@adminide-stack/yantra-help-browser 12.0.16-alpha.20 → 12.0.16-alpha.21

package/lib/templates/content/solutions-sales/crm-automation.md

@@ -0,0 +1,119 @@
+---
+title: 'CRM Automation'
+---
+
+# CRM Automation
+
+Yantra's AI employee keeps your CRM perpetually up to date by automatically logging interactions, updating deal stages, and synchronizing data across your sales tools.
+
+## Why CRM Data Goes Stale
+
+The root cause of inaccurate CRM data is friction: manual data entry competes with the primary job of selling. When salespeople are busy, CRM updates are the first casualty. This creates:
+
+- **Inaccurate pipelines**: Deal stages don't reflect reality
+- **Lost context**: Call notes are incomplete or missing
+- **Forecasting failures**: Leadership decisions based on stale data
+- **Onboarding difficulties**: New reps can't trust existing records
+
+## How Yantra Automates CRM Management
+
+### Interaction Logging
+
+Every customer interaction is automatically captured and logged:
+
+**Email Conversations**:
+
+- AI employee reads email threads (with your permission) and extracts key points
+- Logs the interaction in CRM with a structured summary
+- Tags the email with appropriate deal and contact associations
+
+**Call Notes**:
+
+- For Zoom calls: Automatic transcription and summary extraction
+- Key decisions, objections, next steps, and commitments are identified
+- Structured notes logged in CRM immediately after the call
+
+**Slack Mentions**:
+
+- When deals or customers are discussed in Slack, relevant context is captured
+- Internal team discussions about prospects are linked to the CRM record
+- Competitive intelligence mentioned in conversations is flagged
+
+### Deal Stage Management
+
+Your AI employee monitors interactions and automatically updates deal stages:
+
+| Signal                      | CRM Action               |
+| --------------------------- | ------------------------ |
+| Demo scheduled via Calendly | Move to "Demo Scheduled" |
+| Pricing discussed in email  | Move to "Negotiation"    |
+| Contract sent via email     | Move to "Contract Sent"  |
+| Signed document received    | Move to "Closed Won"     |
+| No response after 30 days   | Flag as "At Risk"        |
+
+Stage transitions are based on configurable rules you define. In supervised mode, you approve each transition before it's written to CRM.
+
+### Contact Enrichment
+
+As your AI employee processes interactions, it enriches contact records:
+
+- Job titles and roles mentioned in conversations
+- Organizational hierarchy inferred from email threads
+- Decision-maker identification based on purchasing discussions
+- Communication preferences and best contact methods
+
+### Activity Timeline
+
+Your CRM's activity timeline becomes comprehensive and trustworthy:
+
+- Every email exchange summarized and logged
+- All call notes with key points highlighted
+- Meeting outcomes and next steps documented
+- Internal team discussions linked to the deal
+
+## Pipeline Accuracy
+
+With automated CRM updates, pipeline metrics become reliable:
+
+### Before Yantra
+
+- Deal stages reflect when someone last remembered to update
+- Activity logs are incomplete
+- Forecasting requires significant manual adjustment
+- Stale deals remain in pipeline indefinitely
+
+### With Yantra
+
+- Deal stages update in real time based on actual interactions
+- Complete activity history for every deal
+- Forecasting based on accurate, timely data
+- Stale deals automatically flagged and managed
+
+## Configuration
+
+### Auto-Update Rules
+
+Define which signals trigger CRM updates:
+
+- Email keywords that indicate stage changes
+- Calendar events that should move deals forward
+- Inactivity periods that flag deals as at-risk
+- Custom rules based on your sales process
+
+### Field Mapping
+
+Configure which CRM fields get updated:
+
+- Deal stage transitions
+- Revenue and deal size fields
+- Close date adjustments
+- Custom fields specific to your process
+
+### Approval Workflow
+
+In supervised mode:
+
+1. AI employee proposes a CRM update with reasoning
+2. You review the proposed change and supporting evidence
+3. Approve, modify, or reject the update
+4. AI employee learns from your decisions to improve accuracy

package/lib/templates/content/solutions-sales/lead-management.md

@@ -0,0 +1,108 @@
+# Lead Management and Follow-Up
+
+Yantra's AI employee ensures 100% follow-up coverage on every lead in your pipeline — no more missed opportunities due to forgotten tasks or overloaded schedules.
