Infer a prospect's tech stack and what it says about their pain
Turns raw tech-stack evidence — BuiltWith exports, tool mentions in job posts, integration pages — into a confidence-labeled read of what a prospect runs, what they almost certainly also run, and what it reveals about budget, maturity, and gaps your product fills. It converts a list of logos into a fit assessment and a credible talk track.
You are a technical GTM analyst who reads tech stacks the way a mechanic listens to an engine. A stack isn't a list of logos — it's a record of decisions, budgets, and problems a company has already admitted to having. I'll paste raw stack evidence: BuiltWith or Wappalyzer output, job postings that name tools, integration pages, case studies, or anything else I've collected. You produce: 1. CONFIRMED STACK — tools with direct evidence, grouped by function (CRM, marketing, data, infra, support, etc.), with the evidence noted per tool. 2. INFERRED STACK — what they almost certainly also run, based on what confirmed tools require or pair with. Label confidence high/medium/low per inference. 3. WHAT IT SAYS — 3 to 5 conclusions about maturity, budget, and philosophy: build-vs-buy leaning, enterprise or SMB tooling taste, where they've clearly invested and where they're running on duct tape. 4. THE GAP — where my product fits: what's missing, what's outgrown, or what my product replaces or complements. If the stack suggests we're a bad fit, say so plainly. 5. TALK TRACK — 2 sentences a rep could use that reference their stack credibly without sounding like we scraped them. Rules: never present an inference as confirmed. No 'they use technology to drive their business' filler. If the evidence is too thin for section 3, say what evidence would change that. Before you analyze, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time: 1. What does your product do, and what tools does it replace, complement, or integrate with? 2. Paste the stack evidence you've got — BuiltWith output, job posts, integration pages, anything. 3. What stacks do your best customers usually run? Any tools that predict a great fit or a dead end? 4. Who's the buyer this research feeds into (technical or business)? Once you have my answers, run the analysis.
How to use it
- 1
Copy the prompt into Claude, ChatGPT, or any LLM.
- 2
Gather evidence first: run the domain through BuiltWith or Wappalyzer, and grab 2-3 current job postings from their careers page — engineers and ops roles name tools constantly.
- 3
Answer question 3 with your real customer patterns; it's what turns stack reading into fit scoring.
- 4
Sanity-check the INFERRED section against anything you learn in discovery, and correct the model in-chat.
- 5
Use THE GAP to decide whether the account enters your sequence at all — a confirmed bad-fit stack is a free disqualification.
Best practices
Job postings are the highest-signal free source — a posting that says 'experience with Salesforce and Outreach required' is confirmation no scraper gives you.
Run this at scale by wiring the same logic into a Clay table with a BuiltWith enrichment column feeding an AI column — this prompt is the single-account version.
Watch for stack age signals: a company still on tools its segment has moved past is either frugal or stuck, and both are angles.
If everything comes back low-confidence, browse or paste their integrations page — companies advertise their stack there voluntarily.
Example: what this looks like in practice
An SDR at a data-pipeline startup pastes BuiltWith output and three job postings for a 200-person e-commerce company. Confirmed: Shopify Plus, Klaviyo, Segment, and a posting requiring 'dbt and Snowflake experience.' The model infers a Fivetran-or-similar ingestion layer at medium confidence, reads the stack as 'modern data team, mid-build-out, buys best-of-breed,' and flags the gap: nothing handles reverse ETL, which is exactly what the startup sells. The talk track references their dbt-and-Snowflake posting as evidence they're activating data downstream. The reply: 'How did you know we were evaluating this exact thing?'
Best fit
This prompt is one gear in a bigger machine. We orchestrate 20+ tools into outbound systems our clients own — and guarantee the results.
Apply for a Pilot Spot → →Frequently asked questions
Combine three free sources: a scanner like BuiltWith or Wappalyzer for website-detectable tools, their job postings for the tools teams actually name, and their integrations or partners page for what they advertise. Each covers a different layer of the stack. This prompt merges whatever you collect into one confidence-labeled picture.
More account & prospect research prompts
Build a 10-minute company deep-dive brief before you touch an account
Produces a one-page, source-backed account brief with a fixed six-section structure: snapshot, revenue logic, recent momentum, evidence-based pressures, two outreach angles, and landmines to avoid. It compresses the hour of tab-hopping most reps do before a tier-one account into ten minutes, and forces every claim to carry a source.
Scan an account for trigger events: news, funding, leadership moves, layoffs
Runs a structured six-month trigger-event sweep on one account — funding, leadership changes, layoffs, launches, expansion, legal news — and returns a dated, sourced signal log, the top three events ranked by outreach value, a ready-to-adapt angle for the best one, and an honest timing call including 'no trigger exists.' It turns 'why now' from a guess into evidence.
Audit a prospect list for quality before a single email goes out
Audits a prospect list before launch: completeness and duplicates, out-of-ICP rows, stale-data risks, deliverability hazards like role-based emails and sequence collisions, and an honest A-F grade with a prioritized fix list. It catches the problems that get misdiagnosed as 'copy issues' three weeks and one burned domain later.