Contact Research

1---2name: contact-research3description: "Research a specific person using Common Room data. Triggers on 'who is [name]', 'look up [email]', 'research [contact]', 'is [name] a warm lead', or any contact-level question."4---5 6# Contact Research7 8Retrieve a comprehensive contact profile from Common Room. Supports lookup by email, social handle, or name + company. Returns enriched data including activity history, Spark, scores, website visits, and CRM fields.9 10## Step 1: Locate the Contact11 12Common Room supports multiple lookup methods — use whichever the user has provided:13 14| What the user gives | Lookup method |15|---------------------|--------------|16| Email address | Look up by email (most reliable) |17| LinkedIn, Twitter/X, or GitHub handle | Look up by social handle — specify handle type explicitly |18| Name + company | Identity resolution by name + org domain; present matches if ambiguous |19| Name only | Search by name; if multiple matches, show a brief list and ask the user to confirm |20 21If no match is found, respond: "Common Room doesn't have a record for this person." Do not speculate or fabricate profile data.22 23## Step 2: Fetch Contact Fields24 25Use the Common Room object catalog to see available field groups and their contents. For full profiles, request all groups. For targeted questions, request only what's relevant.26 27**Key field groups to know about:**28- **Scores** — always return as raw values or percentiles, never labels29- **Recent activity** — use `Contact Initiated` filter (last 60 days) for their actions, not your team's30- **Website visits** — total count + specific pages (last 12 weeks)31- **Spark** — retrieve all Sparks when tracking engagement evolution over time32 33## Step 3: Run Spark Enrichment (If Available)34 35If Spark is available, use it. Spark provides:36- Professional background and job history37- Social presence and influence signals38- Persona classification: Champion, Economic Buyer, Technical Evaluator, End User, or Gatekeeper39- Inferred role in the buying process40 41If Spark is unavailable but real activity data exists (recent actions, website visits, community engagement), infer a persona from those signals. If neither Spark nor activity data is available, classify as Unknown — do not guess a persona from title alone.42 43Retrieve **all Sparks** (not just the most recent) when the user wants to understand how this contact's engagement has evolved over time.44 45## Step 4: Assess Account Context46 47Pull an abbreviated account snapshot for this contact's parent company. Note:48- Open opportunities, expansion signals, or churn risk at the account level49- Whether other contacts at this company are also active50- How this person's engagement compares to their colleagues51 52## Step 5: Identify Conversation Angles53 54Based on activity and signals, surface the strongest 2–3 hooks:55- A recent `Contact Initiated` activity (community post, product event, support ticket)56- A specific web page they visited recently — especially if it signals evaluation intent57- A job change, promotion, or company news58- Their Spark persona and what that suggests about communication style59- Their role in a known active deal60 61## Output Format62 63Only include sections where data was actually returned. Omit sections with no data rather than filling them with guesses.64 65**When data is rich:**66 67```68## [Contact Name] — Profile69 70**Overview**71[2 sentences: who they are, their role, and relationship status]72 73**Details**74- Title: [title]75- Company: [company]76- Email: [email]77- LinkedIn: [URL]78- Other profiles: [Twitter/X, GitHub, CRM link if available]79 80**Scores** [If scores returned]81[All scores as raw values or percentiles]82 83**Recent Activity** (last 60 days) [If activity returned]84[3–5 bullets with dates]85 86**Website Visits** (last 12 weeks) [If visit data exists]87[Total visit count + list of pages visited]88 89**Spark Profile** [If Spark data is non-null]90[Persona type, background summary, influence signals]91 92**Segments** [If segments returned]93[List of segment names this contact belongs to]94 95**Account Context**96[1–2 sentences on their company's status]97 98**Conversation Starters**99[2–3 specific, signal-backed openers]100```101 102**When data is sparse (e.g., only name, title, email, tags returned; sparkSummary is null):**103 104```105## [Contact Name] — Profile (Limited Data)106 107**Data available:** [List exactly what Common Room returned]108 109[Present only the returned fields]110 111**Web Search**112[Any findings from searching their name + company]113 114**Note:** Common Room has limited data on this contact. No activity history, scores, or Spark profile available. I can run deeper web searches or look up their company for additional context.115```116 117Do not generate conversation starters, persona inferences, or engagement assessments from sparse data. These require real signals.118 119## Quality Standards120 121- Lookup must use the correct method for the input type — don't guess on email vs. handle122- Scores as raw/percentile only — never labels123- `Contact Initiated` activity (last 60 days) is the primary engagement signal — lead with it124- If Spark is unavailable, say so — don't fabricate a persona from title alone125- Flag any contact where the most recent activity is older than 30 days126 127## Reference Files128 129- **`references/contact-signals-guide.md`** — full field descriptions, Spark persona guide, and conversation starter principles