DataByte

41 copilots, not one chat box.

A general assistant pointed at a data platform gives you confident answers about tables that do not exist. Every copilot here is scoped to one part of the platform, reads live metadata rather than a trained snapshot, and answers inside the permission model of the person asking.

41 copilots around the platform core41 named AI copilots ship inside the platform. They divide across the same four stages as the product itself: 15 that get data in, 9 that make it useful, 8 that put it to work, 9 that keep it trusted. Each one runs against live platform metadata rather than a trained snapshot, and each one answers inside the same permission model as the person asking.DATABYTE41copilots15Get data incopilots9Make it usefulcopilots8Put it to workcopilots9Keep it trustedcopilots
What a copilot reads before it answers.
The catalogue

Grouped the way the platform is.

The copilots divide across the same four stages as the product itself, with nothing left over. The largest group sits at the front, because getting data in reliably is where most of the work still goes.

All 41 copilots, grouped by what they doGet data in, 15 copilots: Flow Creator, Flow Summarizer, Source-to-Destination Builder, Change Data Capture Builder, Advanced ETL Executions, Deployment Planner, Ingestion Package Operations, Ingestion Insights, Ingestion Optimization Advisor, Ingestion Explorer, Connector Advisor, Connector Governance, Connector Usage Tracker, Integration Explorer, Integration Flow Builder. Make it useful, 9 copilots: Transformer Flow Builder, Transformer Explorer, Spark Advisor, Spark Execution Summarizer, Spark Pipeline Executions, Spark Package Operations, Spark Operations Assistant, Spark Infrastructure Monitor, Spark Optimization Advisor. Put it to work, 8 copilots: SQL Query Generator, Data-as-an-API Builder, API Explorer, MCP Server Analytics, DataOps Intelligence, Pipeline Failure Prediction, Databricks Monitor, Datadog SRE Monitor. Keep it trusted, 9 copilots: Data Source Onboarding, Data Profiling Assistant, Data Quality Analyser, Asset Certification, Lineage Tracker, Ontology Assistant, Classification and Sensitivity, Schema Change Impact, Governance Observability.THE COPILOT CATALOGUEGet data in15Flow CreatorFlow SummarizerSource-to-Destination BuilderChange Data Capture BuilderAdvanced ETL ExecutionsDeployment PlannerIngestion Package OperationsIngestion InsightsIngestion Optimization AdvisorIngestion ExplorerConnector AdvisorConnector GovernanceConnector Usage TrackerIntegration ExplorerIntegration Flow BuilderMake it useful9Transformer Flow BuilderTransformer ExplorerSpark AdvisorSpark Execution SummarizerSpark Pipeline ExecutionsSpark Package OperationsSpark Operations AssistantSpark Infrastructure MonitorSpark Optimization AdvisorPut it to work8SQL Query GeneratorData-as-an-API BuilderAPI ExplorerMCP Server AnalyticsDataOps IntelligencePipeline Failure PredictionDatabricks MonitorDatadog SRE MonitorKeep it trusted9Data Source OnboardingData Profiling AssistantData Quality AnalyserAsset CertificationLineage TrackerOntology AssistantClassification and SensitivitySchema Change ImpactGovernance ObservabilityEvery one runs against live platform metadata, inside the permission model of the person asking.
Copilots, grouped by the stage they act on.
By stage

What each one is for.

Get data in

15 copilots

Build, run and explain the pipelines and connections that move data onto the platform.

Flow Creator

Walks you through building an ingestion pipeline, one decision at a time.

Flow Summarizer

Explains what any ingestion flow does, what it ran, and how it went.

Source-to-Destination Builder

Builds a direct source to destination flow, including connections and column mapping.

Change Data Capture Builder

Sets up change data capture in log, query or trigger mode, with a preview before you commit.

Advanced ETL Executions

Answers questions on advanced ETL runs: status, resources, SLA, rule checks, traceability.

Deployment Planner

Plans an ingestion deployment and validates the schedule and resources before it lands.

Ingestion Package Operations

Monitors package runs, investigates failures and reads performance trends in plain English.

Ingestion Insights

One assistant for ingestion monitoring, troubleshooting, scheduling and configuration.

Ingestion Optimization Advisor

Recommends throughput, resource, scheduling and connector changes for pipelines you already run.

Ingestion Explorer

Searches and explains every ingestion deployment, package and execution in one place.

Connector Advisor

Finds the right connector, explains its operations, and lets you test it in the same conversation.

Connector Governance

Reports connector security posture, approvals, policies, classification and open incidents.

Connector Usage Tracker

Tracks connector health, traces, logs and live connectivity across your estate.

Integration Explorer

Opens up projects, integrations, executions, secrets and connectivity in one view.

Integration Flow Builder

Designs, validates and tests an integration route as a draft before anything goes live.

Make it useful

9 copilots

Design Spark transformations, then watch what they cost and where they slow down.

Transformer Flow Builder

Builds a Spark transformation end to end, from catalogue search to a deployed process group.

Transformer Explorer

Finds transformation deployments and reports their health, performance and cost.

Spark Advisor

Checks a transformation against the live processor catalogue and validates it before handoff.

Spark Execution Summarizer

Turns an execution into an answer: what ran, what failed, what was slow, what it cost.

