Your AI data team
Your AI Data Team
Seven teammates. One workflow. They handle ingestion, transformation, analytics, dashboards, and data quality, with a team lead that runs the whole job. Describe what you need, they do the rest.
Meet the team
Each teammate owns one part of the data workflow.
Manager
Describe your goal in plain English and the Manager breaks it into steps, hands each one to the right teammate, builds the visual canvas, and deploys to Airflow. One conversation takes you from idea to running pipeline, start to finish.
Example Prompt
"Connect my GCS bucket gs://sales-data, clean the CSV files, deduplicate on order_id, and create a monthly revenue dashboard."
Capabilities
- Breaks complex requests into ordered steps automatically
- Delegates each step to the right teammate
- Visual pipeline canvas generation
- Airflow DAG creation and scheduling
- Follow-up conversations to refine results
- Dashboard creation from analysis results
How It Works
- 1You describe your goal in plain English
- 2The Manager creates a plan with ordered steps
- 3Each step runs: source connection, SQL generation, pipeline build
- 4You review and approve at each step
- 5The pipeline is saved, deployed, and optionally scheduled
Ingestion Engineer
The Ingestion Engineer walks you through connecting a new source step by step. It browses buckets and folders, selects specific files, validates connections, infers schema, and hands off to the next teammate, all conversationally.
Example Prompt
"Connect to my GCS bucket gs://company-data and show me what files are in the transactions/ folder."
Capabilities
- Interactive bucket and folder browsing
- File-level selection within folders
- Connection validation before proceeding
- Automatic schema inference from file samples
- OAuth token management for cloud sources
- Handoff to the pipeline build with a pre-configured source
How It Works
- 1You specify the source type (GCS, BigQuery, or REST API)
- 2It authenticates (OAuth for cloud, credentials for databases)
- 3It browses available resources (buckets, tables, endpoints)
- 4You select which data to ingest
- 5Schema is inferred and a data source record is created
Data Engineer
Describe a complete pipeline in one sentence. The Data Engineer gathers context from your connected sources, decomposes the work into ingestion, cleaning, and aggregation tasks, generates SQL for each node, lays out the canvas, and validates the result, all before you touch the builder.
Example Prompt
"Build a pipeline from my GCS sales CSV: deduplicate on order_id, calculate monthly revenue, and output an aggregation metrics table."
Capabilities
- Automatic task decomposition from natural language
- Source context gathering (schema, file formats, sample data)
- SQL generation per node with validation
- Visual canvas layout with connected nodes
- Clarification flow when the request is ambiguous
How It Works
- 1You describe the pipeline you want in plain English
- 2It reads your connected sources and schemas
- 3It decomposes the request into ingestion, cleaning, and aggregation tasks
- 4SQL is generated, validated, and assigned to each node
- 5A complete canvas layout is returned ready to deploy
Analytics Engineer
Describe a transformation in plain English and the Analytics Engineer generates SQL against your actual table schema. A five-layer validation pipeline checks column references, type safety, and security before you see the result, then re-runs transforms when your data or logic changes.
Example Prompt
"Remove duplicate orders by order_id, keep the latest updated_at, cast price to decimal, and filter out rows where status is cancelled."
Capabilities
- Schema-aware SQL generation (knows your columns and types)
- Column reference validation and fuzzy auto-correction
- Type safety checks (TRIM on integers, COALESCE type mixing)
- Security validation (blocks DROP, DELETE, ALTER)
- Automatic error correction when SQL fails validation
- Preview results before committing
How It Works
- 1You describe the transformation in the cleaning or aggregation node
- 2It reads upstream schema (columns, types, sample data)
- 3SQL is generated with full schema context
- 4Validation pipeline checks references, types, and safety
- 5You see a preview of the output and can edit or re-prompt
Analyst
Ask questions about your data in plain English. The Analyst queries both Iceberg tables and BigQuery, generates charts, and can pin results directly to dashboards. It routes each query to the right engine automatically.
Example Prompt
"What were the top 10 products by revenue last month? Show me a bar chart."
Capabilities
- Natural language queries across all data sources
- Multi-source routing (Iceberg via DuckDB + BigQuery)
- Automatic chart type selection based on results
- Pin visualizations directly to dashboards
- Follow-up queries to refine analysis
How It Works
- 1You ask a question (e.g. "What was revenue by region last quarter?")
- 2It detects the right source (Iceberg table or BigQuery)
- 3SQL is generated and executed against your data
- 4Results are returned with an auto-selected visualization
- 5You can pin the chart to a dashboard or ask a follow-up
BI Developer
Describe the dashboard you want and the BI Developer builds it: it analyzes your tables, generates queries, picks chart types, and lays out widgets automatically. Then refine it through conversation. Add, update, remove, or reorder widgets on request, with every change validated and applied to the live dashboard instantly.
Example Prompt
"Create a dashboard showing monthly revenue trends and top 10 customers by spend, then change the revenue chart to a line chart and add a KPI tile for total orders."
Capabilities
- Text-to-dashboard from a single prompt
- Understands what metrics and dimensions you need
- Schema-aware query generation against your tables
- Automatic chart type and layout selection
- Conversational editing: add, update, remove, and reorder widgets
- SQL validation before changes apply to the live dashboard
How It Works
- 1You describe the dashboard (e.g. "monthly revenue by region")
- 2It identifies the metrics and dimensions you need
- 3Columns are resolved against your actual table schemas
- 4SQL queries and chart configurations are generated automatically
- 5You refine through conversation, and changes apply to the live dashboard
Quality Engineer
Analyzes your table schemas and data patterns to generate quality checks automatically. Combines schema analysis, semantic pattern matching, and LLM inference with confidence scoring to surface the rules that matter most, so a bad number gets caught before a stakeholder sees it.
Example Prompt
"Generate data quality rules for my cleaning customers table."
Capabilities
- Automatic schema analysis (types, nullability, uniqueness)
- Semantic pattern detection (emails, dates, currencies)
- LLM-powered business rule inference
- Confidence scoring for every generated check
- Approval routing: auto-approve high-confidence, review the rest
How It Works
- 1You select a table or pipeline layer to monitor
- 2Schema analyzer inspects column types and statistics
- 3Pattern detector identifies semantic patterns in your data
- 4Business-rule checks are generated from context
- 5Checks are scored and routed for approval
Bring Your Own LLM
OptimaFlo is BYOLLM — you provide your own API key (OpenAI, Anthropic, Google, or any OpenAI-compatible endpoint). Your prompts and data never pass through our servers. The AI runs against your key, in your cloud.
Explore Further
See how the agents connect to the rest of the platform.
Seven AI teammates. Your LLM key. Your cloud.
Enhancing data owners with a team of AI agents. From raw data to dashboards, all in your own cloud.
© 2026 OptimaFlo. All rights reserved.