Omnitrace
Built for Databricks · more platforms coming

Two agents. Live now.

Agentic observability for lakehouse compute. Each agent runs continuously, reasons in dollars, and acts within your guardrails.

Agent 01

FinOps Agent

Watches every dollar your lakehouse spends. Finds waste across compute, storage, and infrastructure. Quantifies the annual impact. Fixes it — within your guardrails.

Idle cluster termination
Warehouse auto-stop
Photon enablement
OPTIMIZE & ZORDER
3-tier cost attribution (DBU + AWS + BYO-VPC)
OT-MAT-487 · MISSING_AUTO_TERMINATION $2,568/yr

Cluster violet42 idle 60% of the time, no auto-termination set. Setting auto_termination_minutes=30 saves $2,568/yr. Confidence 0.95.

See the full FinOps Agent

Agent 02

Reliability Agent

Lakehouses don't break — they decay. The Reliability Agent maintains platform health continuously, catches drift early, and investigates incidents so you don't have to.

Small-files explosion detection
OPTIMIZE staleness remediation
Recurring failed query triage
Cluster configuration drift
Conversational incident investigation

› why is nightly_billing_etl failing?

3 of last 5 runs failed at load_invoice_lines — input partition skew increased 4× last week. Re-partition by customer_region saves $4,080/yr. Want me to draft the change?

See the full Reliability Agent

Architecture

From lakehouse telemetry to verified action.

Omnitrace connects Databricks and cloud signals to detectors, Atlas Playbook agents, governed remediation, and verified outcomes.

View architecture

01

Lakehouse signals

Databricks, cloud cost, jobs, SQL, Spark, ownership, and workflow metadata.

02

Omnitrace agents

Detectors and Atlas Playbook agents reason over metadata and operational telemetry.

03

Governed action

Policy gates, approvals, scoped tools, and autonomy levels control every change.

04

Verified outcomes

Read-back checks prove what changed and keep evidence with the action record.

Platform availability

Built for the lakehouse. Expanding everywhere.

Live Now
Databricks
Both agents fully operational
Coming Next
Amazon EMR
Same agents, native EMR telemetry
Roadmap
Snowflake · Starburst
Multi-platform in a single pane

Under the hood

Both agents run the same loop.

Sense → Reason → Act → Verify. Every minute. Every workspace. Continuously.

1 Sense

Continuously senses your lakehouse

Agent ingests rich telemetry across compute, queries, tables, billing, and infrastructure — building a live model of your environment.

2 Reason

Reasons over evidence

AI weighs signals, quantifies dollar impact, and writes natural-language narration explaining why action is justified.

3 Act

Acts through MCP-orchestrated tools

Within your autonomy budget, the agent calls the right write-tool — adjusting cluster, warehouse, or table state. Auditable, reversible, sandboxed.

4 Verify

Verifies its own work

Two-tier verification reads back the post-action state. If the change didn't stick, the agent flags REGRESSED and notifies your team.

Continuous loop — every minute, the agent re-evaluates and re-acts

Shared architecture

Open protocol. Auditable. Yours.

Both agents are built on Anthropic Model Context Protocol (MCP). Every action is a structured tool call you can inspect, replay, or extend. The same guardrail system governs both.

MCP-native action layer
Per-tenant isolation (RLS + filter)
Bring your own LLM
Slack + Email notifications
Jira + ServiceNow backlog
OIDC / Keycloak SSO

Ready to put the agent to work?

Connect operational metadata, prioritize verified savings, and move approved Databricks fixes through the agent loop.