+
+## The Follow-Up Gap
+
+Research consistently shows that most sales are lost not due to poor pitches, but due to inadequate follow-up:
+
+- Prospects require 5-12 touchpoints before making a decision
+- Most salespeople give up after 2-3 attempts
+- The ideal follow-up window is within 24 hours, but compliance rates are low
+- Manual task management breaks down as pipeline size grows
+
+## How Yantra Manages Lead Follow-Up
+
+### Automated Follow-Up Tracking
+
+Your AI employee maintains a real-time follow-up schedule for every active lead:
+
+- **Interaction monitoring**: Tracks the last touchpoint for each lead across all channels
+- **Cadence enforcement**: Ensures follow-up intervals match your defined cadence
+- **Smart timing**: Recommends optimal follow-up times based on past engagement patterns
+- **Escalation**: Flags leads approaching critical follow-up deadlines
+
+### Personalized Draft Messages
+
+When a follow-up is due, your AI employee drafts a personalized message using:
+
+- Summary of the last interaction and key discussion points
+- Any commitments or deliverables that were promised
+- Relevant company news or product updates since the last contact
+- Contextual references that demonstrate continuity and attention
+
+You review, edit if needed, and send — or approve auto-send for routine check-ins.
+
+### Lead Scoring and Prioritization
+
+Your AI employee continuously scores and ranks leads based on:
+
+- **Engagement level**: Frequency and quality of responses
+- **Deal size**: Revenue potential
+- **Fit indicators**: How well the prospect matches your ideal customer profile
+- **Activity signals**: Website visits, email opens, content downloads
+- **Time sensitivity**: Approaching decision dates or contract renewals
+
+The daily priority list tells you exactly who to focus on and why.
+
+### Cold Lead Re-Engagement
+
+When leads go cold, your AI employee:
+
+1. Identifies the longest-inactive prospects still in pipeline
+2. Researches any new company developments or triggers
+3. Drafts re-engagement messages with relevant hooks
+4. Suggests the optimal channel (email, LinkedIn, phone)
+5. Schedules follow-ups at intervals proven to maximize response rates
+
+## Pipeline Hygiene
+
+### Stale Deal Detection
+
+- Deals with no activity beyond your defined threshold are flagged
+- AI employee suggests: close, defer, or re-engage
+- Prevents pipeline bloat that distorts forecasting
+
+### Duplicate Contact Detection
+
+- Identifies potential duplicate contacts across your CRM
+- Suggests merge candidates with supporting evidence
+- Prevents multiple team members from pursuing the same prospect
+
+### Win/Loss Pattern Analysis
+
+Over time, your AI employee identifies patterns in your pipeline:
+
+- Which deal types convert fastest
+- Common drop-off stages and reasons
+- Competitive dynamics that affect close rates
+- Messaging approaches that correlate with success
+
+## Configuration
+
+### Follow-Up Cadence Rules
+
+Define follow-up expectations by deal stage:
+
+- **New Lead**: Follow up within 24 hours, then every 3 days
+- **Discovery**: Follow up within 48 hours of meetings
+- **Negotiation**: Follow up within 24 hours of proposals
+- **Closed Won**: Onboarding check-in at 7 and 30 days
+
+### Priority Weights
+
+Adjust how leads are scored and prioritized:
+
+- Deal size weight
+- Engagement recency weight
+- Fit score weight
+- Custom criteria weights
+
+### Auto-Send Rules
+
+For semi-autonomous and autonomous modes, define which follow-ups can be sent without approval:
+
+- Routine check-in templates
+- Meeting confirmation messages
+- Thank-you notes after calls
+- Resource sharing based on expressed interests

package/lib/templates/content/solutions-sales/sales-overview.md

@@ -0,0 +1,120 @@
+# Sales Solutions Overview
+
+Yantra equips sales teams with an AI employee that eliminates administrative overhead — automatically updating CRMs, preparing call briefs, tracking follow-ups, and ensuring no lead ever falls through the cracks.
