.webp)
Account-based marketing with AI is no longer about plugging ChatGPT into your cold email sequence. It's about giving an AI agent a list of target accounts and watching it research every company, find every decision-maker, identify their specific pain points, write hyper-personalized outreach using their exact language, and then send the connection request — all without you switching tabs.
That's not a hypothetical workflow. GrowthSpree runs this exact process using Claude Cowork, Anthropic's AI agent for non-developers. In this guide, we break down the four-phase ABM workflow we built with Claude — from account list to sent connection request — so you can replicate it for your own B2B SaaS pipeline.
TL;DR: Account-based marketing with Claude AI compresses what used to take a BDR team days into a single session. Using Claude Cowork's browser automation and research capabilities, you can mine LinkedIn for decision-maker contacts across 15+ companies, build a structured spreadsheet, deep-research individual prospects via web search and LinkedIn activity, generate 5-message personalized outreach drips, and send connection requests — all from one interface. GrowthSpree uses this workflow to achieve 2–3x higher response rates compared to generic outreach.
What Account-Based Marketing with AI Actually Means in 2026
Account-based marketing (ABM) is a B2B strategy that treats individual target accounts as markets of one. Instead of casting a wide net, you identify specific companies and decision-makers, then create personalized campaigns tailored to their unique pain points, tech stack, and buying signals.
ABM with AI takes this further by automating the research-intensive steps that traditionally bottleneck the process. According to the State of ABM 2025 report, 78.7% of companies now incorporate AI into their ABM programs, primarily for personalization, predictive analytics, and targeting. The estimated average ROI from ABM programs is 137%, and 49.7% of organizations plan to increase ABM budgets in 2026.
The difference between AI-assisted ABM and traditional ABM isn't speed alone — it's depth. A BDR might spend two minutes per contact checking LinkedIn titles. Claude spends the same two minutes reading their posts, company news, and attribution philosophy — then maps that research to your product's value propositions.
Key Takeaway: ABM with AI in 2026 means using AI agents to automate research, personalization, and outreach execution — not just generating generic email templates, but creating context-rich, prospect-specific engagement at scale.
Phase 1 — Mine Target Account Contacts with Claude and LinkedIn
Contact mining is the process of systematically identifying and extracting decision-maker names, titles, and LinkedIn profile URLs from your target account list. This is traditionally the most tedious step in ABM — and the one Claude automates most dramatically.
Here's how GrowthSpree runs it. Start with a list of target company LinkedIn URLs — for example, 15 Series A/B SaaS companies in your ICP. Give Claude a single prompt: visit each company page, navigate to the People tab, search for marketing and growth roles, and add every match to a spreadsheet.
Claude uses Claude in Chrome to physically browse each company page, click into People, search for relevant roles, scroll through results, and compile everything into a live xlsx file. In GrowthSpree's demonstration, Claude mined 35+ contacts across 15 companies — CMOs, VPs of Marketing, Directors of Growth, and Heads of Product Marketing — into a single structured spreadsheet ready for CRM import. What takes a BDR 3–4 hours takes Claude one automated session.
Key Takeaway: Claude Cowork automates LinkedIn contact mining by browsing company pages, searching People tabs, and building structured spreadsheets — turning 3–4 hours of manual BDR work into one automated session across 15+ target accounts.
Phase 2 — Deep-Research Individual Prospects
Deep research in ABM means going beyond a prospect's job title to understand their specific challenges, priorities, public opinions, and the language they use to describe their problems. This is the step that separates hyper-personalized outreach from generic "I noticed you're a CMO" messages.
In GrowthSpree's workflow, Claude receives a specific prompt for each high-priority contact: research them via web search, scan their LinkedIn posts and comments, identify their pain points, and then map those pain points to GrowthSpree's tools. Claude uses the Web Search connector alongside Claude in Chrome to pull information from multiple sources simultaneously.
For one prospect — a VP of Marketing at a PLG-to-enterprise SaaS company — Claude identified four specific pain points: moving upmarket from prosumer to enterprise buyers, filtering enterprise ICP from 100K+ subscribers, her stated preference for real-time signals over monthly reports (pulled from her LinkedIn posts), and her need for ABM tied to pipeline rather than vanity metrics. Claude even extracted her exact quotes on attribution philosophy and the custom GPTs she'd built — all feeding directly into the outreach personalization layer.
Key Takeaway: Claude deep-researches prospects by combining web search with LinkedIn browsing, extracting their exact language, stated priorities, and pain points — producing research briefs that make outreach feel genuinely personal rather than template-driven.
