inbound-lead-qualification

# Inbound Lead Qualification Takes a set of inbound leads and validates each against your full ICP criteria. Not a fast-pass triage (that's `inbound-lead-triage`) — this is the thorough qualification step that determines whether a lead is genuinely worth pursuing, and produces a scored CSV for the team. ## When to Auto-Load Load this composite when: - User says "qualify these inbound leads", "check if these leads are ICP", "score my inbound" - An upstream triage has been completed and leads need deeper qualification - User has a batch of leads and wants a qualified/disqualified verdict on each ## Architecture ``` [Inbound Leads] → Step 1: Load ICP & Config → Step 2: CRM/Pipeline Check → Step 3: Company Qualification → Step 4: Person Qualification → Step 5: Use Case Fit → Step 6: Score & Verdict → Step 7: Output CSV ``` --- ## Step 0: Configuration (Once Per Client) On first run, establish the ICP definition and CRM access. Save to the current working directory or wherever the user prefers (e.g., `config/lead-qualification.json`). ```json { "icp_definition": { "company_size": { "min_employees": null, "max_employees": null, "sweet_spot": "", "notes": "" }, "industry": { "target_industries": [], "excluded_industries": [], "notes": "" }, "use_case": { "primary_use_cases": [], "secondary_use_cases": [], "anti_use_cases": [], "notes": "" }, "company_stage": { "target_stages": [], "excluded_stages": [], "notes": "" }, "geography": { "target_regions": [], "excluded_regions": [], "notes": "" } }, "buyer_personas": [ { "name": "", "titles": [], "seniority_levels": [], "departments": [], "is_economic_buyer": false, "is_champion": false, "is_user": false } ], "hard_disqualifiers": [], "hard_qualifiers": [], "crm_access": { "tool": "HubSpot | Salesforce | CSV export | none", "access_method": "", "tables_or_objects": [] }, "existing_customer_source": { "tool": "HubSpot | Salesforce | CSV | none", "access_method": "" }, "qualification_prompt_path": "path/to/lead-qualification/prompt.md or null" } ``` **If `lead-qualification` capability already has a saved qualification prompt:** Reference it directly — don't rebuild ICP criteria from scratch. **On subsequent runs:** Load config silently. --- ## Step 1: Load ICP Criteria & Parse Leads ### Process 1. Load the client's ICP config (or qualification prompt from `lead-qualification` capability) 2. Parse the inbound lead list — accept any format: - Output from `inbound-lead-triage` (already normalized) - Raw CSV with any column structure - Pasted list of names/emails/companies - CRM export 3. Identify what data is available vs. missing per lead: - **Have:** Fields present in the input - **Need:** Fields required for qualification but missing - **Gap report:** "X leads have company name, Y have title, Z have nothing but email" ### Output - Parsed lead list with available/missing field inventory - Gap report for the user ### Human Checkpoint If >50% of leads are missing critical fields (company name or person title), recommend running `inbound-lead-enrichment` first. Ask: "Many leads are missing company/title data. Want me to enrich them first, or qualify with what's available?" --- ## Step 2: CRM & Pipeline Check ### Process For each lead, check against existing data sources to identify overlaps: **Check 1 — Existing customer?** - Search customer database by company domain/name - If match found: Flag as `existing_customer` with customer details (plan, account owner, contract status) - This is NOT a disqualification — it's a routing flag (upsell vs. new business) **Check 2 — Already in pipeline?** - Search your CRM (HubSpot, Salesforce, CSV) for the company in active deals - If match found: Flag as `in_pipeline` with deal details (stage, owner, last activity) - Critical: Sales rep should know before reaching out that a colleague already has this account **Check 3 — Previous engagement?** - Search outreach logs for the email/company - If match found: Flag as `previously_contacted` with history summary (when, what channel, outcome) **Check 4 — Known from signal composites?