Skip to main content

Architecture in 60 Seconds

HatiData is built on a two-plane architecture that separates data processing from management. This page gives you the full picture in under a minute.

Two Planes

┌────────────────────────────────────────────────┐
│ Your Infrastructure │
│ │
│ AI Agents ──→ Data Plane (HatiData Proxy) │
│ │ Postgres wire protocol │
│ │ SQL transpilation │
│ │ Query execution │
│ │ Memory + CoT + Triggers │
│ │ Multi-tier caching │
│ ▼ │
│ Object Storage (your bucket) │
└────────────────────────────────────────────────┘

PrivateLink / HTTPS

┌────────────────────────────────────────────────┐
│ Control Plane (HatiData) │
│ Auth · Policies · Billing · Audit · Dashboard │
└────────────────────────────────────────────────┘

Data plane — Runs where your data lives. Accepts Postgres connections, transpiles Snowflake SQL for execution, and provides agent-native capabilities (memory, chain-of-thought, triggers, branching). In Local mode, it runs on your machine. In Enterprise mode, it runs in your VPC.

Control plane — Manages everything that is not query execution: authentication, policy management, billing, audit, and the dashboard. Communicates with the data plane over PrivateLink (Enterprise) or HTTPS (Cloud).

Multi-Stage Query Pipeline

Every SQL query flows through a multi-stage pipeline. Security and compliance are built in — not bolted on:

StageWhat Happens
AdmissionConcurrency control — queue, don't reject
Table extractionIdentifies all referenced tables
Policy checkABAC evaluation against agent identity, role, time, tables
Cost estimationHeuristic credit cost based on joins, scans, aggregations
Quota checkPer-org credit limits enforced
Row-level securityWHERE clauses injected based on agent context
TranspilationSnowflake SQL auto-adapted for execution
Snapshot pinRepeatable reads via point-in-time snapshot pinning
ExecutionColumnar engine with vectorized processing
AI healingOptional: retry failed queries with AI-suggested corrections
Column maskingSensitive columns masked by role (Admin → full, Agent → redacted)
MeteringCredit usage recorded, metrics emitted
AuditPII-redacted, cryptographically hash-chained audit entry written

Full pipeline deep dive →

Agent-Native Capabilities

Beyond SQL, HatiData provides five capabilities through the same Postgres connection and 24 MCP tools:

CapabilityWhat It DoesMCP Tools
IdentityPer-agent authentication, scoping, billing— (via connection params)
MemoryPersistent SQL + vector hybrid search5 tools
Chain-of-ThoughtImmutable hash-chained reasoning traces3 tools
TriggersSemantic concept-matching with 4 action types4 tools
BranchingCopy-on-write schema isolation with merge5 tools

Plus 7 core query tools: run_sql, run_sql_readonly, list_schemas, list_tables, describe_table, run_sql_arrow, get_usage_stats.

Three Deployment Tiers

TierData LocationPriceBest For
LocalYour machineFreeDevelopment, prototyping, CI
CloudHatiData-managed$29/monthSmall teams, startups
EnterpriseYour VPCCustomRegulated industries, production

The same SQL, SDKs, and agent code work across all tiers. The only change is the connection string.

Caching (Three Tiers)

TierBackingLatencyEviction
MemoryIn-memorySub-microsecondTTL + LRU
DiskHigh-performance local storageSub-millisecondTTL + size cap
ObjectCloud object storage10–100msSnapshot-based

Transpilation results are cached separately by SQL hash — repeated queries skip the parse-and-rewrite pipeline entirely.

Next Steps

Stay in the loop

Product updates, engineering deep-dives, and agent-native insights. No spam.