Key facts
| API surface | OpenAI-compatible /v1/chat/completions; keep your existing SDK |
| Grounding | Embeddings and RAG are live for contract, policy and precedent search |
| Models | 30+ models behind one API, from free tiers to frontier |
| Deployment | Plugsky cloud, your VPC, on-prem or air-gapped |
| Access control | Scoped API keys, rotation and usage analytics; enterprise SSO and RBAC options |
| Auditability | Request and response logging with usage analytics |
| Pricing model | Flat monthly self-serve plans; no per-token billing on self-serve |
| Free tier | Free plan with plugsky-micro and plugsky-lite; 14-day full-access trial |
TL;DR
- Ground legal answers in approved internal content with RAG instead of model memory.
- Keep privileged or matter content inside VPC, on-prem or air-gapped deployments where policy requires it.
- Scope retrieval per team, client or site so permissions and confidentiality hold at query time.
- Keep a named human owner for every legal decision.
- Keep privileged matters in isolated workspaces.
How it works, step by step
- Inventory the content to make searchable: contracts, compliance policies, precedent and research memos.
- Define a data boundary for the pilot that excludes restricted material until controls are proven.
- Choose a deployment target: cloud for public content, VPC, on-prem or air-gapped for restricted data.
- Build an evaluation set with counsel and compliance leads so answer quality is judged by domain experts.
- Ingest, chunk and embed approved documents, and require citations on every answer.
- Add refusal behavior for questions outside the indexed, approved content.
- Review logged interactions on a schedule and expand only after accuracy and access checks pass.
Original data
Try it yourself
Open the RAG chunk size calculator →
Where legal teams start
Start with internal questions that already have a written answer. High-value first workloads include:
- Contract search: answer clause, obligation and renewal questions with citations.
- Compliance policy: retrieve policy requirements and control descriptions.
- Precedent and templates: surface approved language and fallback positions.
- Matter and research notes: answer from internal memos inside privilege boundaries.
Each use case augments staff with cited answers; none replaces qualified counsel judgment.
A private RAG architecture for legal knowledge
The stack is consistent across industries: ingest approved contracts, compliance policies, precedent and research memos, chunk and embed with a multilingual embedding model, store vectors inside your environment, and call chat completions that answer only from retrieved context. Plugsky embeddings and chat completions are OpenAI-compatible, so teams already using OpenAI SDKs change the base URL and keep their code.
Privilege and matter metadata should be applied at ingestion and enforced at query time. Keep investigations in isolated workspaces, version templates, and log retrieval for compliance review.
Access control, confidentiality and audit
Privilege, confidentiality and matter separation drive the design. Filter retrieval by matter, keep internal investigations in isolated workspaces, and retain logs for compliance. Legal conclusions and filings always require qualified review before use.
The technical controls are consistent: enforce permission-aware retrieval in your own service layer, scope API keys per application, team or tenant, rotate keys, and retain request and response logs on a defined schedule. Regulatory obligations vary by jurisdiction and sector, so map them with counsel rather than assuming one framework covers every deployment; Plugsky supplies the deployment and logging primitives you document.
See the AI governance framework for related deployment and control detail.
Rollout and human oversight
Pilot on published policy and template content before touching privileged or matter content. Build a labelled question set with counsel and compliance leads, then measure retrieval hit rate, citation correctness and answer accuracy before and after every index or model change. Require citations on every answer, refuse out-of-scope questions, and name a human owner for every legal decision.
Review logged interactions weekly at first, correct the index rather than the prompt when retrieval misses, and expand the corpus only when accuracy and access checks pass.
Honest comparison
| Capability | Plugsky | Public AI assistants | Building in-house |
|---|---|---|---|
| Data boundary | Cloud, VPC, on-prem or air-gapped | Vendor cloud only | You control fully |
| Grounding | Embeddings and RAG are live for contract, policy and precedent search | Uncontrolled retrieval | You assemble and operate |
| Access control | Scoped keys, usage analytics, enterprise SSO and RBAC options | Account-level only | Custom identity work |
| Auditability | Request and response logging | Limited | You build logging |
| Pricing | Flat monthly self-serve plans; see live pricing | Per-seat or per-token | GPU plus operations cost |
| Time to pilot | Days | Hours, without residency control | Quarters |
Frequently asked questions
Can legal teams keep data private with Plugsky?
Yes. Choose the deployment boundary that matches the data: Plugsky cloud for public content, or your VPC, on-prem and air-gapped options for restricted material. Access is controlled with scoped API keys and usage analytics.
Do we need to fine-tune on our internal documents?
Not for a first release. Fine-tuning is coming soon and is better for style than facts. RAG keeps answers current, permission-aware and traceable to a source, which matters more for internal knowledge.
Which model should we use?
Start free with plugsky-micro and plugsky-lite to validate retrieval, then evaluate mid-tier and frontier models from the 30+ model catalogue on your own question set.
How do we stop wrong or unsupported answers?
Restrict the assistant to approved indexed content, require citations, refuse out-of-scope questions and keep a human decision-maker for every regulated or client-facing outcome.
How is pricing structured?
Self-serve plans are flat monthly with unlimited fair-use usage, and there are no per-token charges on self-serve plans. See the live pricing page for current plans and the free tier.
How do we protect privileged material?
Tag privilege at ingestion, enforce it as a retrieval filter, and keep investigations in isolated workspaces with logging.
Can it review contracts at scale?
It can retrieve and summarize clauses for review, but approval workflows and legal judgment stay with qualified counsel.