Clone Your Closed Deal
Takes the account you just closed, uses a similarity model to find its lookalikes, works out which are worth pursuing, and gets personalized outreach sequenced to the right contact at each - one continuous chain from closed deal to working pipeline.
The play
One continuous workflow, from the deal you just closed to lookalikes found, scored, and sequenced into outreach.
Find & score lookalikes
Seeds ZoomInfo's similarity model with the account you just won, enriches every match with firmographic and growth data, then scores and tiers the list with a why-now.
Recommend & personalize
Names the right contact at each top-tier lookalike and drafts a personalized email anchored on the lookalike fit.
Sequence outreach
Hands the drafted email to your rep's CRM/SEP tool to run the actual send cadence - the one step in this chain with no packaged skill behind it yet.
Test this workflow
(Use the ZoomInfo MCP tools if available; otherwise use the GTM CLI. Use the tool schema or CLI help for supported commands.) I just connected ZoomInfo. Help me complete the job below. 1. Read my saved business context with get_gtm_context, or the CLI equivalent. This read is free. Use the returned offerings, ICP, and role to frame the work. If context is missing, continue with the information we have. Save changes only if I explicitly ask; a first briefing does not require updating shared business context. 2. Run the "Clone Your Closed Deal" workflow example I selected in the marketplace - a chained sequence of 6 steps. First, and before doing anything else, ask me for the essential input this workflow needs, in a single message (e.g. the account we just closed, and what we sell) - do not start any research, tool call, or skill below until I've answered. If I don't have a specific account handy, suggest I try a placeholder like "Acme Corp" to see how it works, then invite me to rerun with a real one to make it mine. Only once I've given you that input, run these steps in order, passing each one's output into the next: 1. **Find Similar** - Find lookalikes to the account you just closed 2. **Enrich Company** - Enrich each lookalike with firmographic and growth data (Enrich Company is a per-company paid lookup, and Find Similar can return up to 100 lookalikes - cap this step at the top 20-25 by similarity score, not the full result set, before it feeds Score Accounts.) 3. **Score Accounts** - Score and tier the lookalikes, with a why-now 4. **Recommend Contacts** - Recommend the right contact at each top-tier lookalike 5. **Personalize Email** - Draft personalized outreach anchored on the lookalike fit 6. Sequence the outreach across channels - no packaged skill yet, so this is a manual hand-off. Tell me plainly what to copy and where it typically goes (a CRM task, Slack ping, or shared inbox), instead of stopping silently once the automated steps are done. Preserve this job instead of offering a new task menu. Close with a compact, copy-ready summary of the concrete result - the account and contact, and the final artifact itself (a draft, a briefing, a shortlist) in its own block, not a narrative recap - so it can be pasted directly into a CRM task, email, or message. 3. Before calling a tool, check its schema or documented inputs rather than guessing at parameters. Ask only for missing inputs, in a single message, then name the tools and give a credit estimate if supported by their documentation. Label it as an estimate: actual charges depend on records and work done. Ask for approval once before paid research, then complete the selected job. If a tool call comes back "No approval received" or a similar permission response, say so plainly, name the tool, and continue with the remaining steps. Don't retry the same call hoping for a different result, and don't invent an approval that didn't happen. Include a source-coverage note of no more than 3 lines. Separate an unavailable or unauthorized source from a successful search with no matching records. If connection status is unknown, say so. Never infer "no customer history" from an empty result. Continue with available evidence and identify what is missing; use https://gtm.ai/guides/connect-customer-context for source setup. Recommend CRM changes as drafts. Applying them requires an available, separately connected CRM workflow and my authorization. Do not claim a CRM update was made by ZoomInfo research tools.
Opens with sample data first - swap in your real closed deal to make it yours.
Answer a few questions about the deal, your lookalike criteria, and how you want outreach delivered to get a tailored setup brief.
What a hit looks like
Sample outputAcme Corp just closed. Here's a top-tier lookalike, found and scored, ready to work.
Not a live result - run this workflow on your own account to generate a real one.
Account
Vantage Fluid Controls
vantagefluid.com
Signals
- Similarity match
- 94% model fit to Acme Corp
- Growth signal
- 22% headcount growth, past 12 months
- Tech signal
- Runs a competing point solution
Triggering signal: High similarity to Acme Corp, plus recent headcount growth
Contact
Priya Nandakumar
VP, Sales Operations
p.nandakumar@vantagefluid.com
Draft email
A fit we've seen before
Hi Priya - congrats on Vantage's growth this year. You came up as a strong match to Acme Corp, a company we closed recently that was outgrowing the same point solution you're running today. Worth 15 minutes to see whether the same fit applies here?
How this workflow works
Each step maps to a job to be done in our GTM taxonomy and a real, runnable skill. Expand a step for details.
1Find lookalikes to the account you just closedSeeds ZoomInfo's similarity model with the deal you just won, instead of a manual competitor search.
Runs the closed account through a similarity model trained on firmographic, technographic, and growth patterns, returning a ranked list of companies that look like it - not a guess at "who competes with them," but a model-scored match.
Outcome
A ranked list of lookalike companies, each with a similarity score back to the account you just closed.
Ways to customize
- Adjust how many lookalikes to pull — Widen the list for more volume, or narrow it if your team can only work a handful at a time.