** - Search your CRM or signal tracking system for the company - If match found: Flag as `signal_flagged` with signal type and date ### Output Each lead tagged with: - `pipeline_status`: `new` | `existing_customer` | `in_pipeline` | `previously_contacted` - `pipeline_detail`: One sentence explaining the overlap (or null) - `signal_flags`: Any signal composite matches ### Handling Overlaps - **Existing customer:** Don't disqualify. Mark separately. Might be expansion/upsell. - **In pipeline:** Don't disqualify. Flag for sales rep coordination. Note the existing deal owner. - **Previously contacted but no response:** Still qualify. The inbound signal means they're now warmer. - **Previously contacted and rejected:** Still qualify the inbound. People change their minds. Note the prior context. --- ## Step 3: Company Qualification ### Process For each lead's company, evaluate against every ICP company dimension: **Dimension 1 — Company Size** - Check employee count against ICP range - Sources: enrichment data, LinkedIn company page, web search - Score: `match` | `borderline` | `mismatch` | `unknown` - Note: If the lead is from a subsidiary or division, evaluate the relevant unit, not the parent company **Dimension 2 — Industry** - Check against target and excluded industry lists - Be smart about classification: "AI-powered HR platform" matches both "AI/ML" and "HR Tech" - Score: `match` | `adjacent` (related but not core target) | `mismatch` | `unknown` **Dimension 3 — Company Stage** - Seed, Series A, Series B+, Growth, Public, Bootstrapped - Sources: SixtyFour or Orthogonal, news, enrichment data - Score: `match` | `borderline` | `mismatch` | `unknown` **Dimension 4 — Geography** - Check HQ location and/or the specific person's location - For remote-first companies, check where the majority of the team is - Score: `match` | `borderline` | `mismatch` | `unknown` **Dimension 5 — Use Case Fit** - Based on what the company does, could they plausibly use the product? - This is the most nuanced dimension — requires understanding both the product and the company's operations - Sources: company website, product description, job postings (hint at internal tools/processes) - Score: `strong_fit` | `moderate_fit` | `weak_fit` | `no_fit` | `unknown` ### Output Each lead gets a `company_qualification` block: ``` { "company_size": { "score": "", "value": "", "reasoning": "" }, "industry": { "score": "", "value": "", "reasoning": "" }, "stage": { "score": "", "value": "", "reasoning": "" }, "geography": { "score": "", "value": "", "reasoning": "" }, "use_case": { "score": "", "value": "", "reasoning": "" }, "company_verdict": "qualified | borderline | disqualified | insufficient_data" } ``` --- ## Step 4: Person Qualification ### Process For each lead's contact person, evaluate against buyer persona criteria: **Dimension 1 — Title/Role Match** - Check title against buyer persona title lists - Handle variations: "VP of Marketing" = "Vice President, Marketing" = "VP Marketing" - Be smart about title inflation at small companies (a "Director" at a 10-person startup ≠ "Director" at a 10,000-person enterprise) - Score: `exact_match` | `close_match` | `adjacent` | `mismatch` | `unknown` **Dimension 2 — Seniority Level** - Map to: Individual Contributor, Manager, Director, VP, C-Level, Founder - Check against ICP seniority requirements - Score: `match` | `too_junior` | `too_senior` | `unknown` **Dimension 3 — Department** - Engineering, Product, Marketing, Sales, Operations, Finance, HR, etc. - Check against ICP department targets - Score: `match` | `adjacent` | `mismatch` | `unknown` **Dimension 4 — Authority Type** - Based on title + seniority, classify: - `economic_buyer` — Can sign the check - `champion` — Wants it, can influence the decision - `user` — Would use it daily, can validate need - `evaluator` — Tasked with research, limited decision power - `gatekeeper` — Can block but not approve - `unknown` **Dimension 5 — Right Person, Wrong Company (or Vice Versa)** - If company qualifies but person doesn't: Flag as `right_company_wrong_person` — this