Back to vendors
D

Datafold

Also known as: Datafold Migration Agent

Visit site
Entry priceOutcome based fixed price scoped per migration by number of legacy objects and complexity, with timeline and data parity guaranteed by contract. No public dollar figure.Full pricing detail

Data engineering automation platform whose AI Migration Agent translates and validates data pipelines to full parity, with a Data Knowledge Graph and MCP tools that give coding agents the lineage and business logic of the customer's data.

Datafold automates data engineering. Its lead product is the Datafold Migration Agent, delivered as a managed service supervised by Datafold's team. The agent translates legacy code (SQL dialects, stored procedures and GUI based ETL tools such as Informatica, SSIS, Matillion and Talend) into modern targets such as dbt. It checks the result with value level cross database diffs and corrects itself from compilation errors and data discrepancies until the new pipelines match the old ones. The customer receives a report linking the diffs that prove parity or explain each discrepancy.

Beyond migrations, Datafold runs AI code reviews on every pull request, data diffs in CI, monitors for metrics, tests and schema changes, and a Slack assistant. A Data Knowledge Graph of lineage, business logic, usage and ontology gives context to Datafold's agents and, through an MCP server whose tools create diffs and edit alerts, to the customer's own coding agents. Admins can route the agents to their own LLM provider, from OpenAI and Anthropic to Bedrock, Vertex AI, Databricks or Snowflake Cortex.

Datafold's trust center covers SOC 2, HIPAA and GDPR. It supports SSO through Okta, SAML and Microsoft Entra ID, along with roles, service accounts and an audit log API. It runs as SaaS in a US or EU region or as a single tenant deployment in a VPC on AWS, GCP or Azure, including in the customer's own account. Migrations are priced as a fixed, guaranteed amount scoped by code objects and complexity.

Vendor details

Canonical URL

https://www.datafold.com

Category

Data analyst agent

Funding status

Independent, venture backed data engineering company. Specific funding figures were not retrieved this session.

Company status

independent

Use cases & customers

Primary use cases

AI data migrationcross database data validationdata quality testing in CI/CDdata monitoring and lineagecontext layer for coding agents

Target customers

enterprisedata teamsdata engineersanalytics engineers

Deployment options

SaaSVPCin-VPC AWSin-VPC GCPin-VPC Azure

Integrations

Datafold connects to legacy and modern data sources, including SQL Server, SAP Hana, MySQL, Netezza, Oracle, Teradata, Redshift, Snowflake and BigQuery. It also works with dbt, Coalesce, Airflow, Informatica, SSIS, Talend, Matillion and Microstrategy, and with GitHub, GitLab and Azure DevOps. Data Diff and monitors are available through MCP.

In practice

A team moving off a legacy warehouse has the Migration Agent translate its pipelines, check each translation against the source with value level data diffs and correct itself until parity, ending with a report that links the diffs.

An analytics engineering team gets an AI Code Review on every pull request in GitHub, GitLab or Azure DevOps, with a summary comment and inline suggested changes that a person merges.

An engineer's own coding agent connects to Datafold's MCP server to read lineage and business logic from the Data Knowledge Graph and run a data diff, under a service account limited by group permissions.

Agentic Index coverage score

11.5 / 14 capabilities · 82%

Integrations & Tool Calling Full

Datafold's AI Code Reviews post a summary comment and inline suggested changes on pull requests through its GitHub, GitLab and Azure DevOps apps, and the Migration Agent works across legacy and modern warehouses, ETL tools and the customer's code repository to translate pipelines.

Sourcedocs.datafold.com/deployment-testing/ai-code-reviews.mdread 2026-09-28

Workflow Orchestration Partial

The Migration Agent runs a fixed loop of translating, compiling, diffing and self correcting until parity, and code reviews pass through a review supervisor. The LLM provider settings refer to migration goals and per role model overrides, but the roles are not described, and customers cannot compose their own branching or flows.

Sourcedocs.datafold.com/data-migration-automation/datafold-migration-agent.mdread 2026-09-28

Knowledge Grounding & RAG Full

The Data Knowledge Graph serves the customer's lineage, business logic, usage, ontology and organizational knowledge to Datafold's agents and, over MCP, to the customer's own coding agents.

Sourcedatafold.comread 2026-09-28

Human Oversight & Guardrails Partial

Admins limit which MCP tools an agent's service account can call through group permissions, hiding the rest, and code review suggestions wait for people to merge them in their own Git host. Datafold's engineers oversee migrations as part of its service, which the customer does not operate, and there is no approval step before an agent action commits.

Sourcedocs.datafold.com/security/mcp-tool-permissions.mdread 2026-09-28

Security, Identity & Governance Full

The SafeBase trust center lists SOC 2, HIPAA and GDPR with reports available on request, and Datafold supports SSO through Okta OIDC, Google OAuth, SAML and Microsoft Entra ID with group provisioning, user roles and permissions, custom groups and service accounts.

Sourcesecurity.datafold.comread 2026-09-28

Observability & Auditability Full

An audit log API returns each action with the user, IP, request, object type and ID, status and payload, and agents act through service accounts whose MCP tool calls run under named permissions. Datafold does not say whether the log marks an action as an agent's.

