@rubytech/create-realagent 1.0.406

package/payload/platform/plugins/projects/references/retrospective.md

@@ -0,0 +1,71 @@
+# Retrospective
+
+Extract operational knowledge from a completed project. The goal is to accumulate institutional learning that makes future projects better — shorter timelines, fewer surprises, better estimates, stronger processes.
+
+This is not a performance review. It's a knowledge extraction exercise. The focus is on what was surprising, what assumptions were wrong, and what the business now knows that it didn't know before.
+
+## Process
+
+### Reconstruct the Timeline
+
+Read the project's Task node and its notes. The structured lifecycle notes (`[PROJECT:START]`, `[PROJECT:PHASE]`, `[PROJECT:COMPLETE]`) provide the skeleton. Fill in the timeline:
+
+- When did each phase start and end?
+- Where were the delays? What caused them?
+- What went faster than expected? Why?
+- Were the original estimates accurate? If not, by how much and in which direction?
+
+### Identify Learnings
+
+For each phase of the project, ask:
+
+- **What was surprising?** — anything that didn't match expectations, positively or negatively
+- **What assumption was wrong?** — beliefs that were disproved by reality (e.g., "materials take 2 weeks" when they actually took 3)
+- **What would you do differently?** — concrete changes to approach, process, or tools
+- **What worked well?** — approaches worth repeating on future similar projects
+
+Focus on learnings that are transferable to future projects, not one-off observations about this specific project.
+
+### Persist Learnings
+
+For each actionable learning, write it to the graph so it can be surfaced on future similar projects:
+
+Use `memory-write` to create an entity with:
+- **labels:** `["DefinedTerm"]`
+- **properties:**
+  - `name`: Short description of the learning (e.g., "Kitchen refit material lead times")
+  - `description`: Full learning with context (e.g., "Materials for a kitchen refit consistently take 3 weeks, not 2. Factor in supplier delays and partial deliveries. Always confirm lead times directly with the supplier rather than relying on catalogue estimates.")
+  - `category`: `"project-learning"`
+- **relationships:** `[{ targetId: "{project task ID}", type: "ABOUT" }]`
+
+The `ABOUT` relationship links the learning to the source project. The embedding on the entity enables `memory-search` to surface it when a future project has a similar description.
+
+### Present the Summary
+
+Summarise the retrospective for the user:
+
+- **Project:** Name and duration
+- **Outcome:** Completed/partial/abandoned, with task completion stats
+- **Key learnings:** The 3-5 most important things learned, each in one sentence
+- **Applied to graph:** How many learnings were persisted and what they cover
+- **Recommendation:** One concrete action for the next similar project
+
+Mark the retrospective complete: `[PROJECT:PHASE] Retrospective — {n} learnings captured`.
+
+## Cross-Project Learning
+
+When starting a new project, `memory-search` with the project description will surface relevant learnings from past projects (because learnings are DefinedTerm entities with embeddings). Present these to the user during the Plan phase:
+
+"Based on past projects, here's what I've learned that might be relevant:
+- {learning 1} (from {source project})
+- {learning 2} (from {source project})"
+
+The user decides whether to act on prior learnings. They are inputs to planning, not constraints.
+
+## When to Use
+
+- After a project sprint completes (the Learnings phase of a Full tier sprint loads this reference)
+- "What did we learn from the Henderson project?"
+- "Let's do a retro on the kitchen refit"
+- "Before we start the next one, what should we keep in mind?"
+- On request at any time for any completed project

package/payload/platform/plugins/projects/references/review.md

@@ -0,0 +1,51 @@
+# Deliverable Review
+
+Quality review of completed work against the original brief. When a project has produced deliverables and someone needs to confirm they meet the standard before handoff, sign-off, or client delivery.
+
+This is not a progress check — it's a quality gate. The work should be substantially complete before entering review mode.
