A Private, Fine-Tuned, Self-Hosted Intelligence Platform for Svashasan Labs
Purpose: How Svashasan Labs will build its own internal intelligence platform: an open-weight language model, adapted with LoRA, grounded in our own data through retrieval, operating inside an agentic harness, and self-hosted on a VPS we control.
Status note. Based on the Svashasan Intelligence PRD v1.0 (17 November 2026). Today a starter scaffold exists: a FastAPI service, PostgreSQL/pgvector schema and a basic ingestion route. Connectors, retrieval, identity, agents and the model runtime are planned. Fine-tuning is deliberately scheduled after the retrieval baseline, and no base model has been finally selected.
Know
Retrieval over our data
Answers grounded in Zoho, Git, documents and databases, with citations.
Behave
A LoRA-tuned open model
A small adapter teaches tool use, citation and refusal; facts stay out of the weights.
Act
Inside an agentic harness
Read-only tools first; anything consequential waits for a human.
Own
Self-hosted on our VPS
Company data stays on infrastructure Svashasan controls.
1. What We Are Building
Svashasan Intelligence is a private platform that organises company knowledge, answers questions with evidence, supports analysis and reporting, and later runs carefully permissioned workflows. It is an internal business and engineering plane, entirely separate from Svashasan OS in the vehicle.
Figure 1. Two planes, one hard wall. Svashasan Intelligence may read approved engineering material about Svashasan OS, but it is never part of the real-time vehicle path.
2. The Architecture
Five principles shape it: private by default, retrieval before fine-tuning, permissions before prompting, human approval for consequential actions, and a replaceable model layer.
Figure 2. The platform in four planes. Data enters through governed ingestion, becomes searchable knowledge with access controls attached, and only then reaches the model, which sits behind identity and policy.
3. Our Data, Governed
Initial sources are Zoho CRM, Zoho Mail, engineering documents, Git repositories and internal databases, all read-only. The Zoho CRM and Mail ingestion already specified for Svashasan Investor Intelligence becomes one governed feed into this platform.
Figure 3. Two separate gates. A document approved for retrieval is not automatically approved for training; fine-tuning data needs its own written approval, rights review, redaction and versioning.
Classification
Figure 4. Classification decides everything downstream. Missing classification, ACL or approval means the system fails closed: no retrieval, no training.
4. Retrieval First: Why Answers Stay True
“Training it on our own data” has two meanings, and the platform separates them deliberately.
Figure 5. The most important design decision. Facts live in governed source records and are retrieved with citations; the LoRA adapter teaches the model how to behave inside our harness. Baking facts into weights would make them uncitable, unrevocable and stale.
A question, end to end
Figure 6. One question, end to end. Access control is applied inside the database search, before any text reaches the model, and every citation is re-checked against what the user is allowed to see.
5. Fine-Tuning with LoRA
Once retrieval works, a LoRA adapter makes the open-weight model a better participant in our harness. Qwen3-8B is a candidate for evaluation, not a final choice; the base model is selected on licence, provenance, tool-calling behaviour and measured CPU performance.
Figure 7. LoRA in one picture. The base model stays frozen; we train two thin matrices whose product nudges its behaviour. QLoRA does the same over a 4-bit quantised base so a 7–8B model fits on a single rented 24 GB GPU.
The training pipeline
Figure 8. How an adapter is made. Training is a short, rented-GPU job; the result is a small, hashed adapter file that must pass evaluation before the self-hosted runtime loads it.
Starting configuration
Figure 9. The starting configuration from the PRD. These are template values to verify against the selected checkpoint, not tuned settings.
Proving it was worth it
Figure 10. How we decide whether fine-tuning was worth it. The adapter has to beat retrieval alone on a fixed evaluation set; if it does not, it does not ship.
6. The Agentic Harness
The agent layer coordinates approved tools but never owns the permission model; the API and policy service are authoritative. All retrieved documents, emails and code comments are treated as untrusted evidence, never as instructions.
Figure 11. The agentic harness. The model proposes; the policy service decides. Read-only tools run directly, anything consequential waits for a human, and every action is audited.
What “harness-compatible” means
Figure 12. “Harness-compatible” means two halves. Fine-tuning makes the model a reliable, well-formatted participant; the harness keeps all authority. A model can be persuaded by a malicious email; a server-side policy check cannot.
Tool tiers
Figure 13. What the agents may do. The tool catalogue grows only as each tier proves safe; the right-hand column is a permanent boundary, not a backlog.
7. How It Powers Our Development
Figure 14. What it does for the company. One governed knowledge layer serves engineering, fundraising, partnerships and operations; each team sees only what its role permits.
The development flywheel
Figure 15. The development flywheel. Every commit and document becomes searchable context for the next engineer, so a small team keeps its decisions instead of rediscovering them.
8. Self-Hosted on a VPS
The platform runs on one hardened server: Ubuntu 24.04, 4–8 vCPUs, 32 GB RAM, Docker Compose with pinned images, and no public database or model ports. The PRD names Oracle Cloud Infrastructure as the first host; the same stack runs on any VPS that meets the specification.
Figure 16. Self-hosted on one VPS. Everything that touches company data runs on a server we control; a GPU is rented only for short training runs, and only the adapter comes back.
Security layers
Figure 17. Security, layer by layer. The three dark layers are specific to an AI system: permissions applied before the model sees data, retrieved content treated as untrusted, and tools that the model cannot authorise for itself.
What it costs
Figure 18. The monthly envelope from the PRD: an allocation model, not a vendor quote. If real costs exceed the cap, GPU experiments shrink first, never security or backups.
Figure 19. Why the VPS has no GPU. A published reference price puts an always-on A10 at about fourteen times the whole monthly budget.
9. Roadmap
Figure 20. The delivery plan. Upper-bound estimates in working days, sequential here for clarity; the PRD expects a 4–6 week calendar for a small team with some work in parallel. Fine-tuning comes after the platform works without it.
Figure 21. Release gates. Each is a pass/fail checkpoint; agentic workflows come last, after the platform has proven it answers correctly and safely.
10. Principles That Do Not Change
Decision
What it means
CPU-first deployment
Serve on CPU within budget; rent GPU only for experiments and training
Retrieval before fine-tuning
Facts come from governed sources with citations; adapters change behaviour only
Access control before model context
The model never sees text the user is not allowed to see
Read-only connectors first
No writes to CRM, mail, Git or databases until approval workflows exist
Replaceable model layer
Swap the base model or adapter without migrating data
Not a vehicle control plane
No path from the intelligence platform to actuation, calibration or OTA release
Our data stays ours, our facts stay citable, and the model stays replaceable: Svashasan Intelligence is built so the company gets smarter without handing its knowledge, or its authority, to the model.