SignalPlane User Guide

For the complete, end-to-end documentation, see docs/knowledge_base/user-handbook.md or visit /docs in the app.

Getting started
Navigation and workspaces
Dashboard overview
Research studio
Knowledge base manager
Analytics suite
Insights engine
Content engine
Campaigns and automation
Reports and exports
Company, organization, product, and persona management
Settings and integrations
Collaboration and governance
Video tutorials
FAQ and troubleshooting

Getting started

Sign up with your email and password (8+ characters with upper/lowercase, numbers, and symbols).
Confirm your email address using the verification link.
Verify the workspace created for you on first login.
Complete the onboarding wizard (company, organizations, Build persona funnel, products, hydration).
Connect data sources and providers in Settings.
Upload reference documents in Knowledge Base if you plan to use RAG answers.
Explore the Dashboard to confirm metrics are loading.

When onboarding completes, you are redirected to Prompt Forge to begin prompt and listening runs.

The onboarding wizard now includes a left sidebar progress tracker, refreshed form inputs, inline AI buttons that pull website content (cached for future fills) to autofill company and organization descriptions without citation markers, AI-labeled product positioning notes, company and organization competitors inputs, validation that jumps to and highlights missing fields, and the ability to return to completed steps to make edits before starting hydration.

Onboarding drafts now autosave locally every ~250 ms. Text inputs restore after refresh; PDF uploads cannot be saved locally. Avoid refreshing while documents are attached or finish the step to persist them.
If you try to leave a product step with pending uploads, the app warns you to prevent losing files.
Persona builder progress (sub-steps, topics, preview) resumes after reload. Older saved drafts may miss newly added fields, so re-check compliance topics before submitting.
Completing onboarding clears all saved drafts; to restart manually, return to onboarding and reset, or clear browser storage.
A logout button now appears in the onboarding header; it signs you out and clears any saved onboarding draft before returning you to the landing page.

The public landing page includes Pricing and Live Demo sections for plan review and walkthrough requests before signing up. Public resources are available at /about, /careers, /blog, /contact, /changelog, /legal/privacy, and /legal/terms. If you are already signed in, the landing page surfaces a Dashboard shortcut; signing out returns you to the landing page.

Use the left navigation headings (Prompt Forge, Listening Engine, Recommendations, Analytics, Settings, Docs) to switch between modules.
Expand Insights to access the Organization and Persona dashboards; the Insights heading itself is not selectable.
Insights includes a quick on-page switcher for Organization and Persona dashboards.
Use the left navigation Insights dropdown (Listening Engine, Intelligence, Organization, Persona) plus Prompt Forge, Recommendations, Analytics, Settings, and Docs to switch between modules.
Listening Engine includes an on-page tab switcher to move between Listening profiles and Insights views without leaving the page.
The left navigation SWOTT Library and Prompt Library links open the Listening Engine Insights and Prompt Library tabs and keep the URL in sync for shareable deep links.
Listening Engine tab pills match the Prompt Forge tab styling for consistent navigation cues.
Listening Engine now focuses on profile setup, run history, and scheduled runs; the Live Progress and Search History cards are no longer displayed.
Listening Engine scheduling supports daily and monthly cadences; manual run controls are no longer shown in the UI.
Listening Engine places the compact Create Search Profile editor on the left with Run History on the right for at-a-glance monitoring.
Listening Engine opens directly in the Create Search Profile view, so you can start drafting a profile immediately even before any profiles exist.
Press Cmd/Ctrl + K to open the command palette for quick navigation and search.
The header keeps the command palette search, notifications, and account controls aligned in one row at intermediate widths by shortening the search input before wrapping.
Overview pages for analytics, content, and campaigns include key metrics and deep links.
Breadcrumbs stay visible on mobile in a condensed format for context.
Research and Knowledge Base appear as dedicated modules for ingestion and RAG management.
Use the context selectors to switch organization and persona views without leaving the page; the header labels this area with “Currently viewing:” aligned with the selector text in the dropdowns.
The workspace switcher lets you change workspaces without logging out.
Workspaces load automatically after sign-in; if data is missing, use the workspace picker banner to select or manage a workspace.
Dropdown selectors keep selected text fully visible in compact filters and forms.
If data is missing, confirm the active workspace in the top navigation and check data source status.