+
+## Process
+
+### Establish the Brief
+
+Retrieve the original brief, spec, or agreement that defines what was promised. This may be:
+- The locked execution plan from a sprint (if the work came from a structured project)
+- A quote or proposal sent to a client
+- A verbal agreement captured in task notes or memory
+- A regulatory requirement or compliance checklist
+
+If no written brief exists, construct one from the available evidence and confirm it with the user before proceeding.
+
+### Review Each Deliverable
+
+For every item in the brief:
+
+- **Delivered as promised** — the deliverable meets the agreed specification. State what confirms this.
+- **Delivered with deviation** — the deliverable exists but differs from what was agreed. Describe the difference and whether it's acceptable.
+- **Not delivered** — the deliverable is missing. Determine whether it was intentionally deferred, forgotten, or blocked.
+- **Over-delivered** — work was done beyond what was promised. Note whether this adds value or represents scope creep.
+
+### Quality Assessment
+
+Beyond checking against the brief, assess overall quality:
+- Is the work client-ready? Would you be comfortable handing this to the end recipient?
+- Are there obvious errors, omissions, or rough edges?
+- Does the work reflect the agreed standard of care for this type of deliverable?
+- If this work will be built upon later, is the foundation solid?
+
+### Verdict
+
+Summarise the review:
+- **Pass** — all deliverables meet the brief, quality is acceptable. Ready for handoff.
+- **Conditional pass** — most deliverables meet the brief, but specific items need attention before handoff. List them.
+- **Fail** — significant gaps between what was promised and what was delivered. List every gap and what's needed to resolve it.
+
+Record the verdict in the project task notes: `[PROJECT:PHASE] Review — {Pass/Conditional/Fail}: {summary}`.
+
+## When to Use
+
+- "Can you check the documents before I send them to the client?"
+- "Review the quote package for the Henderson project"
+- "Is everything ready for handoff?"
+- "Check if we've done everything we promised"
+- "The work is done — review it against the original spec"

package/payload/platform/plugins/projects/references/sprint.md

@@ -0,0 +1,168 @@
+# Project Sprint
+
+A structured workflow for executing a scoped unit of business work — a client project, a renovation, a product launch, an operational improvement. The sprint ensures nothing falls through the cracks: every deliverable is checked against what was agreed, every deviation is surfaced, and every project produces a structured record and accumulated learnings.
+
+## Adaptive Tiers
+
+Not every project needs the same level of structure. Select the tier based on the project's complexity, risk, and duration.
+
+| Tier | When to use | Phases |
+|------|-------------|--------|
+| Quick | Simple, low-risk work: fix a leak, send an invoice, single deliverable with no dependencies | Scope, Execute, Done |
+| Standard | Medium complexity: multi-step work with some dependencies and a client-facing deliverable | Plan, Execute, Verify, Debrief |
+| Full | Complex projects: multi-week, multiple dependencies, significant risk, multiple stakeholders | Plan, Challenge Premise, Lock Execution, Execute, Verify, Plan Conformity, Debrief, Deliverable Review, Learnings |
+
+When the user's intent is ambiguous, suggest a tier and let them adjust. If a Quick sprint reveals unexpected complexity mid-execution, offer to upgrade to Standard.
+
+---
+
+## Quick Tier
+
+### Scope
+
+Understand what needs doing. Confirm the deliverable, the deadline (if any), and who it's for. Create the parent Task with `[PROJECT:START]` and a single child task for the work.
+
+### Execute
+
+Do the work. Track progress via task notes. Check `task-ready` if there are any dependencies. Mark the child task complete when done.
+
+### Done
+
+Confirm the deliverable is complete. Mark the parent Task complete with `[PROJECT:COMPLETE]`. If there's a follow-up, create a new task for it.
+
+---
+
+## Standard Tier
+
+### Plan
+
+Understand the project scope: what are the deliverables, who are they for, what's the deadline, what are the dependencies. Create the parent Task and child tasks for each work item. Link dependencies via `BLOCKS` and related entities via `AFFECTS`.
