What it does
An AI agent autonomously researches a target account - scrapes the website, summarizes recent news, extracts decision-makers, scores ICP fit, and drafts an opening hypothesis - then populates the account record directly.
You get
a populated account record with research
ICP score
and an opening hypothesis
How it works
Start on a high value account
Create WorkflowRuns when a high tier account is created, or on demand against a list of accounts. The job is a brief a rep can act on without doing any research of their own.
Read their website
configure_web_scrape_stepFetches the homepage, the about page, the leadership page, pricing if there is one, the customers page and recent blog posts. It honours robots.txt and rate limits per domain.
Summarise what they do
configure_ai_research_stepFrom those pages: a one sentence description, the main product, who they sell to, what they are pushing on right now, the leadership names and titles, any competitors or partners mentioned, and a confidence score on each finding.
Score them against your ICP
configure_ai_research_stepA 0 to 100 fit score built from that summary against your ICP definition of industry, size, technology and use case, with a written reason for the number.
Draft the opening line
configure_write_with_ai_stepTwo or three sentences citing something specific from the research, then a hypothesis about the problem that creates, then a soft ask. Saved for the rep to edit, never sent automatically.
Write it onto the account
configure_update_attribute_stepThe description, main product, current priorities, decision makers, competitors, fit score, reasoning, drafted opener and the time it ran, all onto the account record.
Publish and check the picks
publish_workflowThe workflow is validated and published, with a daily digest of accounts researched and their average fit scores so managers can see what the AI is rating highly.
Ready to run this recipe?
Tell Blu what you need. It builds the segment, content, journey, and dashboard in minutes.
Sign up free
