Everything you need to master Clarion

Once your signals are processed, go to What to Build? in the sidebar. Type a question like “What should we build next?” and Clarion returns ranked, evidence-backed recommendations with customer quotes, revenue impact, and confidence levels.

The complete flow from customer voice to shipped code:

• Ingest — Signals arrive via CSV, webhook, or integration sync.
• Process — Clarion AI automatically classifies, extracts themes, scores sentiment, computes importance, and generates vector embeddings.
• Synthesize — The AI engine clusters related insights into opportunities and scores them with PM frameworks.
• Decide — The “What to Build?” engine recommends priorities. The Knowledge Explorer lets you ask questions against your entire dataset.
• Specify — Spec Studio generates PRDs and machine specs with agent artifacts (.cursorrules, tasks.json, test scenarios, agents.md).
• Ship — Agent Bridge exposes specs via MCP, pushes artifacts to GitHub, and exports to Jira/Linear.
• Measure — Feature-opportunity linking tracks outcomes, the learning system calibrates future recommendations, and the executive dashboard reports ROI.

1. 1

   Welcome & Overview

   A quick product tour showing Clarion’s core value proposition — how signals become insights, opportunities, specifications, and shipped features. Includes an animated walkthrough of the complete data pipeline.
2. 2

   Connect Your Data

   Choose how to get signals into Clarion: CSV Upload (quickest — drag and drop a file), Zendesk/Intercom/Gong (live integrations), or API/Webhook (custom pipelines). You can connect multiple sources.
3. 3

   Set Up Product Hierarchy

   Define your product structure: create products, add feature areas, and map your team’s vocabulary. This hierarchy powers AI classification — signals auto-route to the right product area. You can also skip this step and let the AI suggest a hierarchy after processing your first signals.
4. 4

   Interactive Tour

   A spotlight-based guided tour that highlights each section of the interface — sidebar navigation, signal feed, intelligence dashboard, and AI chat. Clickable hotspots explain each feature in context. Dismiss at any time; replay from Settings → General.

After the wizard, the Dashboard shows a persistent Getting Started Checklist with progress tracking. Items include: connect your first integration, import 50+ signals, review AI insights, explore an opportunity, generate your first spec, and invite a teammate. Items auto-complete as you perform each action. Dismiss the checklist once you’re comfortable.

The top of the dashboard shows four metric cards:

A visual heatmap showing which product areas are receiving the most feedback. Color intensity indicates signal volume; hover for sentiment breakdown.

Buttons for the most common tasks: Import Signals, Ask AI, Create Opportunity, and Generate Spec. New users also see the Onboarding Wizard — a guided 5-step checklist (connect integration, import data, review insights, explore opportunities, generate first spec).

The top row shows high-level metrics with trend arrows (up/down/flat compared to the previous period): total signals ingested, average sentiment score, unique customers reporting, and top emerging themes. Each card is clickable and drills down into the relevant detail page.

AI-detected anomalies and risks appear here: churn risk clusters, negative sentiment spikes, competitor mention surges, and unresolved high-priority opportunities. Each alert links to the relevant detail page for deeper investigation.

Top customers ranked by ARR with their satisfaction trajectory. Segment-level sentiment comparison. Identify at-risk accounts before they churn.

Recent team actions: specs created, opportunities moved, signals reviewed, insights shared. Helps leaders understand team engagement and workload distribution.

The highest-priority opportunities with their evidence strength, customer count, and ARR impact. One-click to open any opportunity or generate a spec directly from the executive view.

1. 1

   Paste Your PRD

   Navigate to /translate (or click “Spec Translator” on the landing page). Paste any product requirements document, user story, or feature brief into the editor. Supports plain text, markdown, and rich text.
2. 2

   AI Translation

   Click “Translate to Machine Spec”. The AI produces a SPEC.md — every vague requirement is quantified: “fast” becomes “< 200ms p95”, “responsive” becomes specific breakpoints, “secure” becomes OWASP compliance requirements.
3. 3

   Download & Use

   Copy the generated SPEC.md or download it. Drop it into your project directory and point Cursor, Claude Code, or Bolt at it — the coding agent knows exactly what to build, with testable acceptance criteria for every requirement.

