AI account research
Reads a target account's website, pulls out the decision makers, scores the fit against your ICP, and drafts an opener for the rep to edit.
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
Start on a high value account
Coming soonBlu builds a step
- 2
Read their website
Coming soonBlu builds a step
- 3
Summarise what they do
Coming soonBlu builds a step
- 4
Score them against your ICP
Coming soonBlu builds a step
- 5
Draft the opening line
Coming soonBlu builds a step
- 6
Write it onto the account
Coming soonBlu builds a step
- 7
Publish and check the picks
Coming soonBlu builds a step
About this recipe
When to use it
Every SDR does the same manual research loop before a first touch: scrape the site, skim the news, guess at decision-makers. This automates it end to end and drops the result straight into the account record.
What it delivers
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.
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
“Reads a target account's website, pulls out the decision makers, scores the fit against your ICP, and drafts an opener for the rep to edit.”
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.
- 01Start on a high value accountCreate a workflow 'AI account deep research' triggered by account_created (high-tier accounts only: by ICP fit or domain-tier flag) OR manual trigger from a list view ('research these 50 accounts'). Goal: produce a structured account-intelligence brief that a rep can act on without doing their own research.
- 02Read their websiteThis step builds a workflow. Configure web scrape step targeting the account's domain. Fetch: homepage hero copy, About page, Team/Leadership page, Pricing page (if exists), Customers page, recent blog posts. Returns raw page content to feed into the AI summarization step. Respect robots.txt; rate-limit per domain. Use the result of "Start on a high value account".
- 03Summarise what they doThis step builds a workflow. Configure AI research step that takes the scraped content and produces a structured summary: (a) one-sentence company description, (b) primary product/service, (c) ICP signals (target market, stated customer types), (d) recent priorities inferred from homepage / blog (e.g. 'expanding internationally', 'launching AI features'), (e) decision-maker names + titles from leadership page, (f) any mentioned competitors / partners, (g) confidence score on each finding. Use the result of "Start on a high value account", "Read their website".
- 04Score them against your ICPThis step builds a workflow. Configure a second AI step that scores ICP fit using the company summary + a provided ICP definition (industry, size, tech, use cases). Output: numeric 0-100 score + reasoning string ('Strong fit because they are a B2B SaaS in [target industry] with ~50 employees and recently raised Series A: matches our ICP for growth-stage teams'). Records a structured fit_score + fit_reasoning attribute. Use the result of "Start on a high value account", "Summarise what they do".
- 05Draft the opening lineThis step builds a workflow. Configure AI write step that produces a draft outreach opener referencing specific findings (not generic). Format: 2-3 sentences referencing a SPECIFIC fact from the research ('I saw your team is expanding into APAC...'), then a value-hypothesis ('Teams growing internationally typically struggle with X: that's where we help'), then a soft CTA. Output stored on the account for SDR review-and-edit, never auto-sent. Use the result of "Start on a high value account", "Summarise what they do", "Score them against your ICP".
- 06Write it onto the accountThis step builds a workflow. Write back to the Account record: company_description, primary_product, recent_priorities, decision_makers_inferred (array), competitors_mentioned, fit_score, fit_reasoning, ai_drafted_opening, research_completed_at. The SDR sees a fully-formed account brief without doing any manual research. Use the result of "Start on a high value account", "Summarise what they do", "Score them against your ICP", "Draft the opening line".
- 07Publish and check the picksValidate workflow DAG and publish. Add a daily summary digest of new accounts researched + their average fit scores so SDR managers can audit which accounts AI is flagging as best-fit. Use the result of "Start on a high value account", "Write it onto the account".
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 /ai-account-research-deep-dive 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 