every entry, queryable.

KindNameDetail