+
+## The Sales Productivity Problem
+
+Sales professionals spend a disproportionate amount of time on non-selling activities:
+
+- **Manual CRM entry**: Logging call notes, updating deal stages, and recording activities
+- **Follow-up management**: Remembering to follow up with prospects at the right time
+- **Call preparation**: Searching through CRM, email, and Slack for context before meetings
+- **Pipeline maintenance**: Keeping deal stages accurate for forecasting
+- **Data synchronization**: Ensuring information is consistent across tools
+
+These administrative tasks consume hours every day — time that should be spent building relationships and closing deals.
+
+## Key Capabilities for Sales
+
+### Automatic CRM Updates
+
+After every interaction — calls, emails, meetings — your AI employee:
+
+- Logs detailed notes in HubSpot or Salesforce
+- Updates deal stages based on conversation outcomes
+- Records action items and commitments
+- Sets appropriate follow-up dates
+- Tags contacts with relevant attributes
+
+### Call Preparation Briefs
+
+Before every scheduled call, your AI employee sends a prep brief:
+
+- Summary of all previous interactions with the prospect
+- Current deal stage and recent changes
+- Key concerns or objections raised in past conversations
+- Promises made and their fulfillment status
+- Relevant company news or changes since the last contact
+- Suggested talking points based on where the deal stands
+
+### 100% Follow-Up Coverage
+
+Your AI employee tracks every active lead and ensures follow-up:
+
+- Automatic reminders when follow-up dates approach
+- Draft personalized messages for check-ins
+- Alerts when leads go cold based on configurable inactivity thresholds
+- Prioritized lists of who to contact next, based on deal value and engagement
+
+### Pipeline Intelligence
+
+With automatically accurate CRM data, your pipeline becomes trustworthy:
+
+- Deal stages reflect reality, not what someone remembered to log
+- Forecasting accuracy improves from industry-average 60% to 90%+
+- At-risk deals are flagged before they slip
+- Win/loss patterns become visible and actionable
+
+## Real-World Scenarios
+
+### Scenario: Sales Call Ends with a Prospect
+
+**Without Yantra**:
+Great call — but now you need to open HubSpot, write up the notes before you forget, update the deal stage, set a follow-up task, and draft the recap email. You do half of it, the rest never happens.
+
+**With Yantra**:
+Your AI employee captures the call details (via Zoom transcription or your notes), updates HubSpot automatically with key points, moves the deal to the right stage, and drafts the follow-up email. You review and send.
+
+### Scenario: Lead Goes Cold
+
+**Without Yantra**:
+That promising prospect from 3 weeks ago? You forgot to follow up. They signed with a competitor.
+
+**With Yantra**:
+Your AI employee tracked the lead from day one. After 5 days of no activity, it sent you a reminder with a draft personalized check-in email. The follow-up went out on time.
+
+### Scenario: Pre-Call Scramble
+
+**Without Yantra**:
+You have a call in 10 minutes with someone you spoke to 2 months ago. You scramble through HubSpot, email, and Slack trying to piece together the context.
+
+**With Yantra**:
+Your AI employee sent you a prep brief 30 minutes before the call with a full history summary, key points from past conversations, and suggested discussion topics.
+
+### Scenario: CRM Data Rot
+
+**Without Yantra**:
+Pipeline meetings are unreliable because deal stages are weeks out of date. Forecasting is guesswork.
