# Aslam C K, GTM Engineer > Aslam C K, GTM Engineer. I design and build GTM systems that fit the business: strategy, motion design and system design, using data, automation and AI as the implementation layer. This is the portfolio of Aslam C K. Every page below has a plain Markdown copy so AI assistants and agents can read it without running JavaScript. The full text of every page in one file is at https://aslamck.pages.dev/llms-full.txt. --- # Aslam C K | GTM Engineer > Aslam C K, GTM Engineer. I design and build GTM systems that fit the business: strategy, motion design and system design, using data, automation and AI as the implementation layer. Web page: https://aslamck.pages.dev/portfolio/ GTM Engineer # I design and build GTM systems that fit the business. Starting with the commercial objective, I work through the resources, market conditions, constraints and timeline to design the GTM motion, then engineer the systems needed to execute it. - View my work - [Book a conversation](https://cal.com/aslam-c-k/1v1) - [Resume](https://aslamck.pages.dev/portfolio/assets/Aslam-CK-Resume.pdf) - [Clay cohort portfolio ↗](https://cohorts.clay.com/@aslam-c-k) - Outbound Systems - GTM Strategy & Motion Design - AI-Native GTM Engineering Work ## Selected Systems Each system started with a business objective and a set of operating conditions, and the architecture came after. Flagship AI-Native GTM Intelligence & Outbound System ### Partner Intelligence Engine Problem: Branded packaged-food importers across 32 countries, including the UK, Australia and the United States: a fragmented, low-digital-presence market that conventional B2B databases couldn't see. System: An 8-agent research and qualification architecture on a custom data layer, running signal to personalized outreach with human checkpoints at every stage that mattered. - 322 Sourced - 230 Scored - 155 Verified - 41 Advanced - GTM Strategy - System Design - AI-Native GTM [View case study](https://aslamck.pages.dev/portfolio/case-studies/partner-intelligence-engine.md) Hiring assessment TAM Architecture & Enrichment ### TAM & Enrichment Architecture Problem: A 90K-phone-number target across a fragmented U.S. beauty & wellness market, with no single data source covering it well. System: Compared coverage and cost across three providers and sequenced an enrichment architecture around it, with Clay as the orchestration layer. - 90K Target #s - 108K Companies modeled - 3 Sources compared - GTM Strategy - System Design [View case study](https://aslamck.pages.dev/portfolio/case-studies/tam-enrichment-architecture.md) Freelance GTM Strategy & Motion Design ### GTM Motion Systems Problem: Two companies, 12+ services each, too broad to target as a single motion with limited resources. System: Narrowed each to one beachhead offer, then built the ICP, signals and outbound motion around that offer alone. - 2 Companies - 1 Beachhead / co. - Signal -based motion - GTM Strategy - Motion Design [View case study](https://aslamck.pages.dev/portfolio/case-studies/gtm-motion-systems.md) Freelance Cold Email Outbound Build ### Outbound for a Lead-Gen Funnel Service Problem: A small founder-led US service that builds lead qualification funnels and runs paid social ads wanted 10 to 20 more booked calls a month from cold email. System: ICP defined by sales motion and offer, not industry; 5 segments chosen from 12, with a beachhead and a stop rule; a signal ladder with anti-signals; a verified list; AI copy that writes or refuses each row; a code QA gate; 6 campaigns. Run by instructing Claude with MCP connectors and Claude skills, with fixed human gates. Booked calls and pipeline were not measured. - 28,526 Decision makers pulled - 2,393 Send-ready - 1.02% Reply rate, day 13 - 6 Positive replies, day 13 - GTM Strategy - Outbound Systems - AI-Native GTM Trust layer Brand Trust & Content Systems ### Minzelis Trust Infrastructure Problem: Outbound gets checked. If a brand's public presence looks unfinished, the reply doesn't come. System: An AI-assisted, brand-ruled content production system that keeps visual identity and output consistent without eating research time. - Rules Brand system - Prompt -based production - System Design - AI-Native GTM [View case study](https://aslamck.pages.dev/portfolio/case-studies/minzelis-trust-infrastructure.md) Personal Personal GTM Content Production System ### Aslam-CPS Problem: Proof of work needs to stay visible and consistent without consuming research time. System: A reusable content architecture: ICP, voice and brand rules in; ideas, prompts and visuals out. - Reusable Architecture - Personal