We Used Claude Cowork to Prospect 12 Companies and Draft 48 Emails in One Session

We needed to reach companies in the printing and packaging manufacturing space — the same industry as our first client, Orient Printing & Packaging. We had a case study with hard numbers (49 use cases mapped, 11 projects deployed, 85% faster document generation) and wanted to put it in front of the right people.

The traditional approach would be: spend a day researching companies, another day finding contacts, another day writing personalised emails, and then manually scheduling follow-ups over three weeks. We did all of it in a single Claude Cowork session.

Step 1: Prospect research

We gave Cowork a simple brief: find companies similar to Orient — Indian printing and packaging machinery manufacturers, 100–500+ employees, established, multiple departments, not yet AI-adopted. The kind of companies where the same use cases we deployed for Orient would immediately resonate.

Cowork searched the web, cross-referenced trade show exhibitor lists (Pamex, Printpack India, Labelexpo), pulled company data from corporate registries, and came back with 12 qualified prospects. Each one had a company profile, key decision-maker names, contact emails, and a rationale for why they fit.

It also tiered them by conversion probability. Tier 1 were companies with nearly identical DNA to Orient — same products, same scale, same operational patterns. Tier 2 were larger companies in the broader packaging ecosystem. Tier 3 were adjacent industries with the same complexity profile.

Step 2: Personalised outreach

This is where most outreach breaks down. Generic emails get ignored. But writing truly personalised emails for 12 companies takes hours of research per prospect.

Cowork drafted personalised initial emails for all 12 prospects. Each one referenced something specific about the company — a recent trade show, their product range, their global footprint — and bridged it to the Orient case study. The hook wasn't “do you want AI?” — it was “we did this for a company in your exact industry, here's what it looked like, want us to map your use cases?”

We also had Cowork recalibrate the tone. The first drafts were too salesy — words like “incredible pace” and “results were wild.” We pulled those back to match our brand voice: understated, warm, let the numbers speak. Cowork redrafted the entire batch with the corrected tone.

Step 3: Full email sequences

One email isn't a campaign. We had Cowork build a 4-touch sequence for each prospect:

• Day 1— Initial outreach with the Orient case study hook
• Day 3— Follow-up highlighting a specific deployed project (Offer Generator, BOM Generator, Troubleshooting Assistant) relevant to that prospect
• Day 7— New angle with a link to our blog article on AI deployment methodology
• Day 14— Graceful break-up email with the case study link, leaving the door open

That's 48 emails total. Each one different. Each one referencing something real about the prospect.

Step 4: Gmail drafts and scheduling

Cowork connected to Gmail and created all 48 emails as drafts, organised by prospect and sequence stage. We labelled them in Gmail for visual clarity: Settle/1-Initial, Settle/2-Day 3, Settle/3-Day 7, Settle/4-Day 14.

Then Cowork built a send calendar — Tier 1 goes first on Monday, Tier 2 on Wednesday, Tier 3 on Friday — with follow-ups staggered across three weeks. It created scheduled reminders at 9 AM IST for each send date, so we get a notification, open Gmail, filter by label, and hit send.

The entire outreach infrastructure — 12 prospects, 48 emails, a 3-week send calendar — was built in a single conversation.

What this means for deployment

This is exactly the kind of workflow we deploy for our clients. Not a chatbot answering questions — a structured system where AI does real operational work. The same approach that built this outreach campaign is what we use to build offer generators, RFQ systems, and troubleshooting assistants.

The pattern is always the same: give the AI structured context (our company brief, the Orient case study, the prospect list), clear instructions (tone, sequence structure, personalisation requirements), and the right tools (web search, Gmail integration). The output is production-quality work that would have taken a team days to produce manually.

That's what settling AI into a business actually looks like.