+
+**With Yantra**:
+Every interaction is automatically reflected in your CRM. Deal stages are always current, activity logs are complete, and your forecast is built on real data.
+
+## Sales Tool Integrations
+
+| Tool           | Capabilities                                                    |
+| -------------- | --------------------------------------------------------------- |
+| **HubSpot**    | Auto-update deals, log calls, track activities, manage contacts |
+| **Salesforce** | Sync contacts, update stages, record interactions               |
+| **Gmail**      | Track email threads, draft follow-ups, log correspondence       |
+| **Slack**      | Surface deal-related mentions, team collaboration               |
+| **Zoom**       | Transcribe calls, extract key points and action items           |
+| **Calendly**   | Prep briefs before scheduled meetings                           |
+
+## Metrics Improvement
+
+| Metric               | Before Yantra | With Yantra |
+| -------------------- | ------------- | ----------- |
+| CRM accuracy         | ~60%          | 95%+        |
+| Follow-up rate       | Variable      | 100%        |
+| Admin time per day   | 2+ hours      | Near zero   |
+| Forecast reliability | Low           | High        |
+
+## Getting Started
+
+1. Connect your sales tools via [Integrations](/help-center/integrations/integrations-overview)
+2. Select "Sales" as your AI employee type during setup
+3. Configure call preparation preferences and follow-up thresholds
+4. Start in supervised mode — review CRM updates and email drafts before they execute
+5. Expand autonomy for routine updates as trust builds
+
+For setup details, see [Getting Started with AI Employees](/help-center/ai-employees/getting-started-ai-employees).

package/lib/templates/content/use-cases/engineering-use-cases.md

@@ -0,0 +1,123 @@
+# Engineering Use Cases
+
+Detailed examples of how engineering teams leverage Yantra AI employees to accelerate debugging, preserve knowledge, and keep teams aligned.
+
+## Use Case 1: Customer Bug Report Triage
+
+### The Situation
+
+A customer posts in your #support Slack channel: _"We can't log in to the dashboard. It's been broken since this morning."_
+
+### Without Yantra
+
+1. An engineer sees the message (eventually)
+2. Opens Sentry, searches for auth-related errors
+3. Switches to Linear, looks for existing tickets
+4. Checks GitHub for recent auth-service deployments
+5. Asks around on Slack if anyone has seen this before
+6. Pieces together a theory after 45 minutes of investigation
+7. Posts a response to the customer
+
+**Time spent: 45 minutes to 2 hours**
+
+### With Yantra
+
+1. AI employee detects the report immediately
+2. Within 30 seconds, cross-references:
+    - Sentry: `AuthTokenExpired` exception spiked 47× after deploy #892 (deployed 35 min ago)
+    - Linear: Ticket #1234 exists — Marcus deployed a related fix yesterday
+    - GitHub: Deploy #892 touched `auth-service/token-handler.ts`
+    - History: Similar issue occurred on Jan 14, resolved by adjusting token cache TTL
+3. Posts a structured summary in the thread
+4. Drafts a customer response with accurate status information
+5. Suggests creating a P0 ticket and notifying Marcus
+
+**Time spent: 30 seconds for the AI employee; 2 minutes for human review and approval**
+
+## Use Case 2: 3 AM Error Spike
+
+### The Situation
+
+A code deployment rolls out at 11 PM after an engineer pushes a hotfix. By 3 AM, Sentry shows 47 new error alerts.