The main Signals page shows a real-time feed of all ingested signals. Each card displays the source icon, customer name, content preview, category badge, sentiment indicator, and timestamp.

Click any signal to see the full raw content, AI-extracted metadata (category, themes, sentiment, urgency, emotions, key quote), customer information, and links to derived opportunities or insights.

Every signal contains these core fields:

CSV Import — Go to Signals → Import CSV for the multi-step import wizard. Upload, map columns, preview, and confirm. Your CSV should have a header row — Clarion recognizes these column names (case-insensitive):

title,rawContent,customerName,customerEmail,customerCompany,customerArr
"Need dark mode","Our entire team works late and the bright UI is painful","Jane Smith","jane@acme.com","Acme Corp",120000
"API rate limiting","Getting 429s when syncing more than 100 records","Bob Lee","bob@widgets.io","Widgets Inc",45000

Integrations (Live Sync) — Connect third-party platforms for continuous signal ingestion. Navigate to Settings → Integrations to configure:

Webhook & API — Create custom webhook endpoints to receive signals from any external system.

1. 1

   Create a Webhook

   Navigate to Settings → Webhooks. Give it a name (e.g., “Typeform Feedback”) and optionally restrict accepted source types. Clarion generates a unique URL and a signing secret.
2. 2

   Configure Your Source

   Point your external system to the generated URL. Include the signing secret as an X-Webhook-Secret header for HMAC verification.
3. 3

   Send Signals

   POST a JSON payload matching the signal schema. Clarion validates, enqueues, and processes each signal automatically.

{
  "title": "Feature request from Typeform",
  "rawContent": "I wish I could export reports as PDF...",
  "sourceType": "webhook",
  "customerName": "Alice Chen",
  "customerEmail": "alice@example.com",
  "sourceMetadata": {
    "formId": "abc123",
    "submittedAt": "2026-02-15T10:30:00Z"
  }
}

If classification results seem off — or after you’ve corrected enough items in the Review Queue for the system to learn — you can trigger Reprocessing on individual signals or in bulk. This re-runs the AI pipeline (classification, theme extraction, sentiment) on selected signals with the latest model context. Access via the signal detail page’s “Reprocess” button or through the bulk actions toolbar.

Every signal that enters Clarion goes through a multi-stage AI pipeline:

1. 1

   Classification

   AI assigns the signal to one of six categories. A confidence score (0–1) is attached; low-confidence items go to the review queue.

1. 2

   Theme & Entity Extraction

   1–3 theme labels are extracted (e.g., “Dashboard Performance”, “Export Functionality”). Products, features, and competitor mentions are identified. A key representative quote is selected.
2. 3

   Sentiment & Urgency Scoring

   Sentiment ranges from −1 (very negative) to +1 (very positive). Urgency from 1 (informational) to 5 (critical/blocking). Emotions are tagged (frustration, excitement, confusion, etc.).
3. 4

   Importance Scoring

   Signals are scored 1–10 for importance based on urgency, customer ARR, frequency of similar requests, and business impact. Importance scores feed into opportunity prioritization and the “What to Build?” engine.
4. 5

   Vector Embeddings and Indexing for Semantic Search

   Clarion AI generates high-dimensional vector embeddings for every signal and insight. These embeddings power semantic search — search by meaning, not just keywords. Vectors are indexed for sub-millisecond retrieval. This powers the Knowledge Explorer, “What to Build?” recommendations, and opportunity clustering.

The Insights page shows the output of the Intelligence Engine in visual form:

Click any theme from the Insights dashboard to open its detail page. You’ll see a sentiment breakdown for that theme (positive/neutral/negative split), segment distribution (which customer groups care most), revenue impact (total ARR of customers mentioning this theme), a 30-day trend chart, and a scrollable list of all linked signals. Use this to go deep on any specific product concern.

When the system detects an anomaly, click to see its detail page. Anomaly types include volume spikes (sudden surge in a theme), sentiment drops (sharp negative shift), and new theme emergence (a previously unseen pattern). Each anomaly shows the triggering data, comparison against historical baselines, affected signals, and suggested investigation actions.

