Examples

Tarski’s examples are not demos — they are executable behavior contracts. Each one teaches a specific platform behavior, and each proves its unsafe paths with fixtures, not only its happy paths. Browse and install them with the CLI:

tarski examples list
tarski examples install

Choose by what you need to learn

You want to learn	Example
First-app authoring	Appointment booking
Recursive derivation and remediation gates	Incident response
Sensitive evidence and human review	Medical intake
External provider effects and replay	Price watch
Plugin-driven collection, offer history, blob archival	Google Shopping Price Monitor
LLM proposal containment	Car dealership chat (live / deterministic)
Multi-agent shared reality	Multi-agent live, incident response
Agent worldview reads, budgets, multi-hop loops	Incident response
Consent- and policy-gated agent reads	Medical intake
Your first declared query	Appointment booking
Consuming the query API externally	Price watch
Entity declarations and optimistic concurrency	Team Tasks
Verified end-user identity and tenant scoping	Member Portal, Team Tasks
Full-stack SDK consumption (React over serve)	Team Tasks web/

Highlights

Appointment booking is the tutorial app: invariants prevent double holds and double bookings, and its first declared query (queries/booking-status.ta, exposed studio, api) comes with a real tarski query booking-status transcript in its README.

Incident response is the flagship agent-read example: compound blast-radius queries exposed to agents, a query budget of 2 enforced by decision rules with PM-readable denial reasons ("budget_exhausted", "no_open_session"), and a backstop invariant that makes over-approval an impossible state. Its fixtures prove multi-hop assessments, denied reads, and failed reads.

Medical intake shows sensitive-evidence handling: candidate extraction with clinician review, PHI projection boundaries, and consent-gated agent reads — the patient-history query approves only when the worldview holds medical.patient_consent(patient_id, "agent_history_review").

Car dealership chat ships in two canonical variants: car-dealership-chat-live uses a live OpenAI model (requires OPENAI_API_KEY; a missing credential surfaces as a visible warning, never a silent deterministic fallback) and car-dealership-chat-det replays deterministic provider scripts for stable containment demos. Both share the same shape: chat becomes evidence, assistant replies and offers enter via proposal.*, decisions accept or reject, and policy-gated intents drive external sends.

Team Tasks is the collaborative-SaaS reference: tasks and comments as entity declarations, tenant-scoped access facts, fail-closed same-version conflicts, and a full React frontend under web/ consuming the published @tarski/client package — reads are row-filtered projection calls, writes are policy-gated observation appends with version-carrying idempotency keys, and live updates arrive over a single declared-query subscription.

Member Portal is the identity-enabled example: verified IdP tokens become actor context at ingress, the access.* account plane gates session starts and appends, tenant notices are row-filtered per verified tenant, and fixtures cover revoked accounts, contested sessions, and cross-tenant scoping.