Your LLM generated a DELETE without WHERE. We blocked it before it reached production.

An operation allowlist blocks based on the first token of the query: if it starts with DELETE, it blocks; if it starts with SELECT, it allows. It's an instrument with no granularity.

AST (Abstract Syntax Tree) parsing builds the complete syntax tree of the query. Vericto traverses that tree looking for nodes that violate the rules. This allows detecting:

• UPDATE products SET price = 0 without a WHERE clause (UpdateStmt > WhereClause = NULL)
• DELETE FROM users without WHERE at any nesting level
• TRUNCATE disguised inside a CTE
• DELETE FROM orders LIMIT 0, a DELETE that deletes nothing but is syntactically dangerous

An allowlist cannot detect any of these cases because they all start with tokens that appear safe on the surface.

AST parsing of a typical query (<500 tokens) takes <2ms at p99. The total proxy overhead (TLS handshake + parsing + forwarding) vs a direct connection is <0.3% in benchmarks.

The proxy is written in Rust with tokio for asynchronous TCP connection handling. No garbage collection pauses, no runtime overhead. Designed specifically for the critical path.

Event logging to the audit trail is completely asynchronous, it is not in the critical path of the query.

No. Vericto acts as a transparent TCP proxy. You only change the host in your connection string:

Your ORM (SQLAlchemy, Prisma, ActiveRecord, Drizzle) doesn't know there's a proxy in the middle. Queries arrive exactly the same way. Vericto intercepts them, analyzes them, and forwards them if they are safe.

The Vericto proxy is deployed across multiple regions with high availability. The Team plan includes an uptime SLA. In the unlikely event of a total proxy failure, the behavior is fail-closed: queries do not pass through until the proxy recovers.

For the Enterprise plan, we offer VPC deployment: the proxy is deployed within your own infrastructure, eliminating external network dependency.

You can monitor service status at status.vericto.com.

Yes, the full text of each intercepted query is stored in the audit trail, encrypted at rest with AES-256-GCM. This is required for the actionable explanation feature and for the compliance audit trail.

The query text is also stored as a SHA-256 hash for indexing. Access to the full text requires authentication with workspace permissions.

Retention varies by plan: 7 days (Free), 30 days (Builder), 90 days (Team), configurable (Enterprise). You can export and purge the audit trail at any time.

Query data is never used to train models or shared with third parties.

The Vericto CLI allows you to validate a SQL query file against your workspace's ruleset without needing a database connection:

vericto check migrations.sql --dialect postgres

✓ 12 queries analyzed.
✗ 1 destructive query detected:

  Line 47: TRUNCATE TABLE orders
  Rule: VERICTO-011 (severity: CRITICAL)
  AST node: TruncateStmt > relation: orders
  Suggested fix: DELETE FROM orders WHERE created_at < NOW() - INTERVAL '90 days'

The process exits with code 1 if there are destructive queries (the CI pipeline fails) or exit code 0 if everything is clean. Compatible with GitHub Actions, GitLab CI, and Jenkins.

No. Vericto is specific to SQL databases. AST parsing is a technique that applies to the SQL language: extending it to NoSQL would require entirely different parsers and the concept of a "destructive query" is less well-defined in those contexts.

The current focus is SQL with the most widely used dialects in production with AI agents: Postgres, MySQL, Oracle, and SQL Server, with SQLite and Snowflake on the roadmap. This covers 95%+ of LLM-to-SQL use cases in production.

Three ways, depending on your architecture:

• TCP proxy: point your connection string at the Vericto proxy instead of your database. It intercepts each query on the wire protocol (Postgres/MySQL) and blocks inline. Zero code changes.
• HTTP API: validate SQL with a REST call before running it. Ideal for Text-to-SQL pipelines, serverless functions, and agents that generate queries dynamically.
• CLI: the vericto binary validates SQL in pre-commit hooks and CI/CD, with an exit code that mirrors the verdict.

The proxy and the CLI are available on every plan, including the free one.

Yes. Vericto deploys in your own infrastructure (your credentials never leave your network) and includes the pieces an enterprise environment requires:

• Ed25519-signed audit trail, offline-verifiable: direct evidence for SOC2 (CC6.1, CC6.3, CC7.2) and ISO 27001.
• SSO / OIDC and role-based access control for your team.
• Custom YAML rules for your organization's specific policies.

The Enterprise plan adds assisted deployment, an SLA, and dedicated support.