When the AI classifies a signal with confidence below 70%, it lands in the Review Queue (accessible from the Insights page). Each item shows the signal content, the AI’s proposed classification, and its confidence. You can confirm or override the category — corrections train the system over time.

Navigate to Knowledge Explorer in the sidebar. You’ll see a full-screen chat interface. Type any question in the input area at the bottom:

• Natural language queries — “What are our top-requested features this quarter?” “How do enterprise customers feel about our API?” “Which competitors offer real-time sync?”
• Multi-entity search — Semantic search across signals, insights, opportunities, specs, and competitors simultaneously. Results are ranked by relevance.
• Context-aware responses — The AI is aware of your org’s product hierarchy, customer segments, opportunity scores, and competitive landscape.
• Rich responses — AI responses include inline data tables for comparisons, mini charts for trends, clickable customer names (navigate to customer view), and citation markers linking to source signals. The system always cites specific data — “23 customers mentioned this” rather than “several customers.”
• Charts and visualizations — The AI can generate opportunity comparison charts and data visualizations inline in the conversation.
• Conversation history — Conversations are saved automatically. Recent chats appear in the sidebar panel so you can revisit or continue previous explorations. You can also share conversation links with teammates.

Navigate to Competitors in the sidebar. A grid of competitor cards shows each competitor’s logo, name, mention count, and average sentiment. Click Add Competitor to register a new one — enter the name and website; AI auto-scrapes for a description.

Click any competitor to see the detail page with four sections:

Each completed research report opens in a structured viewer with an executive summary, detailed findings with comparison tables, SWOT analysis, signal correlations (linking competitive insights back to your customer data), and recommended actions. Reports can be shared with teammates or exported.

Whenever a new signal mentions a known competitor, Clarion automatically creates a CompetitorMention record, classifies the mention type (switching_to, compared_to, came_from, feature_gap), and feeds the data into “What to Build?” recommendations and spec generation context.

The AI continuously monitors incoming signals and identifies when the taxonomy needs updating. Navigate to Taxonomy in the sidebar to view the current category tree. Each node shows its name, signal count badge, and sentiment indicator. Click any node to open the Taxonomy Node Detail page — see the breadcrumb path, child nodes, all linked signals, and a 30-day trend chart showing signal volume for that category. A sunburst visualization provides an alternative hierarchical view where ring segments represent category depth and size indicates signal volume.

The taxonomy supports up to 5 levels of nesting. Visualize your taxonomy as an interactive tree or treemap view. The tree view shows parent-child relationships and signal counts at each level.

MERGE, SPLIT, and ARCHIVE proposals enter a review queue. Team members can approve, reject, or modify proposals before they take effect. CREATE proposals are auto-applied since they add new categories without affecting existing data.

Navigate to Segments in the sidebar. Select two or more segments to compare (e.g., Enterprise vs. SMB, or North America vs. EMEA). The comparison view shows:

• Sentiment comparison per segment
• Top themes for each segment, ranked by frequency
• Category breakdown (feature requests vs. bugs vs. churn risk)
• Revenue impact (total ARR) for each segment’s signals
• Unique themes that appear in one segment but not the other

• What to Build — Filter recommendations by segment.
• Knowledge Explorer — Ask segment-specific questions (e.g., “What do enterprise customers want?”).
• Signal Feed — Filter the feed by segment to focus on specific customer cohorts.
• Digest Reports — Segment-aware digest summaries.

• Volume spikes — Sudden increase in signal volume for a specific category or theme, detected using statistical analysis.
• Sentiment drops — Statistically significant decline in customer sentiment across a theme or customer segment.
• New themes — Emergence of previously unseen topics in customer feedback — potential early indicators of new needs or problems.

• In-app — Bell icon notifications with badge count. Click to see anomaly details.
• Email — Real-time email alerts to your inbox.
• Slack — Slack notifications with anomaly summary and link to details.

Each anomaly has a dedicated detail page showing the underlying data: the signals that triggered the anomaly, historical baseline comparison, affected customers, and suggested actions.

The Opportunities page shows a drag-and-drop Kanban board with five columns:

Toggle between Board, List, and Table views using the top bar. Filter by status, product area, priority range, owner, and date.