ICP - System Design [View case study](https://aslamck.pages.dev/portfolio/case-studies/aslam-cps.md) Personal Personal Knowledge Base (RAG) ### Personal Knowledge Base Problem: I kept retyping the same facts about myself into job sites, applications, resumes, posts and profiles, and AI tools sometimes guessed them. System: One Supabase database of verified facts as the single source of truth. Nothing goes in until I confirm it, unmeasured result numbers are refused, every fact is labelled public or private, and AI tools retrieve facts by meaning instead of guessing. Designed and directed by me, built with Claude Code. - Verified Facts only - RAG Retrieval - System Design - AI-Native GTM Personal Social Engagement Capture (first stage) ### Social Listening Problem: People who comment on or react to a LinkedIn post are showing interest, and that signal is lost unless someone captures it. System: Continuous post scraping in Clay: my own posts, or a specific person, a competitor or a keyword. It pulls everyone who commented or reacted and enriches them. This is the first stage; CRM checks, qualification, scoring, tiering and routing to a sequence are designed but not built yet. - Clay Built with - Stage 1 Live - Social Listening - Signal Design Proof ## In numbers - 8 Specialized agents - 41 Sales-qualified, advanced to outreach in 2 weeks - 90K Phone-# target architecture - [Clay Certified: Outbound Orchestration Foundations ↗](https://cohorts.clay.com/c/253dd7c6-80df-4cd8-b3a5-05a31421b1fe) About ## About Aslam I started by trying to find customers for my brother's food business, a family business. No sales background, just business books, Alex Hormozi, a real problem and pressure to solve it. The job was simple to state: get customers. Manual lead research (Google, Scribd PDFs, UK Trade Info) turned into Apollo and Clay. I used Clay at first only for email verification, later for list building and then full workflow orchestration. The databases turned out to lack coverage for a fragmented ICP, so I moved to reverse-engineering competitors' distributor networks, and then to agents. That gap pushed me into custom data sourcing, ICP design, qualification, signal research, automation and agentic workflows. At the same time, I got increasingly interested in the strategy and motion behind the systems, not just the execution. That led me into freelance GTM work, and into structured learning through Clay University, Apollo Academy, Maven and the Clay Outbound Orchestration Foundation. What that learning covered: Clay's Outbound Orchestration Foundations Cohort 1 went through ICP segments built with signals, persona and messaging in mind, TAM, validating segments, stating assumptions, testing messages and running discovery calls, then signals, enrichment, segmentation, workflows, webhooks, Claygents and outreach drafting in Clay. n8n's Foundations Pathway (n8n101, n8n102 and n8n103) and Quickstart covered building and scheduling workflows, data mapping, sub-workflows, API calls, webhooks, error handling and the AI Agent node with tools and memory. This is learning; not all of it is applied in client work yet. I didn't start as a traditional software engineer. I learned and built by starting with a commercial goal, understanding the conditions the business was working within, and finding or building the system that made the goal achievable. That's still how I work. - Current focus - GTM Engineering roles: Outbound Systems & GTM Strategy Certification Outbound Orchestration Foundations, Clay Verified ↗ - Scholarship - One of 10 Clay-sponsored seats in ThynkCrew Crew 01, an 8-week GTM engineering programme from Nov 2026 - Strongest layers - GTM Strategy · System Design · Engineering [Download Resume](https://aslamck.pages.dev/portfolio/assets/Aslam-CK-Resume.pdf) What I build ## Organized by layer, not by tool ### Strategy - ICP Definition - TAM Mapping - Segmentation - Buyer Research - Qualification - Market Entry ### Motion Design - Signals - Outbound - Messaging - Cold Email Copywriting - Sales Actions - GTM Motion Design ### Systems - Outbound Systems - Workflow Design - Automation - Enrichment - Routing - Orchestration - CRM Workflows - Human-in-the-loop Systems ### AI - Agentic Workflows - Claygent - Claude Skills - AI Research - Personalization - AI-Native GTM Tools Use daily - Clay - Claude Code - MCP - Supabase - Firecrawl - Bright Data - AI Ark - Ocean.io - Prospeo - ListKit - Smartlead - HeyReach - InboxKit - Notion - GitHub - Gemini - APIs - Webhooks - Cloudflare - Granola - Buffer Use now and then - Apollo - n8n - ColdIQ - GetLeads - BuiltWith - PredictLeads - Deepline - TheirStack - Sumble - Semrush - Similarweb - HubSpot - Salesforce - OpenAI - Openmart How I work ## The process behind every system above 01 ### Start with the objective What does the business actually need to achieve? 