The RevvyAI Research Accounts node is in Beta. The product and this information may change. For questions contact your CSM.
Intelligent Workflows include nodes, called RevvyAI Research nodes, that use RevvyAI to create and use custom fields that assist with researching accounts and people.
Revvy AI Research nodes bring AI-powered web research directly into your workflows.
RevvyAI Research nodes provide information that may not already exist in your 6sense or CRM data and requires research across publicly available sources. This information provides additional input to your GTM automation.
RevvyAI Research nodes use one or more RevvyAI fields, which specify the public data. You can create a RevvyAI field by asking a research question about an account or person. RevvyAI researches publicly available information and returns the result in a structured format that can then be used elsewhere in your workflow.
For example, you can research:
Whether a company was mentioned in a podcast or video
Whether a company provides professional services for its products
You can use the resulting information to enrich records, make decisions, or drive downstream workflow actions.
For more information refer to Set Up RevvyAI Research Nodes and Best Practices for RevvyAI Research Nodes.
Supported downstream nodes in workflows
You can use RevvyAI fields with downstream nodes that take as input the selected output (text, number, list, and boolean) of the RevvyAI field. Currently this support includes:
Decision nodes
True/False
Branching
Update nodes
Convert Lead
Update CRM Account
Update CRM Contact
Update CRM Lead
Update Lead from Matched Account
Update MAP Lead
Enrichment nodes
Enrich CRM Accounts
Enrich CRM Contacts
Enrich CRM Leads
Enrich MAP Leads
Record limits
Record usage by RevvyAI Research nodes is subject to the applicable limits for your current plan. During Beta, a RevvyAI Research node can process up to 1000 records per execution. If your workflow contains more records than the configured limit, records beyond the limit are not treated as completed research.
Tip: Use segmentation or filtering when you want to control which records are researched first.
Credit usage
RevvyAI Research nodes use data credits, and charge 1 credit per record per RevvyAI field per research.
The existing enrichment credit model is separate from RevvyAI Research node execution charges.
Every RevvyAI Research node execution is treated as a new research execution and consumes the applicable credits.
RevvyAI Research node execution consumes resources even when it cannot find sufficient information for a record. Therefore, the RevvyAI Research node execution can consume credits even when the resulting field is blank.
FAQ: RevvyAI Research nodes
What happens if there isn't enough public information for a RevvyAI Research node?
RevvyAI may not be able to produce a meaningful result for every record. A lack of information does not necessarily mean that the underlying statement is false. For example, if you ask "Has this company announced plans to enter Germany?" and no reliable public evidence is found, the result should not be interpreted as proof that the company has no such plans.
For important business decisions, review the research output and supporting information before taking consequential action.
What happens if a RevvyAI Research node doesn't return a result?
A research attempt may not return a value when the AI cannot find sufficient information.
The RevvyAI Research node's refresh interval is still honored. The record isn't continuously re-researched simply because the previous research returned no value.
If the same account appears in multiple workflows, will it be researched again?
Yes. Research is associated with the record and RevvyAI field and are treated as completely independent every time the record appears in a workflow.
Will Revvy AI always return the correct answer?
No. AI research systems cannot guarantee that every result will be correct. Results can depend on:
Availability of public information
Quality and recency of sources
How specific the research question is
The complexity of the question
For important business decisions, we recommend reviewing the result and applying appropriate validation before taking action.
Should I use information already available in 6sense as a RevvyAI Research node prompt?
Not necessarily. If the information already exists as a supported 6sense field, generally you should use the existing 6sense data rather than consuming RevvyAI Research node credits to recreate it.
The RevvyAI Research node is most valuable for net-new intelligence that requires external research.
Document changelog
Sep 1 2026: First Beta release