L6 Orchestration
Human approval
Pauses a risky action until a person approves, changes or refuses it, then carries on with a valid history.
Why it matters
Some actions cannot be undone, such as sending, paying or deleting. A pause that loses the waiting action or breaks the history either stops the work or lets the action slip through.
What to build
Durable in-loop gate on risky calls
The default the research recommends. The reasoning and the code behind it are in the app.
What it takes, by kind of agent
- Conversational assistantMust-have
- CodingMust-have
- Deep researchMust-have
- Browser/GUIMust-have
How well it is studied
- Harnesses checked
- 31
- Checked facts behind it
- 398
See the 398 checked facts and how each harness does it
The facts, the code lines they come from and the rules for this topic are in the app. Sign in with Google; new accounts are approved by hand.
Also in L6 Orchestration
- Crash recoverySettled practice
Saves the agent's work step by step, so it can pick up after a crash exactly where it stopped.
- Assistant Must-have
- Coding Must-have
- Research Must-have
- Browser Must-have
- Sub-agentsSettled practice
Hands part of a task to a child agent that works in a clean context and returns a short answer.
- Assistant Optional
- Coding Optional
- Research Must-have
- Browser Not applicable
- Proactive triggersEmerging
Lets the agent start a turn by itself, on a schedule or an event, once per due time and only when it has something to say.
- Assistant Must-have
- Coding Not applicable
- Research Not applicable
- Browser Not applicable
- Safe repeatsOpen problem
Makes sure that running a step again, after a retry, a crash or a re-fire, never repeats a real-world action.
- Assistant Must-have
- Coding Must-have
- Research Must-have
- Browser Must-have
- Checkpoints and rewindEmerging
Save the workspace before the agent edits it, and let a rewind take files and conversation back together.
- Assistant Optional
- Coding Optional
- Research Optional
- Browser Not applicable