02 ### Understand the operating conditions Resources, team capability, budget, market, timeline and data availability. 03 ### Design the GTM strategy ICP, TAM, buyer, segment, qualification and commercial focus. 04 ### Design the motion Signals, channels, messaging, sales actions and handoffs. 05 ### Engineer the system Data, enrichment, automation, workflows, agents, routing and human checkpoints. 06 ### Execute and iterate Look at the actual output and improve the system from what happens in reality. Get in touch ## Working on a GTM problem? If you're building an outbound motion, dealing with a messy data or targeting problem, or trying to turn a GTM process into a real system, let's talk. - [Book a conversation](https://cal.com/aslam-c-k/1v1) - [LinkedIn](https://www.linkedin.com/in/aslam-c-k/) - [Clay cohort portfolio](https://cohorts.clay.com/@aslam-c-k) ### aslam.c.k GTM Engineer [ckaslam33@gmail.com](mailto:ckaslam33@gmail.com) © Aslam C K Availability Open to remote, worldwide - [LinkedIn](https://www.linkedin.com/in/aslam-c-k/) - [Clay portfolio](https://cohorts.clay.com/@aslam-c-k) - [Book a conversation](https://cal.com/aslam-c-k/1v1) --- # Aslam-CPS | Aslam C K > A reusable personal content production system: ICP, voice and brand rules in; ideas, prompts and visuals out. Proof of work, not a pivot into content marketing. Web page: https://aslamck.pages.dev/portfolio/case-studies/aslam-cps.html Personal GTM Content Production System # Aslam-CPS A reusable content-production architecture built for my own LinkedIn presence, proof of work and professional visibility, engineered the same way I'd approach any GTM system. - Purpose: Personal proof-of-work and visibility infrastructure - Category: Content production system - Role: System design and personal content architecture - [Watch the walkthrough (Loom)](https://www.loom.com/share/355e28c53e0e4ef69f7fa8396bdd41f6) 01 ## Commercial objective Publish proof of GTM engineering work consistently, without the content production itself eating the time that should go into research and systems work. 02 ## Operating conditions - One person, no content team, and limited time to dedicate to production each week. - Needed to stay visually and tonally consistent across many posts over time. - Wanted a system that could eventually be adapted for others, not a one-off personal hack. 03 ## System design The system takes structured inputs (ICP, voice, tone, content themes and brand rules) and produces: - Content ideas aligned to the defined themes - Structured captions and post copy - Image prompts, including logo-applied visuals - Video prompts for motion content It's built as a reusable architecture rather than a single personal script: the same structure (ICP, voice, rules in; ideas and assets out) is designed to be adapted for someone else's positioning, not just mine. 04 ## What this is, and isn't This is a content production layer: ideation through to prompt and asset generation. It is not a full social listening or social selling system, and it doesn't replace judgment on what actually gets published. It exists to demonstrate systems thinking applied to a personal brand problem, not to reposition me as a content marketer. 05 ## Learnings - The same GTM-system thinking (inputs → structured process → outputs) applies to a personal visibility problem, not just client-facing work. - A reusable architecture is worth the extra design time even for a "personal" tool: it's what made the system adaptable rather than throwaway. ## Want to see how the system thinks? Happy to walk through the architecture in a conversation. [Book a conversation](https://cal.com/aslam-c-k/1v1) Back to work ### aslam.c.k GTM Engineer [ckaslam33@gmail.com](mailto:ckaslam33@gmail.com) © Aslam C K Availability Open to remote, worldwide - [LinkedIn](https://www.linkedin.com/in/aslam-c-k/) - [Book a conversation](https://cal.com/aslam-c-k/1v1) --- # GTM Motion Systems | Aslam C K > Freelance GTM strategy and motion design for two companies with broad service portfolios, narrowing to a beachhead offer, then designing the ICP, signals and motion around it. Web page: https://aslamck.pages.dev/portfolio/case-studies/gtm-motion-systems.html GTM Strategy & Motion Design # GTM Motion Systems Freelance GTM work for two companies with broad service portfolios and limited resources. The problem wasn't finding leads; it