AI Layer
The layer where the model connects to company data, its limits are drawn and its output is measured.
48 functions →- MCP server: company systems exposed to the model through one standard interface
- Tool definitions: every operation the model may call, named individually
- Authorisation boundary: which role reaches which data and which action
- Read-only and write-capable tools kept apart
- +2
- Ingestion: contracts, procedures, technical documents and record sources
- Chunking and embedding scheme
- Semantic and keyword search working together
- Citation: every answer states the document it came from
- +2
- Multi-step task execution with an explicit plan
- Tool use: opening a record, creating an order, producing a report
- Steps that require human approval, named upfront
- Rollback and compensating actions
- +2
- Forbidden topics and forbidden forms of steering
- An obligation to speak only from the data supplied
- Missing information written as missing rather than invented
- Output validation: shape, range and business rules
- +2
- An eval set built from real questions, held fixed
- Regression checks so a prompt or model change cannot lower quality
- Human review and labelling flow
- A/B comparison and per-version scoring
- +2
- Traces: which question, which context, which tool, which answer
- Audit record and retention period
- Token and cost tracking, cost per unit of work
- Latency measurement and identification of slow steps
- +2
- The system prompt edited and versioned from the admin panel
- Version history and rollback
- Model routing: a different model per task, balancing cost and quality
- Failover to a secondary model when a provider degrades
- +2
- Data excluded from model training
- Data residency: where a request goes and where it is stored
- Processing inventory under KVKK and GDPR
- A self-hosted model option
- +2