L6 Orchestration
Checkpoints and rewind
Save the workspace before the agent edits it, and let a rewind take files and conversation back together.
Why it matters
An agent that edits files will sometimes make a mess. A rewind only helps if it brings back the files and the conversation to the same point and says what it cannot undo.
What it takes, by kind of agent
- Conversational assistantOptional
- CodingOptional
- Deep researchOptional
- Browser/GUINot applicable
How well it is studied
- Harnesses checked
- 7
- Checked facts behind it
- 88
See the 88 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
- Human approvalSettled practice
Pauses a risky action until a person approves, changes or refuses it, then carries on with a valid history.
- Assistant Must-have
- Coding Must-have
- Research Must-have
- Browser Must-have
- 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