Waterfall account enrichment
Enriches an account with a single provider. Returns a no-data status when the provider has no match.
Authored by Sid Chaudhary
Founder & CEO at Intempt
Agentic workflow
Coming soon7 steps Blu runs end to end. It drafts a plan and nothing runs until you approve it.
- 1
Fill the gaps at lowest cost
Coming soonBlu builds a step
- 2
Try the cheap provider first
Coming soonBlu builds a step
- 3
Stop if nothing is missing
Coming soonBlu builds a step
- 4
Fall through to a specialist
Coming soonBlu builds a step
- 5
Research the long tail
Coming soonBlu builds a step
- 6
Record what it cost to find
Coming soonBlu builds a step
- 7
Publish and watch the mix
Coming soonBlu builds a step
About this recipe
When to use it
A single enrichment provider always misses some accounts. This falls through a cascade of providers, and finally AI research, only spending more when the cheaper source actually missed.
What it delivers
Runs a multi-source enrichment cascade - try the primary provider, fall through to secondary, then tertiary, then an AI-research fallback for unstructured discovery - maximizing coverage while minimizing per-record cost.
How you prompt this
Describe the outcome in your own words and Blu Agent maps it to this recipe, or run it by name. It drafts a plan first and nothing runs until you approve it.
Tell Blu Agent what you want
“Enriches an account with a single provider. Returns a no-data status when the provider has no match.”
recipe.md preview
Built from the published catalog. Blu Agent's full step prompts load in your workspace when you run it.
Inputs & outputs
What the recipe needs before it runs, and what it leaves in your workspace.
Inputs
- Nothing declared beyond an Intempt workspace. Blu asks for anything else it needs as it goes.
Outputs
How the recipe runs
Blu follows the steps in order and shows you each one before anything goes live.
- 01Fill the gaps at lowest costCreate a workflow 'Waterfall account enrichment' triggered by account_created OR scheduled refresh for stale accounts (no enrichment update in 90 days). Goal: maximize fill rate on key account attributes (firmographics, technographics, decision-makers, funding) while minimizing cost by querying premium providers only when cheaper ones fail.
- 02Try the cheap provider firstThis step builds a workflow. Configure first enrichment step to query the primary provider (configurable: typically the cheapest provider with broad coverage, e.g. Apollo or Clearbit). Targets: company name, size, industry, tech stack, revenue band, key decision-makers. Outputs to account attributes. Mark fields successfully filled to inform downstream branching. Use the result of "Fill the gaps at lowest cost".
- 03Stop if nothing is missingThis step builds a workflow. Branch step: did the primary enrichment fill the required fields? If YES to skip to AI-fit-scoring. If NO (missing email format, missing decision-maker, or missing tech stack) to continue to secondary provider. Saves money by not paying for premium providers unless needed. Use the result of "Fill the gaps at lowest cost", "Try the cheap provider first".
- 04Fall through to a specialistThis step builds a workflow. Configure second enrichment step that fires only on the no-coverage branch. Query secondary provider (configurable, typically a specialist provider for the missing field type, e.g. ZoomInfo for decision-makers, BuiltWith for tech stack). Only fills fields the primary missed; doesn't re-query already-filled fields. Use the result of "Fill the gaps at lowest cost", "Stop if nothing is missing".
- 05Research the long tailThis step builds a workflow. Configure AI research step that fires when secondary provider also fails to fill a key field. Tasks: scrape the company website, summarize what the company does, identify likely buyer personas from About/Team/Leadership pages, look up recent news for funding/hiring signals. Returns structured output (industry, ICP-fit description, 3-5 decision-maker names with titles). The Claygent-equivalent for the long tail where structured providers have no data. Use the result of "Fill the gaps at lowest cost", "Fall through to a specialist".
- 06Record what it cost to findThis step builds a workflow. Configure the update step that writes all enriched data back to the Account record. Includes a metadata field 'enrichment_source_used' (primary / secondary / ai-research) so RevOps can audit cost per record. Also writes enrichment_confidence (high/medium/low based on which tier filled the data). Use the result of "Fill the gaps at lowest cost", "Try the cheap provider first", "Fall through to a specialist", "Research the long tail".
- 07Publish and watch the mixValidate the workflow DAG and publish for live execution. Set up a daily summary of enrichment-tier-usage so RevOps can monitor cost (e.g. '80% filled at primary tier, 15% at secondary, 5% needed AI research' = healthy cost profile). Use the result of "Fill the gaps at lowest cost", "Record what it cost to find".
Install Intempt and run it
- 1
Sign up
Create a free Intempt workspace.
- 2
Connect your data
Add the sources this recipe reads from.
- 3
Ask Blu
Type /waterfall-account-enrichment in Blu once this recipe is live there.
- 4
Review and approve
Blu builds each step and waits for your OK before anything goes live.
Related recipes
Sid ChaudharyDiscovery call qualification fieldsGenerates an AI summary for Discovery calls from meeting data using the qualification framework in the summary recipe.View recipe Sid ChaudharyPost demo nurtureKeeps a demo warm for 90 days with a playbook, a case study, an ROI calculator and a customer story, and pulls the AE in early if they bite.View recipe Sid ChaudharyReturn rate by categoryShows which product categories get returned most, and which ones have got worse since last quarter.View recipe 