Sourcedocs.datafold.com/api-reference/audit-logs/get-audit-logs.mdread 2026-09-28

Memory & State Persistence Partial

The Slack assistant rereads the latest messages of a thread on every turn, about fifteen messages, so context lasts within a thread. The agents keep no memory across sessions with a set scope and lifetime, and the Data Knowledge Graph holds the customer's knowledge, not the agents' own memory.

Sourcedocs.datafold.com/integrations/agents/slack-bot.mdread 2026-09-28

Deployment & Data Residency Full

Multi tenant SaaS runs in US West (Oregon) or Europe (Ireland) at the customer's choice, and Dedicated Cloud deploys a single tenant instance in a VPC on AWS, GCP or Azure, hosted by Datafold or in the customer's own account and managed by either party.

Sourcedocs.datafold.com/datafold-deployment/datafold-deployment-options.mdread 2026-09-28

Prebuilt Agents / Templates / Packs Full

Datafold ships specialized agents that each do their own job. The Migration Agent translates and validates pipelines, AI Code Reviews review pull requests, and a Slack assistant answers questions about data sources, lineage, monitors and diffs. An optimization agent is also named, without a description.

Sourcedatafold.comread 2026-09-28

Triggers & Channel Coverage Full

AI Code Reviews run automatically whenever a pull request is created or updated, monitors run on schedules and alert on data diffs, metrics, tests and schema changes, and people reach the assistant by mentioning it in Slack or through MCP clients.

Sourcedocs.datafold.com/deployment-testing/ai-code-reviews.mdread 2026-09-28

Model Flexibility & Routing Full

Organization admins register their own LLM provider (OpenAI, Anthropic, Google Gemini, Azure AI Foundry, AWS Bedrock, Google Vertex AI, Databricks, Snowflake Cortex or any OpenAI compatible endpoint) and set models for goals, project defaults and per role overrides; without one the Migration Agent runs on Datafold managed inference.

Sourcedocs.datafold.com/integrations/llm-providers.mdread 2026-09-28

APIs / SDKs / MCP Extensibility Full

A Datafold API and SDK sit beside an MCP server at app.datafold.com/mcp authenticated with an API key, whose permission table names tools such as list_data_sources, create_datadiff and edit_alert that create and change Datafold's own objects.

Sourcedocs.datafold.com/api-reference/mcp-server-setup.mdread 2026-09-28

Testing, Debugging & Optimization Full

The Migration Agent's translated code is checked against the source by value level data diffs, and the agent corrects itself from compilation errors and data discrepancies until parity is reached, so its output does not pass until the data matches. The final report links the diffs proving parity or explaining each discrepancy.

Sourcedocs.datafold.com/data-migration-automation/datafold-migration-agent.mdread 2026-09-28

Browser / Computer-use Not documented

Datafold's agents work through data source connections, Git apps, the API and MCP tools and do not control a browser, desktop or computer.

Sourcedocs.datafold.com/datafold-mcp.mdread 2026-09-28

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Pricing

Outcome based fixed price scoped per migration by number of legacy objects and complexity, with timeline and data parity guaranteed by contract. No public dollar figure.

A fixed price per migration, scoped by the number of legacy objects and the migration's complexity.

What is public

The migration pricing basis (code objects and complexity, fixed and guaranteed) is public. No dollar figure is published for migrations or for the platform.

Cost watchouts

Datafold does not provide IT configuration or education services, so environment setup may take internal effort or a systems integrator. Marketplace private offer terms may differ from direct terms.

Variable cost rationale

Nothing is metered during a migration. The price is fixed upfront from the number of scoped objects and their complexity, so a larger or more complex estate raises the quote rather than the bill. Once the scope is set, the price holds. There is no hourly billing and no scope creep by design, and the timeline and data parity are guaranteed by contract.

Sales call required

Yes, required for paid access

Free / trial

None published, quote and demo on request

Lowest paid plan

Not published, fixed price per migration

Key ambiguities

The pricing model is public (per object, fixed, guaranteed), but no dollar figure is published. The final price depends on the scoped object count and complexity.

Cancellation / refund

Each migration is a fixed price, with the timeline and data parity guaranteed by contract. No cancellation or refund terms are published.

Support SLA / resale

Sold direct, through data platform partners and as a Google Cloud Marketplace private offer. Datafold does not provide IT configuration or education services.

Agentic Index verified 2026-09-28

Alternatives to Datafold

The closest documented capability profiles to Datafold among data analyst agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • Hex12.5 / 14Fuller documented coverage on Workflow Orchestration and Human Oversight & Guardrails
  • Wisdom AI11.5 / 14Fuller documented coverage on Workflow Orchestration
  • ThoughtSpot12.0 / 14Fuller documented coverage on Workflow Orchestration and Human Oversight & Guardrails
  • Zenlytic11.0 / 14Fuller documented coverage on Workflow Orchestration
  • Opensee10.0 / 14Fuller documented coverage on Human Oversight & Guardrails
  • Querio9.0 / 14A lighter documented profile than Datafold

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.