> ## Documentation Index
> Fetch the complete documentation index at: https://rapidreview.io/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# The gated workflow

> Why every Merv experiment passes two adversarial reviews, and how a project periodically reflects on itself.

Merv's premise: an agent doing open-ended research needs structure more than it needs freedom. So the unit of work is an **experiment** with hard gates, and the unit of learning is a **reflection wave** over many experiments.

## Experiment level

<Frame>
  <img className="block dark:hidden" src="https://mintcdn.com/rapidreview/P2fa0fqdwIeqtAmW/images/merv/experiment-workflow-light.svg?fit=max&auto=format&n=P2fa0fqdwIeqtAmW&q=85&s=b5e7a22686f3f31214cf994f4c28d95d" alt="Plan → Design review → Execute → Results review → Complete, with rejections looping back." width="992" height="256" data-path="images/merv/experiment-workflow-light.svg" />

  <img className="hidden dark:block" src="https://mintcdn.com/rapidreview/P2fa0fqdwIeqtAmW/images/merv/experiment-workflow-dark.svg?fit=max&auto=format&n=P2fa0fqdwIeqtAmW&q=85&s=dd0175e383ebe3f90bf5a8ed43316388" alt="Plan → Design review → Execute → Results review → Complete, with rejections looping back." width="992" height="256" data-path="images/merv/experiment-workflow-dark.svg" />
</Frame>

| Stage              | Who                        | Gate                                                                                                     |
| ------------------ | -------------------------- | -------------------------------------------------------------------------------------------------------- |
| **Plan**           | the research agent         | writes a plan that states the claim being tested and how the result will be judged                       |
| **Design review**  | a separate reviewer agent  | approves, or returns to Plan — repeats until approved                                                    |
| **Execute**        | the research agent         | runs the experiment (locally or in a sandbox) and submits a report with evidence                         |
| **Results review** | a different reviewer agent | approves, returns to Execute (fix the run or the report), or returns to Plan (the experiment was flawed) |
| **Complete**       | —                          | the experiment and its evidence become part of the project record                                        |

Reviewers are adversarial by design: their job is to find the reason the plan can't test its claim, or the reason the results don't support the conclusion. The brain enforces the gates — an agent can't mark an experiment complete without an approved review on record.

## Project level

<Frame>
  <img className="block dark:hidden" src="https://mintcdn.com/rapidreview/P2fa0fqdwIeqtAmW/images/merv/project-workflow-light.svg?fit=max&auto=format&n=P2fa0fqdwIeqtAmW&q=85&s=5cda0509d3149d20e8a9cdee56b5968d" alt="Completed experiments fan out to three core lenses plus two written for the wave, then Synthesis, Reflection review, Publish." width="992" height="296" data-path="images/merv/project-workflow-light.svg" />

  <img className="hidden dark:block" src="https://mintcdn.com/rapidreview/P2fa0fqdwIeqtAmW/images/merv/project-workflow-dark.svg?fit=max&auto=format&n=P2fa0fqdwIeqtAmW&q=85&s=522470adb4c24f8bd0a485bd006dab5e" alt="Completed experiments fan out to three core lenses plus two written for the wave, then Synthesis, Reflection review, Publish." width="992" height="296" data-path="images/merv/project-workflow-dark.svg" />
</Frame>

A reflection wave snapshots every terminal experiment and every claim; three fixed lenses plus two written for the wave analyze it independently; the synthesis is reviewed before it's published. [Reflection waves](/docs/merv/concepts/reflection-waves)

## Why gates and not guidelines

* A reviewer that can only advise gets ignored under time pressure. A gate can't be.
* Separating planner, executor, and reviewer into different agents removes the "grading your own homework" failure.
* Recording the review chain makes every conclusion in the project traceable to the evidence and the reviewer who accepted it.

Details: [Experiments and reviews](/docs/merv/concepts/experiments-and-reviews) · [Reflection waves](/docs/merv/concepts/reflection-waves).