1---2name: enterprise-ai3description: Navigate Oracle Cloud Infrastructure's Enterprise AI services: choose models, build agents with RAG and tools, estimate costs, secure access, and integrate with Oracle Database, APEX, and other platform services.4---56# OCI Enterprise AI Skills78Use this OCI subdomain as the front door for Oracle Enterprise AI work. Start here when the user goal is about the AI outcome rather than a specific Oracle service name.910## How to Use This Domain11121. Start with the user journey table below.132. Read only the smallest topic file that matches the task.143. Route database-owned implementation details to `db/features/` instead of duplicating Select AI, vector search, or `DBMS_VECTOR` guidance.1516## Directory Structure1718```text19oci/enterprise-ai/20├── models/21├── agent-workflows/22├── governance/23├── data/24├── cost/25├── integrations/26└── agents/27 └── openai.yaml28```2930## User Journey Routing3132| User Goal | Start With |33|-----------|------------|34| Choose or invoke OCI-hosted models, embeddings, rerank, endpoints, or dedicated serving | `models/enterprise-ai-models.md` |35| Import, fine-tune, host, or lifecycle-manage a custom model | `models/custom-and-imported-models.md` |36| Build an API-first agent with OpenAI-compatible OCI APIs | `agent-workflows/responses-api-agents.md` |37| Deploy a packaged agent runtime on OCI-managed infrastructure | `agent-workflows/hosted-applications.md` |38| Choose the right tool pattern: File Search, Code Interpreter, Function Calling, MCP, or SQL Search | `agent-workflows/agent-tools.md` |39| Ground answers in documents, vector stores, SQL, or Oracle Database vector search | `data/rag-and-search.md` |40| Estimate OCI Generative AI or OCI Generative AI Agents cost drivers | `cost/cost-estimation.md` |41| Secure model or agent access with IAM, private networking, OAuth, guardrails, or audit controls | `governance/private-endpoints-and-governance.md` |42| Connect Enterprise AI to Autonomous Database, APEX, Oracle Integration, Fusion, or OCI AI Services | `integrations/oracle-platform-integrations.md` |4344## Key Starting Points4546- `oci/enterprise-ai/models/enterprise-ai-models.md`47- `oci/enterprise-ai/models/custom-and-imported-models.md`48- `oci/enterprise-ai/agent-workflows/responses-api-agents.md`49- `oci/enterprise-ai/agent-workflows/hosted-applications.md`50- `oci/enterprise-ai/agent-workflows/agent-tools.md`51- `oci/enterprise-ai/data/rag-and-search.md`52- `oci/enterprise-ai/cost/cost-estimation.md`53- `oci/enterprise-ai/governance/private-endpoints-and-governance.md`5455## Common Multi-Step Flows5657| Task | Recommended Sequence |58|------|----------------------|59| Build a governed enterprise assistant | `responses-api-agents` -> `agent-tools` -> `rag-and-search` -> `cost-estimation` -> `private-endpoints-and-governance` |60| Move from model experimentation to production serving | `enterprise-ai-models` -> `cost-estimation` -> `private-endpoints-and-governance` |61| Bring a custom model into OCI serving | `custom-and-imported-models` -> `enterprise-ai-models` -> `cost-estimation` -> `private-endpoints-and-governance` |62| Deploy a packaged agent runtime | `responses-api-agents` -> `hosted-applications` -> `cost-estimation` -> `private-endpoints-and-governance` |63| Build RAG over files | `rag-and-search` -> `agent-tools` -> `cost-estimation` -> `responses-api-agents` |64| Build RAG over Oracle Database | `rag-and-search` -> `db/features/vector-search.md` -> `db/features/dbms-vector.md` -> `db/features/select-ai.md` when in-database generation is needed |65| Add AI to APEX or Autonomous Database apps | `oracle-platform-integrations` -> relevant `db/features/` or `apex/apexlang/` guidance |66| Design production access controls | `private-endpoints-and-governance` -> `enterprise-ai-models` or `responses-api-agents` depending on workload |6768## Scope Boundaries6970- Keep cloud-side model, agent, tool, endpoint, hosting, and governance decisions in this domain.71- Use `db/features/select-ai.md`, `db/features/vector-search.md`, `db/features/dbms-vector.md`, and `db/features/ai-profiles.md` for Oracle Database-owned AI implementation.72- Use `apex/apexlang/` for APEX application artifact generation and APEX AI agent component templates.73- Prefer official Oracle documentation for model availability, supported tools, IAM verbs, endpoint formats, and service limits because Enterprise AI services change frequently.7475## Sources7677- https://docs.oracle.com/en-us/iaas/Content/generative-ai/overview.htm78- https://docs.oracle.com/en-us/iaas/Content/generative-ai/home.htm79- https://docs.oracle.com/en-us/iaas/Content/generative-ai/models.htm80- https://docs.oracle.com/en-us/iaas/Content/generative-ai/fine-tune-models.htm81- https://docs.oracle.com/en-us/iaas/Content/generative-ai/imported-models.htm82- https://docs.oracle.com/en-us/iaas/Content/generative-ai/agents.htm83- https://docs.oracle.com/en-us/iaas/Content/generative-ai/governance.htm84- https://docs.oracle.com/en-us/iaas/Content/generative-ai/oci-openai.htm85- https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/86- https://docs.oracle.com/en-us/iaas/Content/generative-ai/calculate-cost.htm
Oracle