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

# What Is a Meta-Harness?

> The layer that runs several agent harnesses as a team: roles, handoffs, reviews that run a step again, a person at the gate, and a record.

Run several agent harnesses as one team, and the layer you're writing is a
meta-harness: it gives each a role, hands work between them, runs a step again when a review
fails, asks a person at the gate, and keeps a record of every step. The
inner layer, one model and one loop, is the neighbour term,
[an agent harness](/docs/glossary/agent-harness).

## In Obversa

Obversa is that outer layer, and the team is a file. Two engines from
different families on one team is the smallest meta-harness:

```ts examples/teams/writer-reviewer-pair.ts (excerpt) {2-3} theme={null}
    roles: {
      write: engines.claude('claude-sonnet-4-5'),
      review: [engines.codex('gpt-5.6-luna')],
    },
```

One harness writes, another reads its work, and the outer layer decides
what happens with the findings. The whole file and a real run are on
[A writer and a reviewer](/docs/patterns/writer-and-reviewer).

## Who owns what

| The inner harness does | The outer layer does |
| - | - |
| Reads the model's answer and calls tools. | Decides which harness runs next, with which files. |
| Keeps memory inside one session. | Keeps the record across every step and every seat. |
| Stops when its own task is done. | Runs the writer again when the review says no. |
| Has no idea a person exists. | Pauses on a question. The answer arrives through the callbacks client. |

The outer layer is a written-down process. The engines do all the thinking,
one bounded call at a time, and the record outlives the run: a run that
records writes every step as a line in a file you can read afterwards.

Give the review to a seat from another model family. Models score their own
writing higher than other models' writing, even where people rate the two
as equal ([Panickssery, Bowman and Feng, 2024](https://arxiv.org/abs/2404.13076)).
You declare that reviewer in the outer layer, and `workflow()` refuses one
from the writer's own family.

## Next steps

* [What is an agent harness?](/docs/glossary/agent-harness): the inner layer.
* [Feature delivery](/docs/workflows/feature-team): a seven-step team on real
  engines.
* [The record](/docs/concepts/record): what the outer layer writes down.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.