Overview
Half of "the number looks wrong" is really "the pipeline is late". Modus mines your Fivetran connections and their sync state, and gives agents the tools to check, and fix, freshness.
What Modus reads
- 1Destination group
- 2Pipeline (connection)
You select the level Modus is allowed to mine. Everything below it is discovered automatically; everything outside it is never touched.
2context types mined
11agent tool groups
1connection method
4security controls
Context types
Each object Modus mines produces typed context items, addressed by their position in the hierarchy. This is what an agent actually receives.
Pipeline metadata
Source service, destination schema, schedule, and setup state for each selected connection.
Pipeline statistics
Sync state and recency, so an agent can tell whether data is current.
Example context item
fivetran_connector_metadatasnowflake_prod›salesforce_main
- Source
- Salesforce → SALESFORCE schema
- Schedule
- Every 15 minutes
- Last successful sync
- 2026-08-10 06:42 UTC
- State
- Connected · not paused
Common use cases
- 01
Answer "is this dashboard stale?" with the actual last sync timestamp.
- 02
Let an on-call agent trigger a re-sync after a source outage, with approval.
- 03
Explain a missing column by checking what the connector is configured to sync.
Connection method
Connect once. Modus stores credentials in a managed secret store, rotates what it can, and never asks an agent to handle them.
API key & secret
A Fivetran API key and secret, either account-scoped or a system key.
Security & governance
Governance is applied once, at the layer every agent runs through, so it holds no matter which agent asks.
Metadata-first mining
Modus learns from structure and usage, not bulk data. Raw records stay in your environment; only the metadata needed to understand the system is stored.
Scoped selection
You choose exactly which schemas, folders, spaces, or boards Modus is allowed to see. Nothing outside the selection is ever mined.
Write approval
Actions that change state in the source system are marked as writes and require an explicit human confirmation before they run.
Group access by sensitivity
Map your identity groups to sensitivity tiers so each team only ever composes context at or below its clearance.