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.
The field's front door. New tweets, launches and tools land here first — each scored P/Q/S (productivity · quality · sellable, out of 9) with a plain verdict: act, watch, or skip. What proves out graduates into the Stack or the Voices; the rest decays. The freshest section on the site.
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 tools for running agent teams — harnesses, orchestration, model-routing, runtimes, memory, observability and standards.
The vocabulary. Most of it traces to Anthropic's Building Effective Agents — the canonical reference.
Five families of wrapper that spend extra compute to buy extra correctness — how an agent, or a team of them, reaches a better answer. Each card carries an honest does it work / when it backfires, and opens to a today · this week · this month ladder. Read Articulate's take →
The primary sources beneath the practice — where Anthropic lives, and the academic lineage the whole field stands on. Every link goes to the paper or post itself, not a write-up of it.
The live arguments as of mid-2026. No settled answers — that's the point.
| Kind | Name | Detail |
|---|