was that trying to target every service at once would have meant too many ICPs, personas and messages for either team to execute well. - Companies: Two freelance clients (names kept private) - Arrangement: Freelance GTM strategy in exchange for feedback and practical exposure - Role: GTM strategy, segmentation and motion design 01 ## Commercial objective Turn a broad service portfolio into a GTM motion that a small, resource-constrained team could actually run, not a strategy deck that assumed headcount neither company had. 02 ## Operating conditions - Both companies offered 12+ services: targeting all of them would have meant more ICPs, personas, signals and messaging tracks than either team could execute. - Resources were limited on both sides: no dedicated execution team, limited tooling, limited call and outreach volume. - Any motion had to be narrow enough to run consistently with the team and budget actually available. 03 ## GTM strategy: narrowing to a beachhead The approach was the same for both companies: - Start with the business objective and examine the full service portfolio. - Weigh it against the resources actually available. - Narrow to one practical beachhead service rather than trying to cover the whole portfolio. - Build the ICP, buyer persona, and firmographic/technographic profile around that one service. - Define the signals that indicate relevance, then the messaging direction. 04 ## Motion design Client A (language and speaking assessment): the motion focused on a language and speaking assessment offering. Job-posting activity and context were used to identify companies with a live, relevant hiring need, which made the outreach timing and message specific rather than generic. Client B (ERP services): the motion focused on ERP. Signals included ERP-related hiring, ERP Manager-type roles opening up, and more than 10% headcount growth in the prior six months, combined with topic-level intent, stacking multiple signals rather than relying on one weak indicator. 05 ## System design Once the motion was defined, I built the supporting prospecting, qualification and enrichment workflow around it, sized to what each team could actually run, not a system designed for a larger organization. 06 ## Execution reality Both engagements ran at low execution volume: limited call activity, limited LinkedIn activity and limited email execution, mostly due to client-side resource constraints rather than the strategy itself. That means these should be read as proof of strategic thinking, segmentation and motion design under real constraints, not as case studies in high-volume pipeline generation, which they weren't positioned or resourced to produce. 07 ## Learnings - Narrowing to a beachhead offer is often the highest-leverage GTM decision available to a resource-constrained team, before any tooling or automation. - Signal quality compounds: stacking two or three specific, relevant signals (as with Client B) produces a sharper target list than one broad indicator. - A well-designed motion still needs execution capacity to prove itself: strategy and system design can only carry a GTM motion so far without volume behind it. ## Have a broad portfolio and a small team? If you need to turn a wide service list into one motion your team can actually run, let's talk. [Book a conversation](https://cal.com/aslam-c-k/1v1) Back to work ### aslam.c.k GTM Engineer [ckaslam33@gmail.com](mailto:ckaslam33@gmail.com) © Aslam C K Availability Open to remote, worldwide - [LinkedIn](https://www.linkedin.com/in/aslam-c-k/) - [Book a conversation](https://cal.com/aslam-c-k/1v1) --- # Minzelis Trust Infrastructure | Aslam C K > An AI-assisted, brand-ruled content production system built as a trust layer for outbound, keeping a food brand's public presence credible and consistent. Web page: https://aslamck.pages.dev/portfolio/case-studies/minzelis-trust-infrastructure.html Brand Trust & Content Systems # Minzelis Trust Infrastructure Outbound creates the first interaction, but a prospect who checks a company's online presence and finds little evidence of credibility won't reply. This system treats brand trust as part of the GTM motion, not a separate marketing function. - Business: Minzelis, food brand - Category: AI-assisted content production infrastructure - Role: System design for a repeatable brand-trust layer 01 ## Commercial objective Make the brand's public presence credible enough that an outbound message lands in an environment that looks real, consistent and professionally maintained, so the outreach itself doesn't get discounted the moment a prospect looks the company up. 02 ## Operating conditions - No dedicated content or design team: production needed to be repeatable by one person. - Brand consistency had to hold across many pieces of content without a slow, manual review cycle each time. - A food brand's visual identity can't rely on product shots alone: it needs recognizable, reusable elements. 