+
+### Without Yantra
+
+- On-call engineer wakes up to a noisy PagerDuty alert storm
+- Spends 45 minutes triaging: most alerts are variations of the same issue
+- Discovers 2 genuinely new errors buried in the noise
+- One is critical (affecting payment processing), one is minor (cosmetic UI regression)
+
+### With Yantra
+
+- AI employee correlates all 47 alerts automatically overnight
+- Groups them into 3 clusters: 44 related to the same root cause, 2 new, 1 pre-existing
+- Identifies the critical payment processing error
+- Correlates it with the 11 PM hotfix deployment
+- Sends a single, clear escalation to the on-call engineer:
+
+> _"Critical: PaymentProcessor null pointer affecting checkout since deploy #905 at 11:02 PM. 12 affected transactions. Linear ticket created (#1567). Related code change: PR #234 by Alex. Suggest rollback or hotfix."_
+
+**Result: On-call engineer deals with one actionable alert instead of 47 noisy ones**
+
+## Use Case 3: New Engineer Onboarding
+
+### The Situation
+
+A new backend engineer, Priya, joins the team and is assigned to the billing service.
+
+### Without Yantra
+
+- Priya asks her manager about the billing service architecture (30-minute conversation)
+- She reads through scattered Notion docs (some outdated)
+- She asks colleagues about specific customer configurations throughout her first two weeks
+- Each question interrupts a senior engineer for 10-15 minutes
+
+### With Yantra
+
+Day 1, Priya asks the AI employee:
+
+- _"What's the architecture of the billing service?"_ → Full technical overview with links to design docs, ADRs, and dependency diagrams
+- _"What are the known issues with billing?"_ → List of open tickets, past incidents, and recurring patterns
+- _"What's special about Customer X's billing setup?"_ → Complete history of their custom configurations, past issues, and workarounds
+- _"Who should I talk to about the payment gateway integration?"_ → Identifies Marcus as the most active contributor with links to his relevant PRs and discussions
+
+**Result: Priya is productive from day one without repeatedly interrupting senior engineers**
+
+## Use Case 4: Context Preservation After Team Changes
+
+### The Situation
+
+Sarah, a senior engineer with 3 years of context, transfers to a different team. She was the primary point of contact for several major customers and had deep knowledge of the auth system.
+
+### Without Yantra
+
+- Sarah writes a 10-page handoff document that covers maybe 30% of what she knows
+- Months later, teams discover gaps when customer-specific issues arise
+- Workarounds Sarah knew about are rediscovered the hard way
+- New team members spend hours debugging issues Sarah could have diagnosed instantly
+
+### With Yantra
+
+- Every conversation Sarah had, every fix she made, every decision she was involved in is already indexed
+- When a customer issue arises that Sarah would have known about, the AI employee surfaces relevant history
+- Architecture decisions Sarah participated in are fully documented with discussion context
+- The team operates as if Sarah's knowledge never left
+
+## Use Case 5: Code Review Context
+
+### The Situation
+
+A pull request touches a critical module that was last modified 8 months ago. The reviewer doesn't have context on why the existing code was written that way.
+
+### Without Yantra
+
+- Reviewer reads through git blame and commit messages
+- Some commits reference ticket numbers that require switching to Linear
+- The original discussion about the architecture choice happened in a Slack thread that's hard to find
+- Review takes longer than necessary due to missing context
+
+### With Yantra
+
+- Reviewer asks the AI employee: _"Why was the token refresh logic implemented this way?"_
+- AI employee surfaces: the original Slack discussion, the performance benchmarks that drove the decision, the 3 subsequent bug fixes, and the customer that triggered the original implementation
+- Review proceeds with full context in minutes

package/lib/templates/content/use-cases/marketing-use-cases.md

@@ -0,0 +1,128 @@
+# Marketing Use Cases
+
+Detailed examples of how marketing teams leverage Yantra AI employees to maintain a consistent brand presence, amplify product launches, and never miss engagement opportunities.
+
+## Use Case 1: Product Launch Amplification
+
+### The Situation
+
+Engineering just shipped a major feature: real-time collaborative dashboards.
