L6 Orchestration

Safe repeats

Makes sure that running a step again, after a retry, a crash or a re-fire, never repeats a real-world action.

Open problem

Why it matters

Retries and resumes happen all the time in an agent. Without this, one timeout can turn into a double payment or a second email.

What to build

Journal each call and fail closed on replay

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

What these levels mean

How well it is studied

Harnesses checked: 22
Checked facts behind it: 336

See the 336 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.

See the evidence in the app

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
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