Each card on the board shows: title, priority score badge, signal count, customer count, ARR impact, owner avatar, and a category color stripe. Drag cards between columns to update status; drag within a column to reorder.

Click an opportunity to open its detail page with four tabs:

Each opportunity receives an AI-calculated priority score (0–100) based on five weighted factors:

• Evidence synthesis: The engine aggregates signals by theme, weighs them by customer ARR, importance score, and recency, and clusters them into opportunity candidates.
• Framework scoring: Each opportunity is automatically scored using your chosen PM framework — RICE, ICE, MoSCoW, or Value-Effort. Scores are derived from real signal data, not manual estimates.
• Recommendation generation: Clarion AI Pro synthesizes the top-scored opportunities into a ranked list with reasoning, trade-offs, and suggested next steps.
• Learning system: As you ship features and measure outcomes, Clarion AI adjusts future recommendations based on historical accuracy.

Navigate to What to Build? in the sidebar. You’ll see a spacious chat interface with suggested starter questions: “What should we build next?”, “What features would reduce churn?”, “What are enterprise customers asking for?”, and “What’s our biggest competitive gap?”

Type your question and press Enter. Clarion streams the response in real-time, first showing a thinking indicator (“Analyzing X signals...”), then rendering structured recommendation cards. The chat is context-aware — it knows your signals, insights, opportunities, and competitive landscape.

Follow up with questions like “Tell me more about recommendation #2” or “Which customers are most affected?” The AI maintains conversation context for coherent, deep-dive analysis.

Each recommendation includes:

Every response includes a data quality note at the bottom: “Based on 342 signals from 89 customers (Jan–Feb 2026)”. If data is insufficient, the AI says so clearly — it never fabricates evidence.

Each opportunity is automatically scored using your chosen PM framework. Scores are auto-derived from signal data — not manual estimates:

Reach comes from customer count and ARR, Impact from sentiment and importance scores, Confidence from signal volume, and Effort from complexity indicators in the feedback. Switch frameworks any time from the Opportunity Board settings.

Filter recommendations by customer segment to see what different cohorts want. “What should we build for Enterprise customers?” vs. “What do SMB users need most?” Segment-aware analysis prevents one-size-fits-all roadmaps.

1. 1

   Select an Opportunity

   Navigate to Opportunity Validation in the sidebar. Click “New Campaign” and select the opportunity to validate.
2. 2

   Design the Survey

   Define 3–5 quick questions: problem severity, willingness to pay, feature importance ranking. Clarion suggests questions based on opportunity data.
3. 3

   Target Audience

   Choose which customers to survey — all who submitted signals for this opportunity, a specific segment, or a custom list.
4. 4

   Review Results

   Responses roll in with a confidence score — a statistical measure of how validated the opportunity is. High confidence means strong product-market signal.

The survey builder supports five question types for maximum flexibility:

Choose how to reach participants: Email Only (send survey link via email), Email + Survey (inline questions in the email body), or High-Touch (for phone/video calls — manually log responses after conversations).

Select participants from: all customers who submitted signals for this opportunity, a specific segment, or upload a custom list. The AI can also recommend participants based on who has the most relevant signal history and engagement patterns.

Survey recipients receive a branded link (/validate/[slug]) that opens a clean, public micro-survey page. The survey displays your organization’s logo and brand color (configured in Settings → Branding), presents questions one by one, supports concept images for visual validation, and ends with a customizable thank-you page. No login required for respondents.

Campaigns move through six stages: Draft → Review → Scheduled → Active → Analyzing → Completed. At completion, the AI generates a Validation Report with a recommendation: Proceed, Proceed with Changes, Pivot, Kill, or Needs More Data — each with a confidence percentage and supporting rationale.

Navigate to Spec Studio in the sidebar. The list page shows all specifications as a table or card view, with columns for title, linked opportunity, status, version, author, and last updated date. Click “Generate New Spec” to begin.

There are two ways to create a spec:

• From an Opportunity (Essentials, Pro, Enterprise) — Select an opportunity and Clarion generates a PRD pre-filled with evidence from linked signals — customer quotes, pain points, and quantitative data.
• Standalone (Free, Essentials, Pro, Enterprise) — Paste existing PRD text or describe a feature — Clarion structures it into the full PRD format. Free users get Clarion AI; Pro users get Clarion AI Pro for higher quality output.

