Lotus Notes and HCL Domino Private AI Layer Blueprint Generator
This generator turns a handful of facts about your Lotus Notes and HCL Domino environment into a structured architecture plan for a private AI assistant. It covers the components, the security controls tied to your hosting choice, a three-phase rollout and the questions IT has to answer before build.
Fill in
Lotus Notes and HCL Domino Private AI Layer Blueprint Generator
Context
Company: Acme Precision Ltd System: Lotus Notes and HCL Domino, version Domino 11, database NSF (Domino native) Hosting: On-prem server Scale: 1200 named users across 3 sites Target: Pilot in 8 weeks, production in 6 months
Goal: add a private AI assistant over the existing system without moving data to a public cloud service and without replacing the system.
Use cases in scope
Search and summarize quality, quote and approval databases; extract attachments; answer questions across years of workflow history without opening each database.
Data that must never leave the site
Documents restricted by Readers fields, encrypted documents and fields, personal mail files and HR applications.
Control: this data is excluded from the index or processed only on On-prem server infrastructure, with access logged.
Components
| Component | Design |
|---|---|
| Data access path | Domino REST API or DAS, DQL and DXL export against a read-only replica server |
| Retrieval index | Plain text from items, rich text and attachments, with Readers and ACL principals on every chunk |
| Model serving | Open-weight model on vLLM or Ollama on 1 x 24 GB GPU |
| Tool server | MCP or HTTP server with search and open-document tools returning notes links |
| Identity and permissions | Database ACL plus per-document Readers fields; groups expanded from the Domino Directory per question |
| Audit | Append-only log of questions, documents cited and denied matches |
Security controls
Readers fields honored; extraction on a replica; encrypted content excluded and reported; read-only service account; deletions and replication conflicts reconciled nightly.
Hosting mode On-prem server: when air-gapped, models, containers and packages enter through a hash-verified transfer and no component calls an external network.
Rollout
| Phase | Scope | Exit criteria |
|---|---|---|
| 1. Read-only questions | Cited answers over a pilot scope for a small user group on 1 x 24 GB GPU | Answers verified by process owners; no permission leaks in tests |
| 2. Drafts | Summaries, comparisons and drafted records a person reviews and enters | Reviewers accept drafts without major edits in agreed share of cases |
| 3. Approved actions | Narrow actions through the supported API with a named human approver | Every action logged; rollback path tested; sign-off from system owner |
Open questions for IT
1. How many databases are active, and which are safe to archive instead of index? 2. Do documents use Readers fields, and in which databases? 3. Are attachments and rich text the main content? 4. Which Domino server release is running, and are REST and DQL available? 5. Who owns each application and can explain its items?
Approvals
This is a planning document, not a security certification. Component choices (vector store, model size) depend on your pilot measurements; confirm API names and limits against the documentation for your exact version.
Review my blueprint
Send the exported plan for an optional review of the data access path, permissions design and rollout.
Optional. The tool and every export work without this. No spam.
How to use it
Enter your system version, database engine and hosting model, then describe the use cases and the data that must never leave the site. The blueprint fills the context, components, controls and rollout sections, and exports to PDF, Word or Excel. Walk through it with your IT architect and security officer, correct the defaults, and attach it to the project request. Change the GPU field to see how the rollout row for phase one reads on different hardware.
- Be specific about restricted data: it becomes a design constraint, not a footnote
- Pick hosting first; it sets the security controls
- Keep use cases to three or four for the pilot
- List the people who can approve write-back
What the blueprint assumes
The design is the same on every on-prem system: a read-only copy or supported API for data access, a retrieval index that carries permissions, a tool server that exposes only approved read actions, an open-weight model on vLLM or Ollama, and an audit log. Rich text and attachments decide answer quality in Notes applications. The components table names the access path for this system, but you must verify the object and API names for your exact version.
- Read-only by default
- Permissions mirrored from the system
- Write-back only through supported APIs with human approval
- Everything logged
Reading the rollout table
Phase one proves the data and permissions work: cited answers over a small scope. Phase two adds drafts that a person reviews. Phase three allows narrow, approved actions through the system's own API. Do not skip phases: most failures come from skipping permission testing in phase one. Exit criteria are examples; replace them with numbers your process owners agree to, such as the share of answers verified correct in a sample of fifty questions.
Common mistakes
Teams often size the model before they have defined the use case, grant the assistant a powerful service account, or index everything to avoid deciding scope. Another is leaving the open questions unanswered until build starts. Many occasional users and a long extraction job. Use the open-questions section as the agenda for your first IT workshop and assign an owner to each item.
- Powerful service account for convenience
- No permission tests with restricted users
- Indexing without scope decisions
- No owner for open questions
Frequently Asked Questions
Does this document commit us to buying anything?
No. The generator runs in your browser and exports a plan you can share internally. It is a starting point for architecture and security review, and every default can be changed.
Is the plan valid for air-gapped sites?
Yes. Choose the air-gapped hosting option and the controls section adds transfer and network isolation rules. All components in the table run inside the closed network with no external calls.
Why does the plan avoid giving model sizes?
Model size and GPU count depend on concurrency, context length and answer quality targets. Measure them in the pilot, then use the sizing calculator for ranges rather than committing to a number early.
Can we reuse the plan for another system?
The structure transfers, but the data access path, permission model and open questions are specific to each system. Generate a separate blueprint for each platform and compare them.
Netray designs and runs private AI layers on Lotus Notes and HCL Domino with your IT team. If you want a second opinion on your blueprint, we can review it with you.
Related Tools
Lotus Notes and HCL Domino AI Assistant Sizing and Value Calculator
Estimate GPU count, token volume, index size and payback for a private AI assistant on Lotus Domino from users, usage and time saved.
On-Prem AIOn-Prem AI Deployment Checklist
A 30-point pre-deployment checklist covering use cases, hardware, security, model operations, and rollout for self-hosted enterprise LLMs.
On-Prem AIGPU Sizing Calculator for LLM Inference
Work out how many GPUs you need to serve a given open-weight model to your user base, based on memory footprint and token throughput.
On-Prem AIRAG Infrastructure Sizing Calculator
Estimate vector storage, node RAM, generation GPUs, and monthly infrastructure cost for a retrieval-augmented generation deployment over your document corpus.
More On-Prem AI tools
See all- On-Prem LLM Total Cost of Ownership Calculator
- On-Prem vs Cloud AI Cost Comparison Calculator
- Self-Hosted LLM Hardware Estimator
- Air-Gapped AI Readiness Assessment
- LLM API vs Self-Hosted Cost Calculator
- Open-Weight Model Selector
- On-Prem AI ROI Calculator
- LLM Token Cost Calculator
- AI Data Center Power and Cooling Calculator
Keep exploring
Free tools
- Lotus Notes and HCL Domino AI Assistant Sizing and Value CalculatorEstimate GPU count, token volume, index size and payback for a private AI assistant on Lotus Domino from users, usage and time saved.
- SyteLine Private AI Layer Blueprint GeneratorFill in your SyteLine environment and get a ready-to-share architecture plan for a private, on-prem AI assistant.
- SharePoint Server On-Prem Private AI Layer Blueprint GeneratorFill in your SharePoint Server environment and export an architecture plan for a private, on-prem AI assistant: components, security controls, rollout and open questions.