Dashboard overview

Octant now provides three dashboards aligned to the hierarchy:

Company dashboard: strategic view across all organizations, market shifts, and opportunities.
Business unit dashboard: operational visibility across personas/products with actions, SOV, sentiment, and rankings.
Business unit dashboard cards include filters (actions, conversations, segments) and respect the time-range selector.
Conversion & ROI Efficiency tracks persona ad spend versus open interviews (active CRM opportunities) with persona and date-range filters.
Conversations can be filtered by source host and sentiment; actions can be filtered by priority and type.
The time-range selector limits actions, mentions, and metric snapshots to the selected window.
Persona dashboard: tactical view of persona-specific actions, opportunities, and prompts, including recommended prompts that can be activated or dismissed.

Research studio

Use Research to combine prompt intelligence with listening ingestion:

Prompt Forge: select a persona, optionally narrow by linked product (or all products when no persona is set), then generate prompts with AI or add manual/batch prompts.
Prompt Forge includes tabs for Prompt Forge and Prompt Library; the library houses the prompt list and recent runs.
Prompt Library summary stats (Prompts, Active, Categories, Variables) sit at the top of the Prompt Library tab for quick at-a-glance context.
AI Generate controls labeled “Generate, draft, or import prompts at scale.” include prompt volume, optional goal, product selection, and category selection.
Manual prompt creation uses a category dropdown with preset options (How Tos, Documentation, Market Trends, Products, Solutions & Services, Competitors, Social, Any/All); the Save prompt action stays aligned to the bottom-right of the Manual tab.
Batch imports accept one prompt per line without a separate category field.
Prompt Forge summary stats (Prompts, Active, Categories, Variables) sit above the combined Prompt Intelligence panel for quick at-a-glance context.
The Prompt Forge header no longer includes a “+ New Prompt” shortcut; use the Manual or Batch Import tabs to add new prompts.
Prompt Forge goal input is a collapsible toggle in AI Generate; click Goal to expand and add optional guidance.
On your first visit after onboarding, Prompt Forge auto-generates 10 prompts from onboarding inputs and runs Deep Search so results are ready when you arrive.
Prompt creation is idempotent by name; submitting a prompt with an existing name returns the existing prompt instead of an error.
Manual prompt creation uses an optional Name field and no longer requests a separate description.
Real user queries from LLM mentions appear as inspiration before prompt generation.
If DataForSEO credentials are not configured, prompt generation still works but the real user query panel stays empty.
Deep Search runs use Perplexity or Google Search grounding for citations (based on provider selection) and synthesize across all active providers.
Listening profiles schedule continuous ingestion with run history.
Listening Engine channels/domains support AI suggestions based on your profile inputs.
The Listening tab now shows Run History in the left column, while the Search Profiles filter box lives on the Insights tab.
Live updates stay connected unless the network drops, so the status indicator should remain steady.
Provider coverage and run status panels highlight queued, running, and completed work.
Model comparison scorecard lists every provider execution in a run (not just the top scoring ones).
Prompt cards no longer open the editor on click; use the Edit button, and reruns do not auto-open results (use View results).
Run Results open full-screen; citations and sources list the AI provider icons for each URL and wrap long links.
Run Deep Search (all) to kick off runs across the visible prompt list.
Bulk Run Deep Search queues visible prompts in parallel so large prompt sets start faster.
Listening profiles now kick off due runs in parallel so multiple profiles start immediately.
Listening runs process query batches concurrently while honoring rate limits for faster completion.
Research opens directly in Prompt Forge; prompt and listening run history stays within their respective workspaces instead of a shared tab.
Prompt Forge defaults to 25 prompts per batch; attempts to go above 25 at a time trigger an upgrade modal to contact sales for higher limits.
Prompt Forge cards keep titles truncated while keeping action menus aligned for quick scanning.
Research outputs feed analytics, insights, reports, content suggestions, and knowledge base workflows.