03 ## GTM decision Treat credibility as infrastructure: a system that could reliably produce brand-aligned content, rather than a one-off campaign. That meant defining explicit brand rules up front (warm lighting, controlled motion, fixed logo placement, no on-screen text, standardized export specs), so every output stayed consistent regardless of who or what generated it. 04 ## System design The production system took product information, visual worlds and motion styles as structured inputs, and generated: - Image prompts and video prompts, enhanced through Gemini - Social copy aligned to the brand voice - Reusable visual concepts rather than one-off ideas A second layer added market intelligence, campaign archetypes and a brand mascot, giving the content system a strategic frame (audience insight and campaign theme) on top of the production layer. 05 ## What this is, and isn't This is a content production and brand-consistency system: ideation → image base → animation/motion → editing → export, repeatable without a design team. It is not a social listening or social selling system: those downstream stages (distribution automation, engagement, social-led discovery) were not built as part of this system. 06 ## Learnings - Trust is a GTM constraint like any other: it's worth designing a system for it rather than treating it as a marketing side-project. - Explicit brand rules, defined before generation, do more for consistency than reviewing output after the fact. - A content system is most useful as infrastructure that supports a GTM motion, not as an end in itself. ## Outbound landing on a thin public presence? If credibility is the gap between your outbound and your reply rate, let's talk. [Book a conversation](https://cal.com/aslam-c-k/1v1) Back to work ### aslam.c.k GTM Engineer [ckaslam33@gmail.com](mailto:ckaslam33@gmail.com) © Aslam C K Availability Open to remote, worldwide - [LinkedIn](https://www.linkedin.com/in/aslam-c-k/) - [Book a conversation](https://cal.com/aslam-c-k/1v1) --- # Partner Intelligence Engine | Aslam C K > An 8-agent GTM intelligence and outbound system built to find branded packaged-food importers across 32 countries, a market conventional B2B databases couldn't see. Web page: https://aslamck.pages.dev/portfolio/case-studies/partner-intelligence-engine.html AI-Native GTM Intelligence & Outbound System # Partner Intelligence Engine An 8-agent research and qualification architecture built to find branded packaged-food importers and distributors across 32 countries, a fragmented, low-digital-presence market that conventional B2B databases couldn't cover. - Business: Food export, branded packaged goods - Markets: 32 countries, including the UK, Australia and the United States - Timeline: Sourcing-to-qualification progression within ~2 weeks of go-live - Role: GTM strategy, motion design and system architecture 01 ## Commercial objective Find and reach relevant importer-distributors of branded packaged food across a wide set of international markets: companies with a real, evidenced import capability for the product category, not just companies that mentioned relevant keywords online. 02 ## Operating conditions - The target market was fragmented and had low digital presence across most of the 32 countries. - Total addressable market was relatively small, but each correct account carried high commercial value. - Company information was inconsistent: categorization, language and registry formats differed by country. - Conventional B2B databases returned a lot of noise: restaurants, chefs, food-service businesses, bulk commodity importers and suppliers that were not the actual target. - Resources were limited: this had to run without a large team or an enterprise data budget. - The output needed to be usable prospects with verified import capability, not raw, unqualified leads. 03 ## The GTM decision Apollo and Clay's standard data layers did not provide sufficient coverage for this ICP: the fragmentation of the market meant no single vendor owned complete data on it. Rather than force the problem into a standard database-first workflow and accept a high false-positive rate, I designed an alternative data and research architecture built around the market itself. That meant treating company discovery and qualification as a research problem, not a lookup problem, combining directories, registries, trade and customs data, and reverse-engineering competitor distributor networks (a company already distributing a comparable product category is a far stronger signal than a keyword match). 