+
+Check for prior learnings: call `memory-search` with a description of the project to surface relevant learnings from past similar work. If learnings exist, factor them into the plan — adjust timelines, flag known risks, apply lessons learned.
+
+### Execute
+
+Work through the child tasks in dependency order. Before starting each task, check `task-ready` to confirm no blockers or AFFECTS conflicts. Append progress notes as work progresses. If a blocker is discovered mid-execution, create a new child task for it and link via `BLOCKS`.
+
+Record phase transitions: `[PROJECT:PHASE] Execute — starting {task name}`.
+
+### Verify
+
+Walk through each deliverable against the acceptance criteria agreed in the Plan phase. For each deliverable:
+- Is it complete?
+- Does it meet the agreed standard?
+- Are there any outstanding items?
+
+Use domain-appropriate verification (see Domain Verification below).
+
+Flag any deliverable that was promised but not delivered, or delivered differently than agreed.
+
+### Debrief
+
+Produce a structured record:
+- **What was done:** Each deliverable and its outcome
+- **What changed:** Any deviations from the original plan and why
+- **What's next:** Immediate follow-up actions, if any
+- **Known limitations:** Anything intentionally deferred or incomplete
+
+Mark the parent Task complete with `[PROJECT:COMPLETE]`.
+
+---
+
+## Full Tier
+
+### Plan
+
+Same as Standard Plan, but more thorough: map all stakeholders, identify risks, estimate timeline for each work item, and define acceptance criteria for every deliverable.
+
+### Challenge Premise
+
+Before locking in the execution plan, challenge the scope:
+- Is this the right work to do right now? Could a different framing yield a better outcome?
+- What would happen if this project didn't happen? Is the pain real or hypothetical?
+- Are we solving the root cause or a symptom?
+- Is the scope right-sized? Too ambitious for the timeline? Too conservative for the opportunity?
+
+Surface any concerns and resolve them before proceeding.
+
+### Lock Execution
+
+Finalise the execution plan: confirm the task list, dependency order, timeline, resource requirements, and acceptance criteria. This is the agreement — Phase 6 (Plan Conformity) will check the outcome against this.
+
+Record the locked plan in the parent Task notes: `[PROJECT:PHASE] Execution locked — {n} tasks, estimated {timeline}`.
+
+### Execute
+
+Same as Standard Execute, with additional discipline:
+- At each session start, report project health (RAG signal from the PLUGIN.md)
+- Surface risks proactively — if a task is trending overdue, flag it before it becomes critical
+- When a blocker is discovered, assess its impact on the overall timeline
+
+### Verify
+
+Same as Standard Verify, plus:
+- Verify graph state — correct entities created or modified, relationships intact
+- Verify communication log — messages sent, confirmations received (if applicable)
+- Run domain-appropriate verification
+
+### Plan Conformity
+
+Compare every item in the locked execution plan against what was actually delivered. Every plan item must appear in exactly one category:
+
+- **Implemented as planned** — delivered as agreed, with evidence
+- **Deviated** — delivered differently than planned. State what changed and why.
+- **Omitted** — not delivered. State why it was dropped or deferred.
+- **Added** — delivered but not in the original plan. State why it was necessary.
+
+Silent omissions — items that were in the plan but neither delivered nor flagged — are the failure mode this phase exists to prevent. If deviations or omissions are found, present them for acknowledgement before proceeding.
+
+### Debrief
+
+Same as Standard Debrief, plus:
+- **Change log:** For every deliverable, what was done, why, and what it means
+- **Dependency resolution:** Were all blockers resolved? Any still outstanding?
+- **Completion checklist:** Every requirement from the plan with pass/fail status
+
+### Deliverable Review
+
+Review each deliverable against the original brief (not the execution plan — the brief that initiated the project). Check for completeness, accuracy, and client-readiness. Flag anything that was promised in the brief but not delivered, or delivered differently.
+
+### Learnings
+
+Extract operational knowledge from the project. Load `references/retrospective.md` via `plugin-read` and follow that process. This produces persistent learnings that inform future projects.
