The model is not enough. It needs a reliable system around it.

Strong in a demonstration, fragile in production

An agent can succeed in a demonstration and fail in your operations. The harness organizes what it knows, what it can do and what must be checked.

The system around the model

Instructions define the work. Context and memory provide useful information. Tools and permissions bound actions. Checks and supervision control decisions. Cost tracking helps monitor operations.

1. Instructions
2. Context
3. Memory
4. Tools
5. Permissions
6. Checks
7. Supervision
8. Costs

Two types of intervention

Build a new harness: start from tasks, define access and write checks before connecting tools.

Audit and correct an existing system: reproduce its failures, prioritize corrections and test them on the same tasks.

Evaluation protocol

We use the same tasks before and after corrections. Criteria are written before testing and results are recorded, including failures.

Human supervision remains defined for actions that commit the company.

Deliverables

An audit, a prioritized correction list, a rebuilt harness, a test suite and an operations guide, depending on the agreed scope.

Limits

A successful test does not prove reliability in every context. Untested cases still need evaluation. No performance measurements are published here.