Find + Qualify People

Using Octave in Claude

Workflow

Find +
Qualify People

Surface

Claude Chat (MCP)

Cowork

Claude Code

Difficulty

Easy

Medium

Hard

Audience

Sales Reps, SDRs, and AEs doing outbound

What it does

Build a skill that finds contacts via Octave MCP, layers in internal data via MCP, and qualifies each person against your personas

Scenario

You've done your account research. You know the company is a fit. Now you need to figure out who to actually talk to -who's in the buying committee, which personas they match, and whether they're worth reaching out to. Today that means bouncing between LinkedIn, your CRM, and your call recorder to piece together a stakeholder map by hand.

How It Works

You create a skill that orchestrates the discovery. The skill calls the Octave MCP to find and enrich contacts at the account, then hooks into your CRM MCP for existing relationships, your call recording MCP for past conversations, and your product data MCP for usage signals. Each person gets qualified against your Octave personas so you know exactly who matters and why.

Target Account

From account research

Find People

Octave MCP by role and title

Internal Data

CRM, product data, calls - via MCP

Qualified Map

Persona-scored, prioritized

The Old Way

❌ LinkedIn Guessing

Manually searching LinkedIn for titles that might be relevant, with no framework for who actually matters to this deal

❌ No Persona Match

You find names but don't know which persona they map to, what they care about, or what messaging angle to use

❌ Blind Spots

No idea if your team already has a relationship, had a call last week, or has product usage data tied to them

❌ Flat Lists

You end up with a spreadsheet of names -no prioritization, no qualification, no context on who to reach out to first

⏱️ 20–30 minutes per account

The New Way

✓ Targeted Discovery

Your skill calls Octave MCP to find contacts by role and maps them to your personas. You search with intent, not guesswork

✓ Persona-Qualified

Every person gets scored against your Octave personas so you know what they care about and how to approach them

✓ Full Context

Your skill pulls CRM history, call recordings, and product usage via MCP. You see who your team already knows and what's happened

✓ Prioritized Map

A ranked stakeholder map showing who to reach out to first, which persona they match, and why they matter

⏱️ 3–5 minutes per account

What You Get

✓ Stakeholder Map

Contacts at the account mapped to roles, personas, and their position in the buying committee -not just a list of names

✓ Qualification Scores

Each person scored against your Octave personas with rationale -you know who's a strong fit and who's a long shot

✓ Internal Context

CRM relationships, recent calls, and product usage tied to each person so you never reach out cold when you don't have to

✓ Ready for Outreach

You know who to message, what persona they match, and what angle to take -chain directly into messaging generation

Step by Step

1

Connect your MCPs

Your skill needs access to the Octave MCP plus your internal data MCPs. Each connection gives the skill a specific set of tools it can call.

MCPs your skill needs: 1. Octave MCP → find_person, enrich_person, qualify_person 2. CRM MCP (e.g. Salesforce) → query contacts, activities, opps 3. Call Recording MCP (e.g. Gong) → search calls by account 4. Product Data MCP (e.g. BigQuery) → query usage by domain

You set up MCPs once. The skill references them every time it runs. Start with Octave + CRM, add more sources as you go.

2

Build the skill: define your inputs

Your skill takes an account domain and a list of target roles as input. If it's chaining from the Account Research workflow, it also receives the account brief context.

Skill inputs: - companyDomain (required): "acme.com" - targetRoles (required): ["VP Engineering", "VP Platform", "Director DevOps", "Head of SRE"] - accountBrief (optional): context from Account Research skill

3

Build the skill: Octave MCP calls

For each target role, the skill calls find_person to discover contacts, enrich_person to get profile details, and qualify_person to score them against your Octave personas. This is the core discovery loop.

For each role in targetRoles: 1. find_person({ companyDomain, role }) → Octave MCP Returns: name, title, LinkedIn URL 2. enrich_person({ linkedInUrl }) → Octave MCP Returns: full profile, background, focus areas 3. qualify_person({ personData, companyDomain }) → Octave MCP Returns: persona match, score, rationale

4

Build the skill: internal data enrichment

For each person found, the skill calls your internal MCPs to layer in context. This is what turns a list of names into a stakeholder map.

For each person found: 1. CRM MCP → search contacts by email or name Returns: existing relationship, deal history, recent activities 2. Call Recording MCP → search calls by person or account Returns: recent call summaries, key topics discussed 3. Product Data MCP → query usage by account domain Returns: usage trends, feature adoption, activity spikes

This is where Medium difficulty comes from. Each MCP connection adds a data layer. Start with CRM if you only have one internal source.

5

Build the skill: output format

The skill assembles everything into a prioritized stakeholder map. Each person gets a card with their persona match, qualification score, internal context, and recommended approach. Strongest fits and warmest relationships sort to the top.

Output per person: - Name, Title, LinkedIn - Persona Match: [persona name] (score: 85/100) - Rationale: why this persona fits - CRM Context: existing relationship, last activity - Call History: recent conversations with their team - Product Signals: usage patterns tied to their account - Recommended Approach: based on persona + context

6

Run the skill

Give it an account and target roles. The skill handles all the MCP calls, enrichment, qualification, and assembly. You get back a prioritized stakeholder map ready for outreach.

Find the key people at acme.com. Look for VP of Engineering, VP of Platform, Director of DevOps, and Head of SRE. Enrich each person, qualify against our personas, and pull CRM + call + product context for each.

7

Iterate, then chain into messaging

Review the map. Ask follow-ups: "who else might be in this buying committee?" or "check if there's a CTO." Once the map is set, chain directly into the Generate Messaging workflow. The persona matches and account context carry forward.

Now draft personalized outreach for each person on the map. Use their persona match and the account brief to tailor the messaging.