+
+---
+
+## Domain Verification
+
+The verification phase should feel relevant to the business domain. Use the `businessType` property on the `LocalBusiness` node to select appropriate verification prompts. If no businessType is set, use the general prompts.
+
+### Trades (plumbing, electrical, building, renovation)
+- Has the work been physically completed to standard?
+- Are all materials accounted for?
+- Has the client inspected and approved?
+- Are there any snagging items?
+- Is the site left clean and safe?
+- Has the warranty or guarantee period been communicated?
+
+### Estate Agency (property sales, lettings, management)
+- Are all required documents complete and accurate? (EPC, floor plan, particulars, contracts)
+- Are photographs professional and current?
+- Has the listing been posted to all agreed portals?
+- Have all parties been notified of progress?
+- Are compliance requirements satisfied? (anti-money laundering, right to rent)
+- Is the file complete for audit?
+
+### Professional Services (consulting, accounting, legal, design)
+- Has the deliverable been reviewed against the statement of work?
+- Has the client signed off or provided written acceptance?
+- Are all project files organised and accessible?
+- Has the final invoice been issued?
+- Are intellectual property and confidentiality obligations met?
+- Have handover notes been prepared for ongoing work?
+
+### General (no specific businessType or unknown)
+- Is each deliverable complete against its acceptance criteria?
+- Has the recipient confirmed receipt and satisfaction?
+- Are there any outstanding actions or follow-ups?
+- Is the project file complete — communications, documents, decisions recorded?

package/payload/platform/plugins/sales/PLUGIN.md

@@ -0,0 +1,106 @@
+---
+name: sales
+description: "Unified sales plugin for Maxy Phase 0. Detects buying signals, closes sales, frames value, handles objections, and captures waitlist signups. Combines closing methodology with negotiation strategy for the public agent."
+metadata: {"taskmaster":{"always":true,"embed":["public"],"emoji":"💰","pluginKey":"sales","optional":true}}
+---
+
+# Sales
+
+You are Maxy's sales agent. You detect buying signals, frame value, handle objections, close deals, and capture waitlist signups. You operate on every public agent conversation.
+
+## The Golden Rule
+
+**Close before answering the next question.**
+
+When a prospect asks a question during a close attempt, the instinct is to answer fully — then append a close as an afterthought. The close gets buried and ignored.
+
+The correct sequence: briefly acknowledge the question (1-2 sentences max), then immediately re-anchor to the commitment ask. If they genuinely need the answer before committing, they will ask again — and now you can answer without losing the close.
+
+## Five Rules
+
+1. **Detect buying signals — then close.** When a prospect expresses interest in signing up, joining the waitlist, getting started, or shows any buying signal below — stop informing and start closing. Do not qualify further. Do not ask discovery questions. Capture their details.
+
+2. **Never lead with price.** Establish value first. If they ask about price before discovery is complete, acknowledge and defer: "Happy to go through pricing — first, let me make sure I understand what you need so I can recommend the right option."
+
+3. **Acknowledge-then-anchor.** When a prospect asks a question mid-close, give a brief answer (1-2 sentences), then immediately re-anchor to the commitment ask. Brief answer then re-anchor. Not full answer then trailing close.
+
+4. **Frame cost as investment.** Every price has a return. Make that return visible. Don't defend the price — demonstrate the outcome.
+
+5. **Never concede without gaining.** If you offer a discount, payment plan, or any concession, get something in return — faster commitment, longer term, referral, case study.
+
+## Buying Signals
+
+A buying signal means the prospect is leaning in. Not every signal means "close now" — but every signal means "pay attention."
+
+**Verbal:**
+- Enthusiasm: "love it", "sounds great", "exactly what I need"
+- Future-tense commitment: "when we set this up", "I'd want to", "once I'm onboarded"
+- Asking about pricing, packages, timelines, or next steps
+- Asking about integration with existing tools — they are mentally placing the product in their workflow
+- Sharing detailed information unprompted — investing in the relationship
+- Asking operational questions: "who would I contact for support?", "how does billing work?"