Every PRD is editable with a rich text editor. The editor supports:

• Structured sections — Problem Statement, Goals, User Stories, Requirements, Success Metrics, Risks, Timeline, and more.
• Inline editing with formatting toolbar (bold, italic, lists, headings, links).
• Auto-save every 30 seconds with visual save indicator.
• Version history — revert to any previous version.

Specs auto-save every 30 seconds. Click “Save Version” to create a named checkpoint with an optional change note. The version history panel shows all versions with timestamps — click any to see a diff against the current spec. You can restore any previous version.

Click “Generate Machine Spec” to translate the PRD into a structured, machine-verifiable specification. Progress is shown in real-time with a phase timeline. If generation is interrupted, it automatically resumes from where it left off.

The machine spec includes:

• Functional requirements — Detailed specifications with acceptance criteria in Given/When/Then format.
• API contracts — Endpoint definitions, request/response schemas, error codes, and authentication requirements.
• Data models — Database schema changes, field types, constraints, and relationships.
• Test scenarios — Comprehensive test cases covering happy paths, edge cases, error handling, and performance criteria.
• Non-functional requirements — Performance targets, security requirements, accessibility standards.

After generating a machine spec, you can generate five agent artifacts optimized for AI coding assistants:

Download individually or as a ZIP bundle. Preview each artifact before downloading.

From the spec editor, use the “Export for Agents” dropdown to generate and download:

Push generated artifacts directly to a GitHub repository. Clarion creates a new branch, commits all artifact files, and opens a pull request. When the PR is merged, Clarion automatically detects the shipped feature and updates the linked opportunity status.

Specs are validated for completeness and consistency. The validator checks for missing acceptance criteria, undefined API contracts, inconsistent data models, and untested edge cases. Validation results are shown as warnings that you can address before generating artifacts.

Navigate to Settings → Workflows to configure your approval pipeline. The workflow visual editor lets you design approval pipelines by dragging and connecting stages. Preview the flow before activating it for your organization. The editor lets you:

From the Spec Studio editor, click “Submit for Approval”. The spec enters the approval pipeline and reviewers are notified. An approval progress bar shows which stages are complete and who’s pending.

Navigate to Specs → Pending Approvals to see all specs awaiting your review. For each spec, you can: Approve (advance to next stage), Request Changes (send back with comments), or Send Reminder (nudge the assigned reviewer). Comments thread below each spec for reviewer discussion.

Clarion exposes a Model Context Protocol (MCP) server that any MCP-compatible client can connect to. The server provides seven tools:

MCP requests are authenticated with API keys. Generate a key in Settings → API Keys. Include it as a Bearer token:

{
  "mcpServers": {
    "clarion": {
      "url": "https://getclarion.in/api/v1/mcp",
      "headers": {
        "Authorization": "Bearer your-api-key-here"
      }
    }
  }
}

The Agent Bridge page in Clarion provides a visual interface for managing MCP connections, testing tool calls, and monitoring agent activity. You can see which specs agents are currently reading and track tool call history.

1. 1

   Generate API Key

   Create a dedicated API key for MCP use in Settings → API Keys. This key maps to your organization and controls which data the agent can access.
2. 2

   Copy Configuration

   Clarion provides ready-to-paste configuration snippets for Cursor (add to .cursor/mcp.json), Claude Desktop (add to claude_desktop_config.json), Claude Code (add to MCP settings), and Bolt.new.
3. 3

   Test Connection

   Use the “Test Connection” button to verify that the MCP server starts, registers all tools, and can return data.

The Agent Bridge page shows recent MCP calls — which tools were invoked, when, by which client, and the response times. Monitor how your coding agents are leveraging Clarion’s intelligence.

Navigate to Feature Impact in the sidebar. The page lists all tracked features with their name, status (planned, in development, shipped), linked opportunity, ship date, and impact metrics.

When you ship a feature, link it to the opportunity it addresses. This closes the loop — you can now see which customer requests were fulfilled and measure whether the investment was worthwhile.

