Demo
Family Tree — AI-Narrated Demo (Developer)
The same end-to-end recording narrated for a software developer evaluating the SCHEMABOUND SDK. Highlights SchemaboundDeclarativeBase, _call_gemini + gRPC agent memory, and TestClient for unit testing.
Regenerate:
GEMINI_API_KEY=<key> make narrate DEMO=family-tree PERSONA=developerfrom the repository root.
| Scene | What to notice |
|---|---|
| Login | Entry point to the SCHEMABOUND Enterprise control plane |
| LDAP import | Directory data flows into Dolt — becomes the LLM’s context source |
| Empty hierarchy | Starting state before any agent action |
| LLM agent import | _call_gemini injects LDAP context → Gemini returns function_call parts → Person.from_agent_tool_call(**kwargs) writes to PostgreSQL; gRPC records each tool call |
| Agent memory | Every tool call stored as a structured, queryable event |
| Schema registration | SchemaboundDeclarativeBase.to_roam_schema() auto-generates the function-calling schema — zero manual schema code |
Family Tree — AI-Narrated Demo (Executive)
The same recording narrated for a business executive evaluating SCHEMABOUND. Focuses on cost avoidance, always-current documentation, and SCHEMABOUND’s data-first / code-first / hybrid adoption model — no full rewrite required.
Regenerate:
GEMINI_API_KEY=<key> make narrate DEMO=family-tree PERSONA=executivefrom the repository root.
| Scene | Business outcome |
|---|---|
| Login | Unified control plane — one place for identity, data, and AI governance |
| LDAP import | Existing directory assets re-used instantly; no data migration project |
| Empty hierarchy | Baseline state demonstrating clean-slate adoption |
| LLM agent populates hierarchy | AI-driven data work completed in seconds, not sprint cycles |
| Agent memory | Leadership-visible evidence of AI activity — no developer report required |
| Schema registration | Marketing and API documentation self-updating; collateral never goes stale |
Family Tree — AI-Narrated Demo (DevSecOps)
The same recording narrated for a DevSecOps engineer or security auditor. Covers session tracking, structured audit logging via gRPC, RBAC enforcement at the data layer, and the security observability that SCHEMABOUND Enterprise provides out of the box.
Regenerate:
GEMINI_API_KEY=<key> make narrate DEMO=family-tree PERSONA=devsecopsfrom the repository root.
| Scene | Security / audit focus |
|---|---|
| Login | Identity source is LDAP-backed; session ID assigned at login |
| LDAP import | Directory data validated and ingested before any agent can act on it — least-privilege at the data layer |
| Empty hierarchy | Auditable baseline state captured before agent execution |
| LLM agent populates hierarchy | Every function_call → tool call recorded in agent memory via gRPC in the same transaction as the DB write — no dual-write gap |
| Agent memory | Structured, queryable audit log: session ID, tool name, arguments, timestamp — SIEM-ready |
| Schema registration | Schema locked to the registered model; agent cannot call tools outside the declared interface |