geolocal-io/docs/product/use-cases/uc-05-conversational-ssp-ongoing.md

UC-05 — Conversational SSP: Ongoing Relationship

Status: Spec Business model: Model 1 — Endpoint enablement (ongoing optimization and monitoring) Primary surface: GeoLocal.io chat interface (returning user) Priority: P1 (follows UC-04; defines the first-month and beyond relationship) Prerequisite: UC-04 completed (owner verified, initial audit done, setup started or complete)

---

1. Problem

After the first session, a business owner has a GeoLocal endpoint and a list of recommended improvements — but most won't complete them without ongoing guidance. Their online presence changes over time (hours change, services change, listings get outdated), and AI assistants need current data to make accurate recommendations. A one-time activation is not enough: the platform needs to maintain the quality of the data it surfaces to AI assistants.

Without an ongoing relationship, the owner's endpoint degrades, recommendations become stale, and the platform loses credibility with both the owner and the AI assistants that depend on it.

---

2. Desired Outcome

The business owner returns to GeoLocal.io regularly (target: weekly or bi-weekly initially) to:

1. Resume their conversation where they left off
2. Get notified about presence changes or issues
3. Complete recommended improvements with AI guidance
4. Update their business data (hours, services, specials)
5. Receive periodic presence health reports
6. Access new features as the platform evolves

The relationship evolves from "setup helper" to "ongoing AI presence partner" — the owner trusts GeoLocal to keep them discoverable and well-represented.

---

3. Actors

Actor	Role
Business owner	Returning user; has completed initial verification
GeoLocal AI	Conversational interface; remembers context, tracks progress, proactively alerts
Presence monitoring engine	Periodic scanning of business listings across platforms
Notification system	Email or in-app alerts for issues, changes, and recommendations
geolocal platform	Data persistence, MCP endpoint, monitoring, reporting

---

4. Preconditions

• Owner has completed UC-04 (verified, audited, setup in progress or complete)
• Owner has a GeoLocal account (created during verification)
• Business data is persisted in the platform
• MCP endpoint is live (or in progress)

---

5. Main Success Scenario

Return and Resume

1. Owner Returns — Owner visits GeoLocal.io again (days, weeks, or months after first session)

   • The landing page recognizes returning users (via cookie, email, or login)
   • The chat opens with context: "Welcome back! Last time we talked, we were working on getting Maria's Hair Salon set up for AI discovery. Let me catch you up on where things stand."

2. Status Update — The AI summarizes current state:

   • "Your GeoLocal endpoint is live and responding to AI assistants."
   • "We've completed 3 of 7 recommended improvements. Here's what's left…"
   • "I noticed your Google listing was updated — looks like someone added your holiday hours. Good catch."

Ongoing Guidance

3. Continue Recommendations — The AI picks up where the conversation left off:

   • "Last time, we finished your Google Business Profile. Want to tackle your Bing listing today? It'll take about 10 minutes."
   • The AI guides the owner through the next steps conversationally

4. Data Updates — Owner communicates changes naturally:

   • "We're now open on Sundays from 10 to 4."
   • "We added a new service — balaycol."
   • "We moved to a new location."
   • The AI updates the data, confirms the change, and checks if the MCP endpoint needs updating

5. Presence Monitoring — The AI reports on ongoing presence health:

   • "I checked your listings this week. Everything looks good on Google and Apple. Yelp still has your old phone number — want to fix that?"
   • The AI can trigger a fresh audit on request: "Want me to run a full check of all your listings?"

Proactive Alerts

6. Issue Detection — The system detects problems and alerts the owner:

   • "Heads up — your Google Business Profile was flagged for review. You may need to respond within 7 days."
   • "Your website's contact page returns a 404. AI assistants can't reach you through your site right now."
   • "Your MCP endpoint hasn't responded in 24 hours. Let me check what's going on."

7. Opportunity Detection — The AI identifies improvement opportunities:

   • "Google just added a new feature for salons — they can now show available appointment slots directly in search. Want me to help you set that up?"
   • "I noticed a competitor in Cameron Park just updated their listing with services you also offer. You should make sure yours are listed too."

Periodic Reports

8. Health Reports — The AI delivers periodic summaries (weekly or monthly):
   • "Here's your monthly presence report: Your Google listing is at 92% completeness. Yelp is at 67%. Your website could use structured data for hours. Overall health: 81/100 — up from 64 last month."
   • The report is conversational, not a PDF: the AI walks through the key points and offers to help with anything that needs attention

Special Events and Seasonal

9. Seasonal Guidance — The AI anticipates seasonal needs:
   • "Holiday season is coming. Want to make sure your holiday hours are updated everywhere? I can help you set them on Google, Apple, and Bing."
   • "Summer tourism is picking up in Cameron Park. Let's make sure your listing is optimized for visitors searching from outside the area."