If GitHub is connected, feature status automatically updates based on PR lifecycle:

The Outcomes page connects shipped features to their predicted success metrics from the original PRD. For each feature, you can track:

1. 1

   Signal → Insight

   A customer says “I wish I could export reports as PDF.” The AI classifies this as a Feature Request, extracts the “Export” theme, and links it to other similar signals.
2. 2

   Insight → Opportunity

   When 3+ signals cluster around the same need, an Opportunity like “PDF Export Functionality” is created with a priority score based on customer count, ARR, and sentiment.
3. 3

   Opportunity → Specification

   You generate a PRD and Machine Spec from the opportunity. The spec includes direct customer quotes as evidence for each requirement. Push to GitHub with all coding artifacts.
4. 4

   Specification → Feature

   When the linked GitHub PR is merged, the Feature status updates to “Shipped” automatically. The opportunity moves to the “Shipped” column.
5. 5

   Feature → Outcome

   Measure whether the feature achieved its goals — did support tickets decrease? Did NPS improve? The learning system records the outcome and improves future recommendations.

On the Feature Detail page, the Traceability Chain visualization shows this entire journey as an interactive flow diagram. Click any node to navigate to that entity. This is what makes Clarion unique — you can always answer “why did we build this?” with evidence.

Clarion uses role-based access control (RBAC) to manage permissions within your organization.

Invite team members from Settings → Team. Each invitation specifies a role. For Pro plans, you can optionally assign a Pro seat to the invited member (giving them access to Pro features). Invitations are delivered via email and expire after 7 days.

You can also create shareable invite links for bulk onboarding. Invite links can be configured with a maximum number of uses and an expiration date.

Organization name, logo, default timezone, and global preferences. Configure the product hierarchy (Product → Areas → Features) that’s used by all AI operations for accurate signal classification.

Invite team members by email. Four role levels:

Connect and manage all third-party integrations from Settings → Integrations. Each integration shows its connection status, last sync time, and signal count.

Navigate to Settings → API Keys to generate keys for programmatic access and MCP server authentication. Each key is shown once on creation (copy immediately), with a name, creation date, last used timestamp, and a revoke button. Keys are scoped to your organization.

Define your product structure as a multi-level hierarchy — from top-level product areas down to individual features: Product → Areas → Features → Sub-features. The hierarchy uses a drag-and-drop tree editor. Each node displays its signal count badge, aggregated sentiment, and auto-mapped signals. This hierarchy feeds into every AI operation — classification maps signals to product areas, themes roll up to the hierarchy, and specs reference specific product areas for context. Reorder by dragging; add children by clicking the “+” button on any node. Clarion automatically maps incoming signals to 1–3 relevant product areas using AI, enabling per-area analytics and filtering.

• Tree management — Add, edit, reorder, and nest product areas up to 5 levels deep.
• Signal mapping — Each signal is automatically assigned to relevant product areas during processing. The AI reads signal content and matches it against your hierarchy.
• Aggregated metrics — View signal counts, sentiment averages, and opportunity counts per product area — with automatic rollup from children to parent nodes.
• Tree visualization — Interactive tree view with expand/collapse, drag-and-drop reordering, and color-coded health indicators.

Navigate to Settings → Segments to create and manage customer segments. Define segments with rule-based criteria:

• ARR range — e.g., Enterprise (>$100K ARR), Mid-market ($10K–$100K), SMB (<$10K).
• Company size — filter by employee count or organization tier.
• Custom attributes — any metadata from your signal sources (plan type, region, industry, etc.).

Each segment shows a live match count — the number of customers that meet the criteria. Segments power the Segment Comparison page, filter “What to Build?” recommendations, scope Knowledge Explorer queries, and shape every AI analysis across the platform.

Navigate to Settings → Branding to customize your organization’s appearance in outbound communications. Upload your company logo and set a primary brand color. These appear on validation survey pages, digest emails, and shared reports — giving a professional, white-labeled experience to customers and stakeholders.

Navigate to Settings → Workflows to configure multi-stage approval processes (see the Approval Workflows section for full details). The visual drag-and-drop editor lets you define stages, assign roles, configure parallel branches, and set auto-escalation rules.

