A vertical AI suite for Indian businesses, designed before built.

Enterprise buyers buy organizations, not seats. Self-serve individuals are still organizations of one. The temptation in early SaaS is to make user_id the primary key on every domain table — and then to spend a year migrating to a proper tenant primitive when the first enterprise contract lands. AI Core Platform refuses that path.

Every domain object — document, chunk, embedding, run, prompt version, invoice, audit log — belongs to a workspace_id. A user is a member of one or more workspaces. Row-level security and application-level scoping both use workspace_id, never user_id, as the primary tenant key. Personal workspaces are modeled as a workspace of one with a single owner. Self-serve and enterprise share the same code path; the same RLS policy serves a freelancer and a Fortune-500 procurement team.

Four AI products built independently is four codebases, four billing surfaces, four chat UIs, four ingest pipelines, four prompt frameworks, four observability stacks. Four times the maintenance, four times the deploy risk, and a velocity curve that goes flat the day you start the third product.

AI Core Platform builds the platform once. Thirteen platform capabilities — identity and workspace, billing and entitlements, file ingest (structured and unstructured), structured extraction, vector retrieval, structured store with execution sandbox, scheduled external ingestion, AI orchestration, prompt framework, workflow engine, chat UI shell, notifications and usage and audit — are implemented in the core. Each capability must be used by at least two modules to earn its place in the core. The four modules (Docusense, DataSense, ComplianceSense, TaxSense) are plugins on top, each contributing module-specific domain knowledge: Indian contract law, structured tax forms, regulatory scrapers, spreadsheet semantics. The platform pays for itself the day the second module ships.

A modular monolith without discipline becomes a tangled monolith in three months. Cross-module imports of model classes, cross-module SQL joins, cross-module direct service calls — each one is a load-bearing wire that prevents extraction later, and the cumulative effect is a monolith that cannot be split even when the team is ready to.

AI Core Platform’s third principle is structural: a module = entitlement + surfaces + contracts, never DB reach-across. Modules may not read or write another module’s tables directly. Cross-module needs go through the core (both Docusense and ComplianceSense use Vector Retrieval — the core service, with module="docusense" in queries). Module tables live in module-prefixed schemas. A static check on pull requests rejects cross-module imports of model classes. The result: any module can be lifted into its own service in year two if scale demands it, without rewriting the rest.

Every vendor choice an early-stage AI platform makes is a guess. The right embedding provider in 2026 may be the wrong one in 2027. The right vector store, the right LLM router, the right OCR engine, the right workflow queue — these are all guesses that benefit from being reversible.

AI Core Platform implements every core capability as a typed Python interface (port) with one or more adapters: local for development, hosted for production, mock for tests. Picked pgvector for Phase 1? Swap to Qdrant in year two by writing one adapter, not editing 200 callsites. Picked OpenAI for the launch? Add an Anthropic adapter when the price/latency curve shifts. Fifteen ADRs document the choice and the reasoning at the time it was made; the architecture survives the choice changing.

Indian data residency is not a feature toggle. It is a default. If the architecture assumes US-region storage and then adds India later, every workspace ID, every signed URL, every cross-region query has to be retrofitted. AI Core Platform inverts the default: ap-south-1 (Mumbai) is the deployment region, data residency is a workspace plan attribute, and multi-region routing is deferred but not architecturally impossible.

Workspace IDs are designed to carry region prefixes when multi-region lands. Storage buckets are per-region from day one. Billing is INR-first with GST invoices and Razorpay; USD is a secondary path for non-Indian customers. The Hindi, Gujarati, Marathi, and Tamil language paths are first-class in the ingest, embedding, and chat flows — not English with a translation layer bolted on. The wedge against US horizontals is structural, not marketing.