om
AppThentic's own interviewing model, what it does, and why facts are not stored in it.
om is the model AppThentic uses to read your systems, decide what to ask, and talk to owners. It is purpose-built for this job and runs on your infrastructure.
What om does
- Reads code and the conversations around it, and finds business rules.
- Decides which gaps are worth an owner’s attention.
- Writes short, specific questions, and understands the answers.
- Follows an answer to the person who actually decided.
What om does not do
om does not store your facts. A model’s weights cannot cite a source, cannot be corrected one fact at a time, and can produce a confident sentence that nobody ever said. So every rule, answer and approval lives in the evidence store, separately from om. When om needs a fact, it retrieves it from the store and cites it.
| In om | In the evidence store | |
|---|---|---|
| How to read code and ask good questions | ✓ | |
| Your rules, reasons and approvals | ✓ | |
| Sources and history | ✓ | |
| Can be corrected or deleted one fact at a time | ✓ |
Why a model of our own
Running om in your infrastructure means your systems and your people’s answers are never sent to a third-party AI provider. It also means om can be tuned for one job: asking the right person the right question, briefly.
See Deployment and Data handling.