L6 Orchestration
Crash recovery
Saves the agent's work step by step, so it can pick up after a crash exactly where it stopped.
Why it matters
Agents run for a long time and can be stopped at any moment. Without safe saving and a clean resume, a crash loses the work or leaves a session the model provider refuses to continue.
What to build
Commit each step in a fenced transaction
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
- 32
- Checked facts behind it
- 499
See the 499 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
- 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
- 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