Navigate to Settings → Notifications to configure how you receive alerts. Two delivery channels: Email and Slack webhook. Toggle notifications for: new high-priority signals, anomaly alerts, spec status changes, approval requests, and team activity. Set a Slack webhook URL to receive notifications in your team channel.

Scheduled summary reports delivered via email or Slack. Digests keep stakeholders informed without requiring them to log in.

Navigate to Settings → Digests to configure automated summary emails. Each team member can set their own schedule and delivery method independently. Choose frequency (Daily, Weekly, or Monthly), set your timezone, and toggle which sections appear: Signal Summary, Highlights, Anomaly Alerts, New Opportunities, Sentiment Trends, and AI Recommendations. Use “Send Test” to preview the email. View digest history to see what was sent.

Configuration

• Frequency — Daily, weekly, or monthly.
• Delivery — Email or Slack.
• Timezone — Reports are generated at the configured time in the user’s timezone.
• Content — AI-generated highlights summarizing new signals, emerging themes, sentiment shifts, and top opportunities since the last digest.

Navigate to Settings → Login Activity to view your login history — timestamps, IP addresses, device info, and success/failure status. Filter by date range and status. Useful for security auditing and detecting unauthorized access attempts.

Navigate to Settings → Profile (or click your avatar in the top-right corner). You can update your display name, email address, and upload a profile avatar. Your avatar appears on signals you create, specs you author, opportunity cards you own, and in the team activity feed.

Change your password from the profile page. If you signed up with Google OAuth, you can optionally add a password for email/password login. You can also link additional OAuth providers to your account for flexible sign-in options.

If you belong to multiple organizations, click the organization name in the sidebar dropdown to switch between them. Each organization has its own data, team, plan, and settings — switching is instant with no logout required.

Payments are processed securely. We accept all major credit/debit cards, UPI, and net banking. Billing is monthly or annual (annual saves 20%). Manage your subscription, download invoices, and update payment methods in Settings → Billing.

If you have a coupon code, enter it on the checkout page before completing payment. Coupons can provide a percentage discount or grant free access for a specific plan. Coupon codes are created by platform administrators and may have expiration dates or usage limits.

Enterprise plans include custom seat counts, dedicated support, SLA guarantees, custom integrations, and advanced security features. Contact sales to discuss your requirements.

The admin home page shows key platform metrics: total organizations, total users, Pro subscribers, monthly recurring revenue (MRR), recent signups, and billing events. Sparkline charts show trends over the last 30 days.

Navigate to Admin → Users to see a searchable, sortable table of all platform users: name, email, role, subscription tier, Pro seat status, last login timestamp, and organization count. Admins can edit user details or deactivate accounts.

Navigate to Admin → Organizations to see all organizations: name, plan, Pro seats used vs. allocated, member count, and total signal count. Click any organization for detailed management options.

Navigate to Admin → Coupons to create and manage promotional coupon codes. Create coupons with a code, discount percentage or fixed amount, expiration date, and maximum usage count. Toggle coupons active/inactive. View redemption history for each coupon. Users redeem coupons during checkout on the billing page.

Navigate to Admin → Login Activity to see a platform-wide login log. Paginated for large datasets. Filter by date range, success/failure status, and search by email. Monitor for suspicious login patterns or brute-force attempts.

Monitor LLM API spending across the platform. Track costs by organization, model (Clarion AI vs. Clarion AI Pro), and operation type (classification, spec generation, knowledge chat). Identify high-usage organizations and optimize AI spend.

Navigate to Admin → Test Mode to access the seed control panel. Generate demo data for testing: sample signals, opportunities, specs, and features. Useful for onboarding demos, sales presentations, and development environments.

From the Executive Dashboard, click “Share” to generate a shareable report link. Choose which sections to include: executive summary, top opportunities, risk alerts, team activity, sentiment trends, and feature velocity. Set an expiration date (7 days, 30 days, or never). The generated URL looks like /reports/[token] and works for anyone with the link.

Reports show your organization’s branding (logo and colors) and include a Clarion watermark. Viewers see a read-only interface with no ability to modify data.