is a referral opportunity - If person qualifies but company doesn't: Flag as `right_person_wrong_company` — rare for inbound, but possible with job changers ### Output Each lead gets a `person_qualification` block: ``` { "title_match": { "score": "", "value": "", "reasoning": "" }, "seniority": { "score": "", "value": "", "reasoning": "" }, "department": { "score": "", "value": "", "reasoning": "" }, "authority_type": "", "person_verdict": "qualified | borderline | disqualified | insufficient_data", "mismatch_type": "null | right_company_wrong_person | right_person_wrong_company" } ``` --- ## Step 5: Use Case Fit Assessment ### Process This step connects the company's likely needs to your product's actual capabilities. It goes deeper than Step 3's company-level use case check. 1. **Infer the lead's intent** from their inbound action: - Demo request message → What did they say they need? - Content downloaded → What topic were they researching? - Webinar attended → What problem were they trying to solve? - Free trial signup → What feature did they try first? - Chatbot conversation → What questions did they ask? 2. **Map intent to product capabilities:** - Does the product actually solve what they seem to need? - Is this a primary use case or a stretch? - Are there known limitations that would disappoint them? 3. **Assess implementation feasibility:** - Based on company size and stage, can they realistically implement? - Do they likely have the technical resources / team to adopt? - Any known blockers for companies like this? (e.g., "banks need SOC2 and we don't have it yet") ### Output ``` { "inferred_intent": "", "intent_source": "", "product_fit": "strong | moderate | weak | unknown", "product_fit_reasoning": "", "implementation_feasibility": "easy | moderate | complex | unlikely", "known_blockers": [] } ``` --- ## Step 6: Score & Verdict ### Scoring Logic Combine all dimensions into a final qualification verdict. **Composite Score Calculation:** | Dimension | Weight | Possible Values | |-----------|--------|-----------------| | Company Size | 15% | match=100, borderline=50, mismatch=0, unknown=30 | | Industry | 20% | match=100, adjacent=60, mismatch=0, unknown=30 | | Company Stage | 10% | match=100, borderline=50, mismatch=0, unknown=30 | | Geography | 10% | match=100, borderline=50, mismatch=0, unknown=30 | | Use Case Fit | 25% | strong=100, moderate=60, weak=20, no_fit=0, unknown=30 | | Person Title/Role | 15% | exact=100, close=75, adjacent=40, mismatch=0, unknown=30 | | Person Seniority | 5% | match=100, too_junior=20, too_senior=60, unknown=30 | **Hard overrides (bypass the score):** - Any hard disqualifier present → `disqualified` regardless of score - Any hard qualifier present → `qualified` regardless of score (but still show the full breakdown) - Existing customer → Route separately, don't score as new lead **Verdict thresholds:** - **Score ≥ 75:** `qualified` — Pursue actively - **Score 50-74:** `borderline` — Qualified with caveats, may need manual review - **Score 30-49:** `near_miss` — Not qualified now, but close enough to consider (referral or nurture) - **Score < 30:** `disqualified` — Does not fit ICP **Sub-verdicts for routing:** - `qualified_hot` — Score ≥ 75 AND Tier 1/2 urgency from triage - `qualified_warm` — Score ≥ 75 AND Tier 3/4 urgency - `borderline_review` — Score 50-74, needs human judgment call - `near_miss_referral` — Score 30-49 AND right_company_wrong_person (referral opportunity) - `near_miss_nurture` — Score 30-49, might fit in the future - `disqualified_polite` — Score < 30, needs polite decline - `disqualified_competitor` — Competitor employee - `existing_customer_upsell` — Existing customer with expansion signal ### Output Each lead gets: ``` { "composite_score": 0-100, "verdict": "", "sub_verdict": "", "top_qualification_reasons": [], "top_disqualification_reasons": [], "summary": "One sentence: why this lead is/isn't a fit" } ``` --- ## Step 7: Output CSV ### CSV Structure Produce a CSV with ALL input fields preserved plus qualification columns appended: **Core qualification columns:**