---

6. Alternate Paths

ID	Trigger	Behavior
A1	Owner returns after long absence	AI catches up: "Welcome back! It's been a few months. Let me give you a full update on your presence and what's changed."
A2	Owner wants full re-audit	"Sure — I'll run a fresh audit of all your listings. This might take a minute." Full audit re-execution
A3	Owner has multiple locations	AI manages each location separately: "Which location do you want to work on today — Cameron Park or Rocklin?" (post-MVP)
A4	Owner wants to add services	Conversational data update: "What new services do you offer? Tell me about them and I'll add them to your profile."
A5	Owner wants to pause	"No problem — I'll pause monitoring. When you're ready to pick back up, just come back and we'll resume."
A6	Owner is a delegate (not owner)	AI handles delegate context: "You're managing this for Maria, right? Let me show you what needs attention."

---

7. Exception Paths

ID	Trigger	Behavior
E1	MCP endpoint goes down	Alert owner immediately: "Your MCP endpoint stopped responding. I'm checking now… [diagnosis]. Here's what to do."
E2	Business closes permanently	AI detects closure signals (website gone, listings removed). Offers graceful decommission: "It looks like you may have closed. Want me to update your listings or pause your endpoint?"
E3	Owner disputes audit finding	AI explains methodology: "I found your Yelp listing has the old number because [source]. Want me to help you update it, or did I get it wrong?"
E4	Platform changes break listings	AI detects upstream changes (Google changes their API, Yelp changes their format). Adapts and notifies: "Google updated their listing format. I've adjusted — your data still looks good."
E5	Owner abandons ongoing relationship	Session persists. Owner can return anytime. After extended absence, AI offers full catch-up rather than incremental updates

---

8. Functional Requirements (Product)

Return User Experience

• Recognize returning users (cookie, email, or login)
• Resume conversation with full context
• Summarize what happened since last visit
• Show progress toward goals

Presence Monitoring

• Periodic scanning of business listings (cadence TBD — daily, weekly)
• Change detection: hours, services, contact info, reviews
• Issue detection: broken links, removed listings, flagged profiles
• Health scoring: per-platform and aggregate

Conversational Data Management

• Owner communicates changes in natural language
• AI parses and updates structured data
• Confirmation before saving: "So you're now open Sundays 10–4. Save that?"
• Edit history: owner can see what changed and when

Proactive Alerts

• Issue alerts: endpoint down, listing flagged, website broken
• Opportunity alerts: new platform features, seasonal optimization
• Digest option: bundle alerts into a weekly summary instead of real-time

Periodic Reports

• Conversational health reports (weekly or monthly)
• Trend data: completeness scores over time
• Action items derived from report findings
• Comparison to previous periods

Seasonal and Event Guidance

• Calendar-aware suggestions (holidays, local events, tourism seasons)
• Proactive hour updates for holidays
• Special promotion support

---

9. Conversation Flow Requirements

The ongoing relationship conversation differs from the first-hour flow in key ways:

• Context-aware: The AI remembers everything from previous sessions — what's been done, what's pending, what the owner cares about
• Proactive: The AI initiates topics (alerts, opportunities) rather than only responding to owner input
• Efficient: Returning users don't re-explain their business. The AI leads with what's new or needs attention
• Flexible: The owner can jump to any topic: "Update my hours," "Run an audit," "What's my health score?" — the AI handles it without requiring a specific flow

---

10. Success Metrics

Metric	Definition	Early Target
Return rate	Owners who return within 30 days of first session	>50%
Session frequency	Average sessions per owner per month	2+ in first month
Recommendation completion	% of recommended actions completed within 30 days	Track; improve
Data freshness	% of endpoints with data <30 days old	>80%
Endpoint uptime	% of endpoints responding to AI assistants	>99%
Owner retention	Owners active after 90 days	Track; improve
Health score improvement	Average health score delta (first session vs. 30 days)	+20 points target

---

11. Out of Scope for UC-05

• Multi-business accounts (deferred)
• Voice input (deferred)
• Multi-language support (deferred)
• Automated fixes applied by the AI (owner executes; AI guides)
• Partner referral workflow (deferred)
• Revenue/usage-based billing (deferred)
• White-label or reseller features (deferred)
• Model 2 intermediate features (see UC-02)

---

12. Dependencies

• UC-04 (first-hour onboarding complete)
• User authentication (login for returning users)
• Session persistence and history
• Presence monitoring engine (periodic)
• Notification delivery (email or in-app)
• Business data management (CRUD via conversation)
• MCP endpoint health monitoring
• Calendar integration (seasonal awareness)

---

13. Open Questions

1. What is the monitoring cadence? Daily, weekly, or event-triggered?
2. Do we email the owner proactively, or only alert in-app when they return?
3. How do we handle owners who have multiple businesses? (post-MVP)
4. Should we offer a "set it and forget it" mode where the AI auto-updates listings?
5. What's the escalation path when the AI can't resolve an issue?
6. Do we charge for ongoing monitoring, or is it included in the base service?
7. How do we balance proactive alerts with notification fatigue?
8. Should the AI suggest a follow-up cadence to the owner? ("Check in weekly for best results")