Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

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=developer from the repository root.

SceneWhat to notice
LoginEntry point to the SCHEMABOUND Enterprise control plane
LDAP importDirectory data flows into Dolt — becomes the LLM’s context source
Empty hierarchyStarting 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 memoryEvery tool call stored as a structured, queryable event
Schema registrationSchemaboundDeclarativeBase.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=executive from the repository root.

SceneBusiness outcome
LoginUnified control plane — one place for identity, data, and AI governance
LDAP importExisting directory assets re-used instantly; no data migration project
Empty hierarchyBaseline state demonstrating clean-slate adoption
LLM agent populates hierarchyAI-driven data work completed in seconds, not sprint cycles
Agent memoryLeadership-visible evidence of AI activity — no developer report required
Schema registrationMarketing 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=devsecops from the repository root.

SceneSecurity / audit focus
LoginIdentity source is LDAP-backed; session ID assigned at login
LDAP importDirectory data validated and ingested before any agent can act on it — least-privilege at the data layer
Empty hierarchyAuditable baseline state captured before agent execution
LLM agent populates hierarchyEvery function_call → tool call recorded in agent memory via gRPC in the same transaction as the DB write — no dual-write gap
Agent memoryStructured, queryable audit log: session ID, tool name, arguments, timestamp — SIEM-ready
Schema registrationSchema locked to the registered model; agent cannot call tools outside the declared interface