clawdbot-workspace/proposals/solvr-discovery-questions.md
2026-02-05 23:01:36 -05:00

238 lines
7.1 KiB
Markdown

# Solvr Discovery Questions
## Pre-Engagement Scoping Call
*Use these to sound sharp, set boundaries, and avoid landmines.*
---
## 1. User Interface & Access
**How do Zack and Allyson prefer to interact with their agents day-to-day?**
- Telegram?
- iMessage?
- Slack?
- Email?
- Web dashboard?
*Why you're asking: Different interfaces = different infrastructure. iMessage needs Mac hosting. Telegram is simplest. This scopes the build.*
**Will each executive interact only with their assigned agent, or do they need access to all three?**
*Why: Affects permissions, routing logic, and potential confusion.*
**Do you need mobile access, desktop, or both?**
*Why: Mobile-first means Telegram/iMessage. Desktop opens up more options.*
---
## 2. Infrastructure & Hosting
**Do you have a preference for where the agents run?**
- Your own servers (we deploy to your infrastructure)
- Cloud instance we manage for you
- No preference — recommend what's best
*Why: "Your infrastructure" = less ongoing responsibility for you. "We manage" = recurring revenue but more liability.*
**Are there any compliance or data residency requirements we should know about?**
- SOC 2?
- GDPR?
- Data must stay in US/EU?
*Why: If they say SOC 2, price goes up. If they say "no," you're clear.*
**How do you currently handle API credentials and secrets?**
- 1Password / secrets manager?
- Shared doc? (oof)
- IT team manages?
*Why: Shows you take security seriously. Also flags if they're a mess internally.*
---
## 3. GoHighLevel Specifics
**Which GHL features are mission-critical for the agents?**
- Contacts & pipelines?
- SMS/email campaigns?
- Workflows & automations?
- Reporting?
- All of the above?
*Why: You have 65 tools built. This confirms coverage and avoids "but we also need X" later.*
**Are you on GHL Agency or Location level?**
*Why: API access differs. Agency = more powerful. Location = more limited.*
**Do the agents need to trigger GHL workflows, or just read/write data?**
*Why: Triggering workflows is more complex. Reading/writing is straightforward.*
---
## 4. LinkedIn (The Risky One)
**For LinkedIn management — are you comfortable with agents drafting posts for human approval, or do you want fully automated posting?**
*Why: "Human approval" = safe. "Fully automated" = ban risk. Let them choose the risk level.*
**Would you use a dedicated LinkedIn account for automation, or Zack/Allyson's personal accounts?**
*Why: Dedicated account = if it gets banned, no big deal. Personal account = yikes.*
**Are you aware that LinkedIn actively restricts automation, and there's inherent account risk with any automated activity?**
*Why: CYA. Get this on record. If an account gets restricted, it's not your fault.*
---
## 5. Meeting Intelligence
**Where are meeting recordings stored today?**
- Google Drive (automatic from Meet)?
- Local downloads?
- Somewhere else?
*Why: Scopes the "ingest" part of meeting intelligence.*
**Do you need real-time transcription during meetings, or is post-meeting processing okay?**
*Why: Real-time = much harder. Post-meeting = standard whisper workflow.*
**Who should receive the meeting summaries and action items?**
- Just the meeting organizer?
- All attendees?
- Specific people?
*Why: Affects distribution logic and permissions.*
---
## 6. Agent Coordination
**When one agent hands off to another, how should that look to you?**
- Silent (happens in background)?
- Notification ("Dot handed this to Rose")?
- Approval required ("Dot wants to hand this to Rose — approve?")?
*Why: Silent = simpler. Approval = more control but more friction.*
**Should agents be able to assign tasks to each other autonomously, or should a human approve task delegation?**
*Why: Same as above — autonomy vs. control tradeoff.*
**Is there a "source of truth" for client/contact info?**
- GHL is the master?
- Notion?
- Spreadsheet?
- Multiple systems (uh oh)?
*Why: One source = clean. Multiple = sync hell. Flag this early.*
---
## 7. Design & Content
**For design assets — do you have existing brand guidelines, templates, or a style guide?**
*Why: If yes, agents can follow them. If no, you're not responsible for "off-brand" output.*
**What formats do you need for generated content?**
- PNG/JPG for social?
- PDF for reports?
- PPTX for presentations?
*Why: Scopes the design MCP capabilities needed.*
**Who approves design output before it goes live?**
*Why: Establishes human-in-the-loop. Protects you from "the agent posted something ugly."*
---
## 8. Success Criteria
**What does success look like 90 days after launch?**
*Why: Gets them to define the goal. You deliver to THAT, not endless scope creep.*
**What's the #1 thing you want off your plate?**
- Zack's answer?
- Allyson's answer?
*Why: Prioritizes what matters. If you nail this one thing, they're happy.*
**How will you measure ROI on this project?**
- Time saved?
- Revenue generated?
- Leads qualified?
- Meetings booked?
*Why: Anchors expectations to measurable outcomes.*
---
## 9. Timeline & Priorities
**Is there a hard deadline or event driving this project?**
*Why: If yes, you know the pressure. If no, you have flexibility.*
**If we had to launch with only ONE agent fully functional, which would it be?**
*Why: Forces prioritization. You deliver that one first, then iterate.*
**Are there any integrations or features that are "nice to have" vs. "must have"?**
*Why: Separates core scope from stretch goals. Protects you from scope creep.*
---
## 10. Red Flag Detectors
**Have you worked with AI agents or automation before?**
- If yes: What worked? What didn't?
- If no: What are your expectations?
*Why: Experienced = realistic expectations. First-timers = may need education.*
**Who's the decision-maker for approving deliverables?**
*Why: Avoids "I like it but my partner doesn't" at the end.*
**Is there anyone else on your team who should be involved in this conversation?**
*Why: Surfaces hidden stakeholders early.*
---
## Questions YOU Should Be Ready For
They might ask you:
| Their Question | Your Answer |
|----------------|-------------|
| "Can you guarantee the agents won't make mistakes?" | "Agents operate with human oversight for critical actions. We build in approval workflows for anything high-stakes." |
| "What if LinkedIn bans the account?" | "We mitigate risk with rate limiting and human approval for outreach. If you'd prefer, we can use a dedicated automation account separate from personal profiles." |
| "How long until we see ROI?" | "Most clients see time savings within the first 2 weeks. Full ROI depends on your volume, but we'll set measurable KPIs together." |
| "Can we add more features later?" | "Absolutely. The architecture is modular — we can add new MCP integrations or agent capabilities as your needs evolve." |
| "What happens if you get hit by a bus?" | "All code and documentation is yours. We'll do a full handoff and training so your team can maintain it independently." |
---
## After the Call
Summarize in an email:
1. What they said their priorities are
2. What you're including in scope
3. What's explicitly OUT of scope
4. Timeline and next steps
*This protects you. If scope creeps later, point to the email.*
---
*Good luck king* ᕕ( ᐛ )ᕗ