Genesis Data Agents
Eve (System Manager)
System-level orchestrator for data agent lifecycle, mission management, and safe data operations. Provides coordination, governance, and utilities across agents, missions, and connected data systems.
Eve builds, alters, deploys, and monitors specialized data agents; manages missions & tasks; runs read-focused discovery/analysis; and coordinates artifacts, documentation, and collaboration across the platform.
Purpose
Orchestrate the lifecycle of data agents, manage missions/tasks, and coordinate safe data operations & collaboration.
Scope
Agent lifecycle, mission/task management, metadata discovery & safe queries, docs & artifacts indexing/exports/versioning, Slack/Sheets collaboration.
Design Goals
Deterministic & auditable operations, safety-first defaults for prod, reproducible & configurable workflows.
Typical Use Cases
Typical Use Cases
- Create & activate a specialized data agent with a tailored tool set
- Stand up a mission with tasks, dependencies, and cross-agent assignments
- Run read-only data discovery and summarize findings with safe sampling
- Index project documentation and answer grounded questions
-
Export deliverables to Sheets/files and notify stakeholders in Slack
Start with a minimal tool set and expand only when a mission requires it.
Inputs & Prerequisites
Inputs & Prerequisites
Connections & access
- Connected databases (e.g., Snowflake) with read permissions
- Optional: Google Drive service account for Sheets/Docs
- Slack activation and optional allow-list
- Optional web search key (for web queries where allowed)
-
Default schema:
GENESIS_DATA_AGENTS.EVE_WORKSPACE -
Default stage:
GENESIS_DATA_AGENTS.EVE_WORKSPACE.MY_STAGE - Mission structure: clear objectives, tasks, owners, and dependencies
Keep access read-only by default. Promote to write only for workspace outputs and with explicit confirmation.
Core Workflows
Core Workflows
1
Data agent lifecycle management
Create a new agent with precise instructions & tool grants; activate on Slack (open or allow-listed); update instructions/tools as needs evolve.
2
Mission & task management
Create missions, define tasks, wire dependencies, assign agents; track status, attach artifacts, summarize outcomes; maintain an audit trail.
3
Data discovery & analysis
Enumerate db/schema/table metadata; run safe, read-focused queries with LIMITs & optional controlled sampling; write intermediate results to the workspace on request.
4
Documentation & artifacts
Index data dictionaries/ERDs/specs; answer grounded questions; export tables to CSV/XLSX/Sheets; persist outputs in file storage; version artifacts with git.
5
Collaboration & operations
Post progress in Slack, create review Sheets, attach files to missions/tasks; configure/monitor background jobs; coordinate specialized agents (field mapping, data quality, pipelines).
Every mission maintains status, history, and linked artifacts for traceability.
Creating a Custom Data Agent (How Eve does it)
Creating a Custom Data Agent (How Eve does it)
Planning checklistParameter confirmation (prior to creation)
- Name & purpose: specialization + boundaries of responsibility
- Instructions: concise, operational guidance (inputs, outputs, constraints)
- Tool set: start minimal; add only what’s necessary
- Slack access: open vs allow-listed; channels to operate in
project_manager_tools, data_connector_tools, slack_tools, artifact_manager_tools, google_drive_tools, git_action, image_tools, web_access_tools, document_index_tools, file_manager_tools, delegate_work
Add snowflake_tools for warehouse queries; harvester_tools for metadata harvesting; manage_tests_tools for CI-style test orchestration.
- Agent name & short description
- Instructions text
- Initial tool set
- Slack activation: on/off, access policy
- Validate instructions; run a quick capability check
- Optionally deploy to Slack and set the access list
- Document the agent in the docs site and link to the missions it supports
Keep a small validation suite (sample prompts/queries) to sanity-check each new or updated agent before enabling it broadly.
Default Outputs
Default Outputs
| object | fields (examples) |
|---|---|
| Missions | id, name, status, target completion, history |
| Tasks | id, name, status, dependencies, assigned agent, work logs |
| Workspace objects | tables/views in GENESIS_DATA_AGENTS.EVE_WORKSPACE (on request) |
| Artifacts | files (CSV/XLSX/JSON), downloadable links, git-tracked documents |
| Document indices | list/search with grounding references |
All outputs are auditable and linked back to missions/tasks for end-to-end lineage of work.
Tools & Permissions
Tools & Permissions
Typically used by Eve
- project_manager_tools (missions, tasks, dependencies, status, history)
- data_connector_tools, snowflake_tools (metadata discovery, read-focused queries)
- document_index_tools (index/search documentation)
- file_manager_tools, artifact_manager_tools (persist/share outputs)
- google_drive_tools (Sheets/Docs collaboration)
- git_action (versioning of specs, notebooks, docs)
- slack_tools (updates, reviews, notifications)
- web_access_tools (read web pages/APIs when allowed)
- delegate_work (coordinate specialized agents)
- harvester_tools (metadata harvesting controls)
- genesis_job_tools, system_stats_tools (background jobs & system info)
Grant only the least privilege needed for the mission at hand. Review tool grants during post-mortems.
Safety & Operational Notes
Safety & Operational Notes
- Read-first on production data; use LIMITs & narrow scans
- Writes only to the workspace schema unless explicitly requested
- Confirmation required before destructive/irreversible actions
- Data minimization: mask PII/secrets; avoid external sharing without approval
-
Resource safeguards: avoid full scans/cross joins; stop if thresholds are exceeded
Never execute DDL/DML on production without explicit human approval and change-control references.
Configuration
Configuration
- Slack: activation, allow-list, channels
- Databases: connections, harvest inclusions/exclusions, intervals
- Workspaces: target schema/stage for outputs
- Exports: default formats (CSV/XLSX/Sheets), naming conventions, storage locations
-
Web/Docs: SERPer key (optional), Drive service account JSON (optional)
Store non-secret config in version control; keep secrets in a vault and reference them at runtime.
Orchestration Diagram
Orchestration Diagram
Quickstart Example (YAML snippets)
Quickstart Example (YAML snippets)
Wire this quickstart into your CI to smoke-test orchestration paths after changes.