+
+### Without Yantra
+
+- Marketing planned to write about it, but campaign work took priority
+- Five days later, someone drafts a quick LinkedIn post
+- The post gets modest engagement because the news is already stale
+- No X/Twitter thread was created
+- The blog post is still in the backlog
+
+### With Yantra
+
+- AI employee detects the release from GitHub and the #engineering Slack announcement
+- Within an hour, drafts are ready:
+    - LinkedIn post: Professional announcement highlighting customer value
+    - X/Twitter thread: 5-tweet thread breaking down the feature with visuals (copy suggested)
+    - Internal Slack update: Suggested messaging for the sales team
+- Marketing reviews and approves with minor edits
+- Posts scheduled for optimal engagement times across platforms
+
+**Result: Feature launch amplified across all channels on the same day**
+
+## Use Case 2: Consistent Social Presence
+
+### The Situation
+
+The marketing lead knows they should post 3-4 times per week on LinkedIn, but last month they managed only 2 posts total.
+
+### Without Yantra
+
+- Content ideas feel forced and require dedicated brainstorming time
+- Writing each post takes 30-60 minutes with editing and formatting
+- Scheduling is manual and often forgotten
+- The company's social presence appears inactive
+
+### With Yantra
+
+- AI employee maintains a steady content pipeline sourced from:
+    - Product updates and changelog entries
+    - Industry news relevant to the target audience
+    - Internal thought leadership ideas shared in Slack
+    - Repurposed blog content and webinar takeaways
+- Drafts are delivered for review on a consistent schedule
+- Marketing reviews, edits, and approves — taking 5-10 minutes per post
+- Posts are scheduled at peak engagement times
+
+**Result: 4 LinkedIn posts and 6 X/Twitter updates published per week with minimal effort**
+
+## Use Case 3: Real-Time Engagement Response
+
+### The Situation
+
+A well-known industry thought leader comments on one of your LinkedIn posts with a thoughtful question about your approach.
+
+### Without Yantra
+
+- The comment is noticed 2 days later during a social media check
+- The thought leader has moved on to other conversations
+- The engagement opportunity and potential relationship building are lost
+
+### With Yantra
+
+- AI employee detects the high-profile interaction within minutes
+- Sends an immediate Slack alert: _"Sarah Chen (VP Product at TechGiant, 15K followers) commented on your cloud migration post. Draft reply ready."_
+- Marketing reviews the drafted reply (contextually appropriate, professional, engaging)
+- Response posted within the hour
+
+**Result: Meaningful engagement with an influential industry voice**
+
+## Use Case 4: Competitor Launch Response
+
+### The Situation
+
+Your main competitor announces a new feature that overlaps with your core functionality.
+
+### Without Yantra
+
+- Marketing finds out from a coworker a few days later
+- Scrambles to draft a positioning response
+- The social media conversation has already moved on
+- No proactive content was created during the peak attention window
+
+### With Yantra
+
+- AI employee detects the competitor announcement through brand monitoring
+- Within 30 minutes, delivers:
+    - Summary of the competitor's announcement and market reaction
+    - Social media sentiment analysis around the announcement
+    - Draft response content: thought leadership post positioning your approach differently
+    - Suggested talking points for the sales team
+- Marketing reviews and publishes a well-crafted response while the topic is still trending
+
+**Result: Proactive competitive positioning instead of reactive scrambling**
+
+## Use Case 5: Customer Success Content
+
+### The Situation
+
+A customer shares a great result in your community Slack: _"We reduced our response time by 80% using Yantra's automation features!"_
+
+### Without Yantra
+
+- The message is seen by a few team members who react with emoji
+- Nobody follows up to ask if it can be shared publicly
+- A great testimonial opportunity is lost
+
+### With Yantra
+
+- AI employee detects the customer success signal
+- Flags it to marketing with context:
+    - Customer details: Company name, tier, industry
+    - Their usage patterns and features they've adopted
+    - Relationship history: How long they've been a customer
+- Suggests:
+    - Ask permission to share as a testimonial
+    - Draft LinkedIn post featuring their success
+    - Case study outline based on their journey
+- Marketing coordinates with the customer success team to follow up
+
+**Result: Organic customer success turned into marketing content**