Job & services underneath
- jtbd-039 · Find lookalike accountsICP & TAM Modeling
2Enrich each lookalike with firmographic and growth dataFills in the operating detail behind each similarity match so scoring has something to work with.
Pulls headcount, funding, tech stack, and growth signals for every lookalike the similarity model returned, turning a bare company name into a record worth scoring.
Outcome
Every lookalike carries the same enrichment depth as an account you'd research by hand.
Guardrail: Enrich Company is a per-company paid lookup, and Find Similar can return up to 100 lookalikes - cap this step at the top 20-25 by similarity score, not the full result set, before it feeds Score Accounts.
Job & services underneath
- jtbd-157 · Enrich with any GTM datapointData Quality & Enrichment
3Score and tier the lookalikes, with a why-nowTurns a list of similar companies into a ranked shortlist worth a rep's time.
Scores every enriched lookalike and assigns an A/B/C tier, surfacing a why-now for each - the growth or tech-stack signal that makes this the right moment to reach out, not just a plausible fit.
Outcome
A tiered shortlist, not a flat list of every lookalike the model returned.
Job & services underneath
- jtbd-007 · Prioritize which accounts to pursueAccount Research & Prioritization
4Recommend the right contact at each top-tier lookalikeNames a specific person to reach at each account worth pursuing, not just the account itself.
Takes the top-tier lookalikes and recommends a contact at each based on role fit and buying-committee position, so the next step has someone real to write to.
Outcome
A named contact with title and verified email at every account worth pursuing.
Job & services underneath
- jtbd-002 · Find the right person to contactBuyer Discovery
5Draft personalized outreach anchored on the lookalike fitWrites an email that opens with the specific reason this account looked like a fit, not a generic template.
Generates a short, personalized email per recommended contact, anchored on the similarity match and the why-now surfaced during scoring - the same fit reasoning a rep would use if they'd researched the account by hand.
Outcome
A ready-to-send draft per contact, each referencing real signal instead of boilerplate.
Job & services underneath
- jtbd-012 · Write personalized outreach emailsCampaign Orchestration
6Sequence the outreach across channelsNo packaged skill runs this step - it's a real hand-off to your CRM/SEP tool, not a gap in the chain.
Deciding the send cadence and channel mix is deliberately a separate job from writing the email (jtbd-012 explicitly excludes it, so it can't double as jtbd-014's work) - and that job lives in the CRM/SEP tool your reps already work in, not in an MCP skill. Push the drafted emails there to actually execute the sequence.
Outcome
The drafted outreach is loaded into your rep's existing sequencing tool, cadence and channels set there.
This is the one step in the chain with no packaged skill today, and not because it was missed - it's genuinely outside what a chat-driven tool can execute on its own. Needs a connected CRM/SEP tool (Outreach, Salesloft, or similar) to actually run.
Job & services underneath
- jtbd-014 · Execute multi-channel sequencesCampaign Orchestration
push destination outside ZoomInfo's own surfaces - the rep's CRM/SEP tool
See it walked through
Why this workflow
A closed deal is a proven pattern. The account that bought looks a specific way, and other companies that look the same way are a better-qualified starting point than a cold ICP search. This example seeds Find Similar's similarity model with the account you just closed, rather than searching the web for competitors by hand. From there it runs the result through the same enrichment, scoring, and personalization chain as our other examples: Enrich Company, Score Accounts, Recommend Contacts, and Personalize Email.
The chain's last step is different from the others. Sequencing the outreach across channels is a genuine hand-off to your rep's CRM/SEP tool (Outreach, Salesloft, or similar), not a 6th packaged skill. Deciding the send cadence and channel mix is deliberately its own job in our taxonomy, kept separate from writing the email so the two can chain without overlapping. That's exactly what happens here; it just means the chain's final link runs outside any MCP tool.
Try variations once you've made it yours. Run it against every deal closed in a given week instead of one at a time. Or narrow the lookalike list to a single vertical if you're testing expansion into one adjacent market instead of casting wide.
Created by
Hannah Telegen
Principal Product Operations Manager
At a glance
- Skills used
- 5
- Est. time
- 10-15 min
- Inputs needed
- The account you just closed, and what you sell
- A connected CRM/SEP tool, to actually run the sequence in step 6
Related content
Skill
Find Similar
Find companies or contacts similar to a reference entity using ZoomInfo's ML-powered similarity model — ranked lookalikes for TAM analysis, territory expansion, and prospecting.
Skill
Enrich Company
Look up a company's full profile by name, domain, ticker, or ZoomInfo ID — firmographics, financials, corporate structure, and growth signals in one place.
Skill
Score Accounts
Score and tier a list of accounts by ICP fit, intent, and trigger signals. Returns a composite 0–100 with explainable component breakdown, a specific "why now" per account, and the working weight set as a saveable filter.
Workflows
Zero History, First Call Ready
Takes a deal you just inherited with zero relationship history, maps the buying committee you don't know, names real people to fill the gaps it finds, and gets you credible on the one contact you already have a call booked with - before you dial.
Workflows
Perfect Storm: Signal-Based Outreach
Spots a "perfect storm" of buying signals on a tiered account, recommends the right contact, and drafts a signal-anchored outreach email - so a rep can act while the signal is still hot.