38 lines
1019 B
Markdown
38 lines
1019 B
Markdown
# FAQ
|
|
|
|
## How is an AI student's learned mastery represented?
|
|
|
|
As structured operational state, including:
|
|
- mastered concepts
|
|
- evaluator summaries
|
|
- weak dimensions
|
|
- evidence records
|
|
- artifacts
|
|
- capability export
|
|
|
|
## Does Didactopus change the AI model weights?
|
|
|
|
No. In the current architecture, Didactopus supervises and evaluates a learner
|
|
agent, but it does not retrain the foundation model.
|
|
|
|
## How is an AI student ready to be put to work?
|
|
|
|
Readiness is represented operationally. A downstream system can inspect:
|
|
- which concepts are mastered
|
|
- which weak dimensions remain
|
|
- what artifacts were produced
|
|
- what evaluator evidence supports deployment
|
|
|
|
## Is the capability export a certification?
|
|
|
|
Not by itself. It is a structured mastery report. In future, it could be combined
|
|
with formal evaluators, signed evidence records, and policy rules.
|
|
|
|
## Why is this useful?
|
|
|
|
Because it allows Didactopus outputs to feed into:
|
|
- task routing
|
|
- portfolio review
|
|
- benchmark comparison
|
|
- agent deployment policies
|