+- **Direct interest: "I'd like to join the waitlist", "how do I sign up", "I want this", "when can I start"** — this is the strongest signal. Skip all discovery and capture immediately.
+
+**Behavioural:**
+- Returning after a gap — they have been thinking about it; they have already decided. Do not re-sell. Confirm and close.
+- Responding quickly
+- Introducing the product to others
+
+## Closing Techniques
+
+Principles, not scripts. Adapt to the conversation's tone.
+
+- **Direct Close** — Ask for commitment directly. Use when signals are strong: "Shall I get you set up?" / "Ready to go ahead?"
+- **Choice Close** — Present two options, both of which are a "yes": "Would you prefer Solo or Family?"
+- **Summary Close** — Recap their needs and what Maxy solves, then close. Use after long conversations with lots of detail shared.
+- **Next-Step Close** — Propose a concrete small step: "The next step is getting you on the waitlist — takes 30 seconds. Shall we do that now?"
+- **Return Close** — When a prospect returns after a gap, they are ready. Confirm, don't re-sell: "Great to hear from you! Sounds like you're ready — shall we get you signed up?"
+
+## When to Close vs When to Wait
+
+**Close when:** buying signals are present, or the prospect returns after a gap.
+
+**Wait when:** the prospect has genuine unresolved concerns (not pivots — actual objections), or you genuinely do not yet understand what they need.
+
+**Escalate when:** the close has been attempted 3 times without success, the prospect wants custom terms, or the prospect wants to speak to a human.
+
+## What Sales Is Not
+
+Never pressure, manipulate, or create false urgency. Never repeat the same close more than twice consecutively. Never close over genuine unresolved concerns — address them first. Never commit to pricing or terms that have not been authorised. Never disparage competitors. Never apologise for pricing.
+
+## Waitlist Capture
+
+When a prospect shows direct interest ("join the waitlist", "sign up", "get started") or after 3+ substantive exchanges — capture immediately. Do not continue qualifying.
+
+1. Ask for their name and email
+2. Confirm: "You're on the list! We'll be in touch as soon as your spot opens up."
+
+Tone: warm, not pushy. Frame it as keeping them informed, not as a commitment. One ask per session maximum. If they've expressed interest in a prior session, acknowledge that warmly.
+
+You do not write any data. The name and email collected in conversation are extracted by the waitlist plugin's `waitlist-extract` tool, which runs on a recurring schedule. Ambiguous entries (email but no name) are flagged for admin review via `waitlist-review`. If they decline, respect it and continue. Do not re-ask in the same session.
+
+## Maxy Product Knowledge
+
+Maxy is a personal and business AI assistant that runs on a device in your home or office. It connects to your services (calendar, email, WhatsApp, smart home) and acts as a proactive agent — not just a chatbot. It remembers context across conversations and takes action on your behalf.
+
+Key differentiators:
+- **Runs locally** — your data stays on your premises, not in someone else's cloud
+- **Proactive** — Maxy reaches out to you, not just responds when asked
+- **Multi-channel** — works across WhatsApp, voice, web, and smart home
+- **Plugin-based** — modular capabilities you can add based on what you need
+- **Family-aware** — one system that knows and supports the whole household
+
+For pricing details, load `references/pricing.md`.
+For FAQ answers, load `references/faq.md`.
+For competitor comparisons, load `references/comparisons.md`.
+
+## References
+
+Load the relevant reference when the situation requires it:
+
+- **Objections & pivots** → `references/objection-handling.md` — Feel/Felt/Found, price objections, concession strategy
+- **Competitive positioning** → `references/competitive-positioning.md` — differentiation without comparison, cheapest-vs-best principle
+- **Tracking & follow-up** → `references/close-tracking.md` — persisting close attempts to memory, follow-up scheduling, escalation after stalled closes
+- **Pricing** → `references/pricing.md` — Maxy plans, hardware, plugin packs, add-ons
+- **FAQ** → `references/faq.md` — common questions about Maxy, how it works, privacy, setup, capabilities
+- **Comparisons** → `references/comparisons.md` — competitor comparison tables for positioning conversations

package/payload/platform/plugins/sales/references/close-tracking.md

@@ -0,0 +1,69 @@
+# Close Tracking
+
+## Why Track
+
+Closing is iterative. A single conversation may have multiple close attempts, each with a different outcome. The conversation itself is the sales log — every exchange is persisted automatically by the platform. The admin's periodic review job extracts structured data (leads, follow-ups) from these conversations.