04 ## Motion design The motion ran from signal to personalized outreach, with an explicit qualification gate before any contact was researched, and a human checkpoint before anything was sent. The system's job was to prepare research and personalization, not to replace judgment on relationship-sensitive actions. 05 ## System design Discovery and research required probabilistic reasoning (interpreting sources, classifying companies, verifying claims) that a deterministic workflow alone couldn't handle well. That's what moved the system toward an agentic architecture: eight agents with defined boundaries, inputs, outputs and handoff logic, coordinating through a shared data layer built on Supabase. The CEO used the system through its web interface: the code lives in a GitHub repo, the data in Supabase, and the interface is published by Cloudflare Pages, connected to both. 06 ## Architecture 1 #### Intent Signal Agent Detects relevant market and company-level signals (activity, category movement, commercial relevance) using a defined signal taxonomy and weighting. 2 #### Lead Discovery Agent Finds candidate companies via directories, registries, trade sources, competitor-network research and targeted web research, the sources standard databases missed. 3 #### Lead Qualification Agent Verifies existence, import capability and commercial role using evidence rather than marketing language. 4 #### Company Researcher Agent Builds a deeper profile: market role, brands, categories, geography, positioning and a reason for outreach. 5 #### Contact Scouting Agent Identifies relevant decision-makers, adapting to company size, structure, country and title conventions. 6 #### Contact Researcher Agent Researches the individual's role, authority and professional context. 7 #### Personalized Digital Prospectus Agent Builds a company-specific commercial asset ahead of outreach, giving the prospect a tangible reason to engage. 8 #### Outreach Draft Agent Prepares email and LinkedIn touchpoints built around the commercial tension behind the signal, held for human review before sending. Human-in-the-loop by design. Automation covers repetitive research; the agents handle reasoning-heavy discovery and qualification; a person stays in control of anything relationship-sensitive, including every send. 07 ## Execution & qualification Qualification was intentional attrition, not failure: each stage filtered for evidenced import capability rather than keyword relevance. Sourced 322 Scored 230 Verified 155 Advanced 41 On the contact layer, 159 decision-makers were researched, and 66 verified emails were found through a Clay → Apollo enrichment waterfall. Where a contact-level reveal failed, the system fell back to company-level targeting rather than guessing at a contact. Separately, reverse-engineering known competitors' distributor networks surfaced 81 additional companies, each one already demonstrating category import activity, which made it a stronger signal than a keyword match from a database search. 08 ## Evidence - 32 Countries mapped - 8 Specialized agents - 322 Companies sourced - 159 Decision-makers researched - 81 Competitor-network discoveries - 66 Verified emails - 41 Advanced to outreach - 29 Personalized prospectuses generated 09 ## Learnings - No single data vendor owns complete coverage for a fragmented, low-digital-presence ICP: the system has to build its own coverage. - Competitor distributor-network research is a stronger discovery signal than keyword search for categories with established comparable players. - Import capability needs to be verified through evidence, not inferred from marketing language. - Agentic research earns its complexity when the task is reasoning-heavy (interpretation, classification, verification), not as a default for every workflow. - Keeping a human checkpoint before every send preserved relationship quality without slowing down research and qualification. ## Working on a similar data or targeting problem? If a fragmented market or messy ICP is blocking your outbound motion, let's talk it through. [Book a conversation](https://cal.com/aslam-c-k/1v1) Back to work ### aslam.c.k GTM Engineer [ckaslam33@gmail.com](mailto:ckaslam33@gmail.com) © Aslam C K Availability Open to remote, worldwide - [LinkedIn](https://www.linkedin.com/in/aslam-c-k/) - [Book