Hosted workflow

Drizzle Postgres plus Synapsor

Use Drizzle for typed app queries and Synapsor for agent-safe external source workflows.

Problem

Typed query builders do not by themselves create evidence bundles, branch-staged proposals, settlement, or replay.

Why app glue gets messy

Agent-facing paths often duplicate business policy in tool descriptions and app glue.

How Synapsor helps

Synapsor adds the reviewed agent data-access boundary while Drizzle continues to own normal app queries.

Value sources

Example names and seed ids are developer-defined. SESSION values are set by your backend. ARG values come from the SDK/HTTP call. Handles such as wrp://..., evidence://..., and agent-run://... are returned by Synapsor and should be stored for audit/replay.

Read the value-source guide

Expected outcome

Agents call high-level Synapsor capabilities instead of low-level Drizzle update tools.

Production checks

Drizzle stays in the app path.
Synapsor records agent evidence/proposal/replay state.
Generated mappings should be reviewed after Drizzle migrations.
The model never receives a raw update builder.

schema.sql

export const tickets = pgTable("tickets", {
  id: text("id").primaryKey(),
  tenantId: text("tenant_id").notNull(),
  status: text("status").notNull(),
});

agent.ddl.sql

CREATE AGENT WORKFLOW support.drizzle_ticket_flow
SESSION REQUIRE tenant_id, principal, current_ticket_id
ALLOWED CAPABILITIES (support.answer_ticket_question, support.propose_ticket_resolution)
EVIDENCE REQUIRED
AUTO BRANCH ON PROPOSAL
CHECKPOINT EVERY STEP;

python

run = db.agent_runs.start(workflow="support.drizzle_ticket_flow", input={"ticket_id": "T001"})