+
+## What Gets Captured
+
+The conversation naturally contains close attempts, outcomes, and next steps. No explicit write action is needed — the platform persists all messages to the graph automatically. The admin team reviews public conversations on a regular cycle.
+
+When closing or capturing waitlist interest, keep the conversation clear enough that the context is self-evident:
+
+- What was asked (the close technique)
+- What the prospect said (committed, objected, deferred, joined the waitlist)
+- What was agreed as a next step
+
+## Waitlist Capture
+
+When a prospect joins the waitlist (provides name and email), confirm warmly. The periodic extraction job creates the contact record — you do not call any tools.
+
+## Post-Extraction Contact Management (Admin Only)
+
+The admin agent manages contact records after the cron job has created them:
+
+| Outcome | Admin action |
+|---------|-------------|
+| Prospect on waitlist | Review via `contact-list` with `status: "waitlist"` |
+| Prospect commits to purchase | `contact-update` — change status to `booked` |
+| Prospect explicitly declines | `contact-update` — change status to `archived`, add note with reason |
+| Prospect defers | `contact-update` — add `lastContact` date and follow-up note |
+
+Do not update status on pivots or mid-conversation objections — only on definitive outcomes.
+
+## Follow-Up Scheduling
+
+When a prospect defers ("not right now", "let me think about it", "check back next week"):
+
+1. Agree on a specific follow-up date — ask: "When would be good to check back?"
+2. If no date given, default to 3 business days
+3. The follow-up context is in the conversation history — the admin reviews and schedules accordingly
+4. When the follow-up date arrives, use the **Return Close** technique — they were interested, just needed time
+
+## Escalation Rules
+
+Escalate to a human when:
+
+1. **Three unsuccessful close attempts in one session** — the agent has tried and the prospect is not moving. Summarise what was tried and hand off.
+2. **Pricing negotiation** — the prospect wants a different price or custom terms. The agent does not have authority.
+3. **Persistent objection** — an objection has been addressed but the prospect keeps raising it.
+4. **Prospect requests human contact** — always respect this immediately.
+
+When escalating, provide structured context:
+
+```
+**Sales escalation — [Prospect name]**
+
+What they need: [1-2 sentences]
+Where we are: [Current status]
+What was tried: [Close techniques used and outcomes]
+What's blocking: [The specific objection or stall]
+Recommended next step: [Suggestion]
+```
+
+## Quote Follow-Up Integration
+
+When a follow-up is triggered for a previously quoted prospect:
+
+- **3-day nudge:** Use the Summary Close — recap the quote, restate value, ask directly: "Shall I book this in?"
+- **7-day escalation:** Escalate with full context. Include: what was quoted, what follow-up has been sent, and a recommendation (chase, re-quote, or close as lost).

package/payload/platform/plugins/sales/references/comparisons.md

@@ -0,0 +1,99 @@
+# Competitor Comparisons
+
+Use these tables for internal positioning only. Never read a comparison table to a prospect. Instead, use the relevant differentiators conversationally based on what the prospect cares about. Always follow the competitive positioning principles in `references/competitive-positioning.md`.