a conversation](https://cal.com/aslam-c-k/1v1) --- # TAM & Enrichment Architecture | Aslam C K > A multi-source TAM and enrichment architecture built for a 90K-phone-number target across a fragmented U.S. beauty and wellness market. Web page: https://aslamck.pages.dev/portfolio/case-studies/tam-enrichment-architecture.html TAM Architecture & Enrichment # TAM & Enrichment Architecture A GTM engineering assessment: map and architect a data pipeline for a 90,000-phone-number target across a fragmented U.S. beauty and wellness market, comparing three data providers on coverage, cost and quality. - Context: SalesCaptain, hiring test assessment for a GTM agency, done right after Clay's Outbound Orchestration Foundations Cohort 1 - Target market: U.S. single-location beauty & wellness, 2–50 employees (ideally 5–50) - Sources compared: Openmart, Apollo, Clay - Role: TAM architecture and enrichment-economics design - [Read the full assessment](https://docs.google.com/document/d/1SBidOTUOYk6AcNLzs4Dlzjq9zrwUpvvVG-djPxt39Ik/edit?usp=sharing) - [Watch the walkthrough (Loom)](https://www.loom.com/share/cf2b356dd38744cb933a7978ab225469) 01 ## Commercial objective Map the addressable market of U.S. beauty and wellness businesses (hair salons, nails, spa, massage, makeup, lash, brow, skin/facial, waxing, barber and tanning) and architect a data pipeline capable of reaching a target of 90,000 phone numbers. 02 ## Operating conditions - Target businesses were constrained to a single retail location, 2–50 employees (ideally 5–50), across two technology segments (specific and general). - No single data provider covered the market cleanly: each had different strengths, blind spots and cost structures. - Phone number availability varies significantly by provider and can't be assumed uniform. - Enrichment at this scale carries real cost: credit spend needed to be modeled, not ignored. 03 ## GTM strategy Rather than pick one provider and accept its coverage gaps, I treated this as a source-comparison problem: run the same segment definition through Openmart, Apollo and Clay, measure what each returned after strict exclusions, and use the comparison to decide where each source should sit in the pipeline. 04 ## Motion & system design Apollo was used first because it already filters by technology, so the technology segment didn't need to be enriched again. Openmart filled gaps where Apollo's coverage was thin. Clay sat on top as the orchestration layer (audiences, segments and deduplication), so the same company was never enriched twice across sources. The order mattered as much as the source selection: cheap and reliable first, secondary routes only where needed. 05 ## Findings After strict exclusions, the three sources returned meaningfully different TAM sizes: - 43,848 Apollo TAM (strict exclusions) - 21,872 Clay TAM (strict exclusions) - 150K+ Openmart pre-dedup output - 108K Companies modeled for enrichment Openmart's broad, niche-by-niche searches exceeded 150,000 companies before deduplication, useful for reach, but it needed heavy overlap cleanup before it was usable. The estimated model settled on roughly 108,000 companies requiring enrichment to responsibly approach the 90K phone-number target, after accounting for expected phone availability and deduplication across sources. The assessment also modeled provider economics directly: roughly 452,000 Apollo credits and 32,500 Clay credits, plus per-company enrichment costs depending on the source used, not just a company count, but a cost-aware plan for reaching it. 06 ## Outcome This was an architecture and assessment exercise: it demonstrates how I evaluate data providers and design a practical, cost-aware enrichment pipeline, not a claim that 90,000 phone numbers were delivered. 07 ## Learnings - TAM size depends heavily on which provider is asked and how exclusions are defined: a single-source number is rarely the real market. - Sequencing providers by cost and coverage, with an orchestration layer for deduplication, beats picking one "best" source. - Enrichment economics (credits, per-record cost, expected yield) belong in the architecture decision, not as an afterthought. ## Evaluating data providers for a new market? If you're weighing coverage against cost across multiple sources, I can help architect the comparison. [Book a conversation](https://cal.com/aslam-c-k/1v1) Back to work ### aslam.c.k GTM Engineer [ckaslam33@gmail.com](mailto:ckaslam33@gmail.com) © Aslam C K Availability Open to remote, worldwide - [LinkedIn](https://www.linkedin.com/in/aslam-c-k/) - [Book a conversation](https://cal.com/aslam-c-k/1v1)