Spark Pipeline Executions

Reads stage metrics, task diagnostics, shuffle statistics and the execution graph for you.

Spark Package Operations

Reports package throughput, resource use, SLA compliance and failure patterns.

Spark Operations Assistant

One assistant for Spark monitoring, troubleshooting and tuning, whatever your experience level.

Spark Infrastructure Monitor

Reports live cluster capacity: core allocation, memory pressure and pod demand.

Spark Optimization Advisor

Quantifies savings by category and names the over-allocated and under-allocated workloads.

Put it to work

8 copilots

Query, publish and operate. Ask in plain English, ship an API, catch a failure early.

SQL Query Generator

Writes executable SQL from a plain-English question using live metadata, never guessed names.

Data-as-an-API Builder

Turns a query into a published, parameter-validated API resource step by step.

API Explorer

Shows API pools, resources and clients, with usage, performance and access patterns.

MCP Server Analytics

Lists registered MCP servers, their tools and their health, and answers questions on them.

DataOps Intelligence

The consolidated view: SLAs, monitoring, rule checks, alerts, recommendations and cluster queues.

Pipeline Failure Prediction

Predicts a failure 15 to 60 minutes ahead and runs the remediation before the SLA breaks.

Databricks Monitor

Read-only watch on jobs, clusters, pipelines, streaming lag and catalogue failures.

Datadog SRE Monitor

Watches monitor transitions, SLO burn and synthetic failures, and routes alerts by severity.

Keep it trusted

9 copilots

Profile, classify, certify and trace every asset, and see what a schema change will break.

Data Source Onboarding

Verifies a new source, inspects its schema, and hands it to profiling and classification.

Data Profiling Assistant

Builds a statistical fingerprint of every table and column, with masked previews.

Data Quality Analyser

Recommends assertion rules from profiling history and rolls results into a quality score.

Asset Certification

Grants and revokes trust badges against documentation, quality and ownership checks.

Lineage Tracker

Traces a field back to its source at column level and explains the derivation in plain English.

Ontology Assistant

Maps schemas and columns to business terms, resolves synonyms and proposes taxonomies.

Classification and Sensitivity

Finds personal and financial data, tags it, and propagates the label down the lineage tree.

Schema Change Impact

Names every report, pipeline and dashboard a schema change will break, before it breaks.

Governance Observability

Watches freshness, latency and health, then raises an incident to the named data owner.

Ways to ask

The conversational surfaces underneath them.

The copilots are scoped agents. These are the general capabilities they are built on, available across the platform rather than tied to one module.

Talk to Your Data

Plain-English queries over SQL, NoSQL, S3, Cassandra, and APIs.

ETL/ELT Designer

Describe the requirement, and the agent ships a deployment-ready pipeline.

Spark Summarizer

Turns verbose Spark logs into "what ran, failed, was slow, fix this."

ProcBot Designer

Describe a process, and the agent generates the working script in bash, Python, Terraform, or Ansible.

Sherlock

Autonomous agents help with not only problem discovery but throughout the process from problem detection to auto-remediation and closure.

DataOps AI

Ask about pipeline health and SLAs; answers come from live telemetry.

AI Governance & Intelligence

AI agents continuously enrich metadata, classify sensitive data, monitor compliance, and generate governance insights across enterprise data assets.

Data Exploration AI

Describe the requirements in natural language, and the agent generates the transformation code behind the scenes to produce the output.

Agent Studio

Every copilot above was built in a studio you also get.

The catalogue on this page is not a fixed set that ships and stops. It is what our own teams built with the tooling that comes with the platform, and the same tooling is how you add the ones we did not think of.

Conversational

Waits to be asked

Answers a person in their own words, over certified data, with the source of every statement attached. Built for the people who have questions and no appetite for SQL.

Autonomous

Acts without being asked

Runs on a trigger or a schedule, decides what to do inside the boundaries you set, and stops for a person where you told it to. Built for the work nobody wants to own.

An agent you build starts governed.

It reads the same ontology, resolves names through the same catalogue, and answers inside the same permission model as everything else on the platform. Governance is not a layer you add to it afterwards, because there is nowhere else for it to run.

Agent operations

Then you have to watch them.

An agent that answers a question is a pipeline that nobody scheduled. It has runs, failures, cost and drift, and it needs the same operational treatment as anything else that touches production.

Telemetry, the same as any pipeline

Runs, failures, latency and cost across models, agents, prompts and executions, in the same operations view as your ingestion and transformation workloads.

Prompts go through release management

A prompt is tested and certified before it reaches production, and released as a version you can point at later. Changing one is a release, not an edit.

How they run

Three things that are true of every one of them.

Your permission model, not theirs

A copilot sees what the person asking is allowed to see. Row and column level rules apply to the answer the same way they apply to a query.

Live metadata, not a snapshot

Names of sources, tables and columns are fetched at the time of the question. A copilot that cannot find a column says so and asks.

On your infrastructure

The copilots run on self-hosted models inside your deployment, including air-gapped ones. No prompt and no result is sent to a model vendor.

Ask one of them something about your own stack.

Thirty minutes, your connectors, your tables. The copilots answer on live metadata, so you will see straight away whether they are useful.