Phase 3 — Generate Hyper-Personalized Outreach Sequences
A hyper-personalized outreach sequence is a multi-touch message series where every message references specific details about the prospect's role, company, challenges, and stated opinions — not just their name and title. This is where AI-powered ABM delivers its highest leverage.
Using the research from Phase 2, Claude generates a 5-message LinkedIn drip sequence structured as follows. Message 1 is the Connection Request — under 300 characters, referencing the prospect's specific philosophy or a recent public statement. Message 2 is the Value-First Touch — asking about a specific challenge the research identified, such as PLG-to-enterprise lead quality, without pitching anything. Message 3 is the Insight Share — introducing a relevant tool (like Zipeline for real-time signal monitoring) using the prospect's own "early signals" language. Message 4 is Social Proof — a case study from a similar-stage company facing the same transition, referencing specific metrics. Message 5 is the Direct Ask — mapping each GrowthSpree tool to the prospect's specific stated needs with a clear meeting request.
Claude outputs this as a formatted docx with the full research brief, pain point mapping, a tool alignment table, and all five messages with timing (Day 1, Day 7, Day 14, Day 21, Day 28). For a secondary ICP contact at a different company, Claude pulled a recent patent lawsuit as a personalization hook — research depth no template tool can match.
Key Takeaway: Claude generates 5-message LinkedIn outreach drips where every touchpoint references prospect-specific research — their exact language, company challenges, and stated priorities — delivered as a formatted document with timing and tool-alignment mapping.
Phase 4 — Execute Outreach Directly from Claude
Outreach execution in this context means Claude physically sending the LinkedIn connection request with a personalized note, using browser automation — closing the loop from research to action without leaving the interface.
GrowthSpree gives Claude a follow-up task: send the connection request. Claude navigates to the prospect's LinkedIn profile via Chrome, clicks Connect, clicks "Add a note," types the personalized 211-character message, and clicks Send. Claude confirms delivery by verifying the button changed from "Connect" to "Pending."
In GrowthSpree's demonstration, Claude sent the actual connection request with a note referencing the prospect's attribution philosophy — a detail extracted during Phase 2. The entire cycle from target account list to sent connection request happened within Claude Cowork. You're not just using AI to write outreach copy — you're running an end-to-end ABM pipeline where research, personalization, and execution happen in a single agentic workflow.
Key Takeaway: Claude doesn't just write outreach — it sends it. Using Claude in Chrome, the connection request is physically sent on LinkedIn with the personalized note, completing the full ABM cycle from account list to executed outreach in one session.
How to Set Up This ABM Workflow for Your Team
Setting up this workflow requires Claude Cowork (available on Claude's Max plan), the Claude in Chrome extension, and optionally the xlsx and docx skills for structured outputs. You need three things prepared before starting.
First, your target account list as LinkedIn company URLs — sourced from your CRM, Sales Navigator, or manual research. Second, a prompt template specifying the roles to mine (CMO, VP Marketing, Head of Demand Gen, Director of Growth) and output format. Third, a company context document describing your product, tools, and value propositions so Claude can map pain points to your offering. GrowthSpree's context document described Zipeline, QLA, and ABM Accelerator — enabling Claude to naturally weave product-specific value into every outreach message.
Key Takeaway: The workflow requires Claude Cowork, Claude in Chrome, a target account list as LinkedIn URLs, role specifications for mining, and a company context document — enabling any B2B SaaS team to replicate GrowthSpree's end-to-end ABM automation.
Ready to Run ABM That Actually Reaches Decision-Makers?
If your ABM still involves BDRs manually browsing LinkedIn and sending templated requests, you're competing against teams that have automated the entire pipeline. GrowthSpree's Claude-powered workflow compresses days of research into a single session — with personalization depth that template tools can't replicate.
Contact GrowthSpree for a free ABM workflow consultation.
Frequently Asked Questions
What is account-based marketing with AI?
Account-based marketing with AI is a B2B strategy that uses AI agents to automate the research-intensive steps of ABM — including target account identification, decision-maker contact mining, prospect research, personalized outreach generation, and execution. Instead of BDRs manually researching each account, AI tools like Claude handle research, personalization, and even message delivery at scale.
Can Claude AI actually send LinkedIn connection requests?
Yes. Using the Claude in Chrome extension, Claude Cowork can navigate to a prospect's LinkedIn profile, click the Connect button, add a personalized note, and send the request. In GrowthSpree's workflow, Claude sent a connection request with a 211-character personalized message referencing the prospect's specific attribution philosophy.
