LINKEDIN

Purpose

LINKEDIN extracts governed intelligence from LinkedIn messaging.

Every LinkedIn conversation — direct message, InMail, connection request — is an INTEL source. LINKEDIN reads the LinkedIn web interface via Chrome DevTools MCP, extracts conversation metadata and message content, resolves contacts to INTEL profiles, and ledgers all correspondence. Raw messages stay private (auth-gated); only SHOP-safe summaries surface publicly.

Structure

Leaf SERVICE scope. No governed child scopes. Extracted intelligence lands in INTEL/*.md (auth-gated).

Required closure artifacts per scope: CANON.md, README.md, LINKEDIN.md, VOCAB.md, ROADMAP.md, COVERAGE.md, LEARNING.md.

Learning lane per governed scope: LEARNING.md at the scope root is terminal and SHALL NOT nest further LEARNING/.

Routes

web_docs: https://hadleylab-canonic.github.io/
web_surface: https://hadleylab-canonic.github.io/SERVICES/LINKEDIN/
magic:    magic://hadleylab-canonic.github.io/SERVICES/LINKEDIN/

Pipeline

LinkedIn Messaging (web, authenticated)
  -> Chrome DevTools MCP snapshot (a11y tree extraction)
  -> conversation list scan (name, date, preview)
  -> thread detail extraction (full messages, timestamps)
  -> INTEL contact resolution (name + title + org -> USERS/)
  -> INTEL update (INTEL/{contact}.md)
  -> LEDGER (correspondence log, clock, cross-axioms)

Ecosystem Connectivity

1. Upstream: SHOP governance and SERVICES meta-governance.
2. Runtime: SHOP-safe outputs only. Raw messages stay private (auth-gated).
3. Source: https://www.linkedin.com/messaging/ — browser-authenticated, no local DB.
4. Sink: INTEL/*.md — correspondence ledger updates.
5. Auth: Chrome session cookies or Safari session (no API key required).
6. Profile format: Name + Title + Org from LinkedIn profile header.

Pages

Default: Overview.