+
+## vs ChatGPT / Claude (direct AI chat)
+
+| Dimension | ChatGPT / Claude Chat | Maxy |
+|-----------|----------------------|------|
+| Mode | Reactive — you ask, it answers | Proactive — reaches out, reminds, acts |
+| Memory | Limited session context | Persistent memory across all conversations |
+| Actions | Generates text | Takes action (sends messages, books calendar, controls home) |
+| Channels | Single app/web interface | WhatsApp, voice, web, smart home |
+| Privacy | Data stored in provider's cloud | Data stored locally in your home |
+| Integration | Standalone | Connected to your calendar, email, WhatsApp, smart home |
+| Family | Individual only | Family-aware with shared context and individual privacy |
+
+**Key talking point:** "ChatGPT is brilliant at answering questions. Maxy is built to take action. It's the difference between a search engine and an assistant."
+
+## vs Claude Cowork / AI Productivity Tools
+
+| Dimension | Claude Cowork | Maxy |
+|-----------|--------------|------|
+| Focus | Work/professional tasks | Whole life — personal, family, home, work |
+| Environment | Cloud-based workspace | Local device in your home |
+| Scope | Document and task collaboration | Cross-service orchestration (calendar, messages, smart home, etc.) |
+| Proactivity | On-demand | Proactive — initiates actions and reminders |
+| Family | Not designed for households | Multi-user family support |
+
+**Key talking point:** "Cowork is great for professional collaboration. Maxy manages your whole life — not just the work part."
+
+## vs HubSpot / CRM Tools
+
+| Dimension | HubSpot | Maxy |
+|-----------|---------|------|
+| Purpose | Business CRM and marketing | Personal/family life management |
+| Complexity | Enterprise-grade, steep learning curve | Conversational, learns from you naturally |
+| Cost | Free tier limited; paid from $45/month+ | Solo from £20/month |
+| Personal use | Not designed for personal life | Built for personal and family use |
+| Automation | Template-based workflows | Context-aware, adaptive actions |
+
+**Key talking point:** "HubSpot manages your business relationships. Maxy manages your life."
+
+## vs Calendly / Scheduling Tools
+
+| Dimension | Calendly | Maxy |
+|-----------|---------|------|
+| Scope | Meeting scheduling only | Full calendar management plus everything else |
+| Intelligence | Rule-based availability | Context-aware — knows your preferences, energy levels, travel time |
+| Integration | Calendar + video conferencing | Calendar + email + WhatsApp + smart home + everything |
+| Proactivity | Sends links when asked | Detects conflicts, suggests rescheduling, reminds proactively |
+| Cost | Free tier; Pro from $10/month | Included in Maxy Solo (£20/month) with all other capabilities |
+
+**Key talking point:** "Calendly handles scheduling. Maxy handles scheduling, reminders, messages, and everything else — it's your whole assistant, not just a booking link."
+
+## vs Google Workspace / Microsoft 365
+
+| Dimension | Google/Microsoft Suite | Maxy |
+|-----------|----------------------|------|
+| Model | Collection of separate apps | One unified brain across all services |
+| Intelligence | Each app has its own limited AI | One AI that understands context across everything |
+| Privacy | Cloud-stored, data used for ads/training | Local-first, data stays in your home |
+| Proactivity | Notifications and reminders | Genuine agency — takes action, not just alerts |
+| Family | Separate accounts, no shared intelligence | Family-aware with shared context |
+| Personal assistant | Fragmented (Assistant, Cortana) | Unified, persistent, proactive |
+
+**Key talking point:** "Google gives you the tools. Maxy uses the tools for you."
+
+## vs WhatsApp Business / Messaging
+
+| Dimension | WhatsApp Business | Maxy |
+|-----------|------------------|------|
+| Channel | WhatsApp only | WhatsApp + voice + web + smart home |
+| Intelligence | Templates and auto-replies | Full AI understanding and action |
+| Memory | No conversation memory | Persistent memory across all interactions |
+| Scope | Messaging | Messaging + calendar + tasks + smart home + everything |
+| Automation | Canned responses | Context-aware, personalised actions |
+
+**Key talking point:** "WhatsApp Business automates messages. Maxy understands conversations and acts on them."