How many contacts can Claude mine from LinkedIn in one session?
In GrowthSpree's demonstration, Claude mined 35+ marketing and growth contacts across 15 target companies in a single automated session. The output was a structured spreadsheet with company name, person name, job title, and LinkedIn profile URL for each contact.
What makes AI-personalized outreach different from templates?
AI-personalized outreach references specific details from the prospect's LinkedIn activity, public statements, company news, and stated challenges. For example, Claude extracted a prospect's exact quotes on attribution philosophy and her preference for real-time signal detection, then wove those details into each message of a 5-touch sequence. Template-based outreach uses generic role and company name placeholders that prospects immediately recognize as automated.
Do I need coding skills to set up this ABM workflow?
No. Claude Cowork is Anthropic's AI agent designed specifically for non-developers. The entire ABM workflow — contact mining, research, outreach generation, and LinkedIn execution — runs through natural language prompts in the Cowork interface. No code, no API keys, no scripting required.
Key Facts & Data Points
Emphasize your product's unique features or benefits to differentiate it from competitors
In nec dictum adipiscing pharetra enim etiam scelerisque dolor purus ipsum egestas cursus vulputate arcu egestas ut eu sed mollis consectetur mattis pharetra curabitur et maecenas in mattis fames consectetur ipsum quis risus mauris aliquam ornare nisl purus at ipsum nulla accumsan consectetur vestibulum suspendisse aliquam condimentum scelerisque lacinia pellentesque vestibulum condimentum turpis ligula pharetra dictum sapien facilisis sapien at sagittis et cursus congue.
- Pharetra curabitur et maecenas in mattis fames consectetur ipsum quis risus.
- Justo urna nisi auctor consequat consectetur dolor lectus blandit.
- Eget egestas volutpat lacinia vestibulum vitae mattis hendrerit.
- Ornare elit odio tellus orci bibendum dictum id sem congue enim amet diam.
Incorporate statistics or specific numbers to highlight the effectiveness or popularity of your offering
Convallis pellentesque ullamcorper sapien sed tristique fermentum proin amet quam tincidunt feugiat vitae neque quisque odio ut pellentesque ac mauris eget lectus. Pretium arcu turpis lacus sapien sit at eu sapien duis magna nunc nibh nam non ut nibh ultrices ultrices elementum egestas enim nisl sed cursus pellentesque sit dignissim enim euismod sit et convallis sed pelis viverra quam at nisl sit pharetra enim nisl nec vestibulum posuere in volutpat sed blandit neque risus.
Use time-sensitive language to encourage immediate action, such as "Limited Time Offer
Feugiat vitae neque quisque odio ut pellentesque ac mauris eget lectus. Pretium arcu turpis lacus sapien sit at eu sapien duis magna nunc nibh nam non ut nibh ultrices ultrices elementum egestas enim nisl sed cursus pellentesque sit dignissim enim euismod sit et convallis sed pelis viverra quam at nisl sit pharetra enim nisl nec vestibulum posuere in volutpat sed blandit neque risus.
- Pharetra curabitur et maecenas in mattis fames consectetur ipsum quis risus.
- Justo urna nisi auctor consequat consectetur dolor lectus blandit.
- Eget egestas volutpat lacinia vestibulum vitae mattis hendrerit.
- Ornare elit odio tellus orci bibendum dictum id sem congue enim amet diam.
Address customer pain points directly by showing how your product solves their problems
Feugiat vitae neque quisque odio ut pellentesque ac mauris eget lectus. Pretium arcu turpis lacus sapien sit at eu sapien duis magna nunc nibh nam non ut nibh ultrices ultrices elementum egestas enim nisl sed cursus pellentesque sit dignissim enim euismod sit et convallis sed pelis viverra quam at nisl sit pharetra enim nisl nec vestibulum posuere in volutpat sed blandit neque risus.
Vel etiam vel amet aenean eget in habitasse nunc duis tellus sem turpis risus aliquam ac volutpat tellus eu faucibus ullamcorper.
Tailor titles to your ideal customer segment using phrases like "Designed for Busy Professionals
Sed pretium id nibh id sit felis vitae volutpat volutpat adipiscing at sodales neque lectus mi phasellus commodo at elit suspendisse ornare faucibus lectus purus viverra in nec aliquet commodo et sed sed nisi tempor mi pellentesque arcu viverra pretium duis enim vulputate dignissim etiam ultrices vitae neque urna proin nibh diam turpis augue lacus.
Related posts
