A Consultant Turns a Company Name Into a Scored Lead in Under 20 Minutes
Using only Google's tools, an AI consultant built a two-command Gemini pipeline that produces a researched company profile, a 0–16 qualification score and an outreach draft in under 20 minutes, instead of about 45 minutes of tab-switching.
Who this is about: AI implementation and strategy consultancy
What it takes
- Cost
- Free planGemini: Free with a Google account. Google AI Plus is $4.99 a month and Google AI Pro is $19.99 a month; Ultra starts at $99.99.Price checked Oct 15, 2026 on gemini.google. Prices change; check before you buy.
- Setup time
- An afternoonOur estimate from the source, for one business.
- Skill needed
- No codeApps and settings only.
Explain it simply
A "lead" is a company that might become a customer. This consultant set up Google's AI, Gemini, so that typing one short command researches a company and a second one scores it from 0 to 16 on things like budget and need, then drafts a short message. What used to take 45 minutes of clicking between tabs now takes under 20.
What was done
Before opening any tool, he wrote down exactly what he sells and to whom, and defined four scoring dimensions (budget, need, timing, accessibility), each scored 0–4 based on observable evidence. A custom Gem holds the framework. "Research [Company]" runs Deep Research on the company with emphasis on its technology and AI posture.
"Score [Company]" identifies a decision-maker, scores the lead and drafts a LinkedIn message under 80 words. NotebookLM is used to challenge the scores, and Sheets tracks the pipeline.
How it went
Each lead took under 20 minutes instead of about 45. On test companies the scores pointed to different actions: one scored 14/16 (reach out now), one 13/16 but with a Need score of 1/4 (too advanced to need help), and one 9/16 (keep on radar).
- Limits: it was tested on only three companies. Deep Research takes 7–10 minutes per company and has daily limits on the $20/month Pro plan. It does not find targets for you, and finding the right person on LinkedIn is still manual. The full prompts sit behind a paywall.
Prompt
Research [Company Name] -> Deep Research: company fundamentals, AI & technology posture (priority), business momentum (last 12 months only), pain signals.
Score [Company Name] -> Find a decision-maker, score 0-4 on Budget, Need, Timing, Accessibility (cite evidence for each), total /16, and draft a LinkedIn message under 80 words that references something the contact actually said or published.The two commands are from the post; the scoring framework is adapted. The full instructions are paywalled.
Business fit
Who this helps, and how:
Agencies and freelancers: qualify prospects before spending time on a pitch, and lead with a specific angle.
AgenciesIndependent contractors (barbers, bartenders, consultants): consultants can weight the research toward the signals their own service depends on.
AgenciesStartup founders and e-commerce sellers: score potential B2B customers or wholesale accounts before outreach.
StartupsLocal service businesses: research commercial accounts (offices, property managers) before a contract pitch.
Local & serviceMedical and health professional business owners: vet potential referral partners or corporate wellness clients before reaching out.
Local & service
Related
- Evidence grade BA Reply-Only Bot Booked 20 Sales Calls in 8 Days From Cold EmailStrong evidence, using Grok Bot, Cold-email sending tool and Booking calendar
- Evidence grade CA Sales Team Turned Demo Calls Into HubSpot-Ready Notes and Follow-Ups With a Lindy AgentVendor or secondhand, using Lindy and HubSpot
- Evidence grade DA Founder Automated Outbound and Meta Ads With Claude Code and Hermes: 100 Leads Contacted a DayLight evidence, using Claude Code, Hermes Agent and Meta Ads CLI
- AI use cases for sales teamsDepartment hub: AI for sales, 34 examples
Similar tools
Other tools for this job, and how they differ. Chosen by our editors, never paid for.
“Strong evidence” (grade B) means: The person who did the work describes the setup and results in detail. How we grade. Spotted a mistake? Suggest a correction.