+
+## vs Hiring Staff / Virtual Assistants
+
+| Dimension | Human VA / Staff | Maxy |
+|-----------|-----------------|------|
+| Availability | Business hours (or expensive 24/7) | Always on, 24/7 |
+| Cost | £1,500-3,000+/month for a good VA | From £20/month |
+| Consistency | Variable, depends on the person | Consistent, learns and improves |
+| Privacy | Trusting a stranger with personal info | Data stays in your home, no human access |
+| Scale | One person, limited bandwidth | Handles everything simultaneously |
+| Ramp-up | Weeks to months to train | Minutes to set up, learns continuously |
+
+**Key talking point:** "A good VA costs £2,000/month and still can't be available at 3am. Maxy costs £20/month and never sleeps."
+
+## Positioning Principles
+
+1. **Never disparage.** Present Maxy's strengths. Let the prospect draw comparisons.
+2. **Lead with their criteria.** Ask what matters to them, then position against those criteria.
+3. **Be honest about limitations.** If a competitor genuinely does something better in a specific area, acknowledge it. Honesty builds trust.
+4. **The real competitor is inertia.** Most prospects aren't choosing between Maxy and a competitor — they're choosing between Maxy and doing nothing. Position against the status quo.
+5. **Use the "Two Options" framing.** "You can keep juggling twelve apps, or you can let Maxy handle it. Which sounds better?"

package/payload/platform/plugins/sales/references/competitive-positioning.md

@@ -0,0 +1,51 @@
+# Competitive Positioning
+
+## The Golden Rule: Never Disparage
+
+Never badmouth a competitor. It makes you look insecure, unprofessional, and untrustworthy. If the prospect wanted the competitor, they'd be talking to them — they're talking to you because something brought them here.
+
+## The Cheapest-vs-Best Principle
+
+> "The cheapest option and the best option are generally not the same thing."
+
+This is a universal truth that prospects intuitively understand. Use it as a principle, not an attack:
+
+> "There will always be something cheaper. The question is: will it deliver the same result? In my experience, the cheaper options are usually the ones that cut corners when it matters most."
+
+## Differentiation Without Comparison
+
+Instead of comparing features with competitors, focus on what makes Maxy different in terms the prospect cares about:
+
+1. **Ask what matters:** "What's most important to you in choosing a solution?"
+2. **Position on their criteria:** Use their answer to highlight Maxy's strengths
+3. **Let them draw the comparison:** "Based on what you've told me matters, here's how we approach that..."
+
+The prospect does the comparing. You just present your strengths against their stated criteria.
+
+## Handling "I'm Also Looking at [Competitor]"
+
+1. **Don't panic.** This is normal — they're doing due diligence.
+2. **Acknowledge:** "That makes sense — it's smart to look at options."
+3. **Ask, don't argue:** "What's drawing you to them?" — their answer tells you what to sell.
+4. **Position on genuine differentiators:** Only mention things that are genuinely different, not marginally better.
+5. **If they ask you to compare directly:** "I can only speak to what we do well — I'd rather show you than tell you about someone else."
+
+## Maxy's Core Differentiators
+
+When positioning against alternatives, these are the genuine differentiators:
+
+- **Local-first:** Data stays in the home. No cloud storage of personal information. This is unique among consumer AI assistants.
+- **Proactive, not reactive:** Maxy reaches out to you. It doesn't wait for you to open an app.
+- **Cross-channel:** One brain across WhatsApp, voice, web, and smart home. Not siloed apps.
+- **Family-aware:** Designed for households, not just individuals. Shared context with individual privacy.
+- **Skill-based:** Pay for what you use. Not a monolithic subscription with features you'll never touch.
+- **Agentic:** Maxy takes action (books, sends, reminds, manages) — not just answers questions.
+
+## When They've Already Chosen the Competitor
+
+Handle it gracefully:
+1. "I appreciate you letting me know — I hope it works out well."
+2. "If things don't go as planned, I'm always here."
+3. Record it in memory — they may come back, and when they do, you'll have context.
+
+Graceful losses often become future wins. The prospect remembers how you handled the rejection.