Knowledge base manager

Use Knowledge Base to upload and manage reference documents for RAG:

Upload PDFs, docs, and text sources for retrieval.
Monitor processing status and retry failed files.
Inspect chunk previews to validate retrieval quality.
Tag documents for faster filtering and reuse.
Re-embed documents when sources or models change.
AI assist can suggest document names, descriptions, and tags from file context, and suggestion previews render structured values for complex fields.

Analytics suite

Use Analytics to understand what drives visibility:

The Analytics navigation tabs are ordered as Visibility, Citations, Competitors, and Sentiment.
Topics: detect emerging themes and the volume behind them.
Regions: identify where attention is growing or shrinking.
Channels: compare distribution across social, news, and community sources.
Rankings: choose a topic to see average SEO position trends, top-ranking domains/URLs by keyword and location, plus AI visibility scores with platform breakdowns and context snippets.
Backlinks: monitor domain authority, referring domains, and trend shifts (scoped to the active workspace).
Reviews: follow ratings and sentiment across review platforms.
Sentiment: track overall sentiment score, key drivers, and trends, with prompt execution details per entity; the tab description clarifies it shows sentiment for each citation per prompt.
AI visibility: monitor brand mentions across ChatGPT, Claude, Gemini, and Perplexity, with multi-brand trends and topic drilldowns.
Competitors: benchmark your brand against rivals.
Citations: review sources and citations used by the system.
Citations analytics highlights share-of-voice, top domains, and most-cited URLs, with domain-level drilldowns for trends, prompts, topics, platforms, and regions.
Use the analytics filter bar to multi-select topics, platforms, and regions; selections persist in the URL for sharing.
Analytics tables support horizontal scrolling on smaller screens to reach all columns.

Insights engine

Insights are organized as a SWOTT library (Strength, Weakness, Opportunity, Threat, Trend):

Strength: share-of-voice exceeds 20% (saturated coverage).
Weakness: share-of-voice is below 10% (coverage gaps).
Opportunity: weaknesses with high impact potential if addressed.
Threat: negative sentiment or declining visibility (≥20% mention drop).
Trend: growing mentions or engagement momentum.
Review insights by status (new, in progress, completed).
Open an insight to see evidence, supporting mentions, and recommendations.
Mentions show the estimated impact for each insight (displayed as mention counts).
GEO Impact scores highlight predicted GEO performance plus recommended content type and topic; use Refresh Impact on the detail view to re-run predictions.
Assign owners and due dates to track follow-through.
Regenerate or refresh insights after new data ingestion.
Listening completions now trigger automatic insight generation when enough new mentions land.

Content engine

Create, optimize, and measure content performance:

Suggestions: accept AI-generated content ideas with metadata and themes.
Suggestions now surface GEO impact scores and highlight when a recommendation matches the Impact API guidance.
Toggle between AI-assisted and rules-only suggestion generation.
Generated content previews appear inline before you open the editor.
Content studio: draft, edit, and generate new assets across Generate, SEO, Variants, and Experiments tabs.
Rich editor with AI-assisted rewrites includes inline diff previews and fast save actions.
SEO scoring: assess keyword coverage, meta tags, readability, and grammar issues.
A/B testing: compare variants and track engagement outcomes.
Send finalized content into campaigns to keep activation connected.

Campaigns and automation

Campaigns coordinate messaging across channels:

Email campaigns: build sequences in a stepper (details, steps, preview, enroll) and schedule sends.
Nurture flows: map multi-step cadences across audiences with drag-and-drop reordering and flowchart previews.
PR campaigns: manage press releases, journalist lists, and outreach tracking.
Campaign analytics: monitor funnel performance and engagement trends.
AI assist can draft campaign summaries, email copy, press release briefs, and targeting keywords.

Reports and exports

Reports turn analytics into shareable assets:

Report overview: generate and track report status.
Use the step-by-step wizard (Template → Date Range → Recipients → Review) for guided setup.
Email recipients are validated as you type, with inline feedback.
Templates: define sections, charts, and metrics per report type.
Schedules: automate report creation and delivery.
Share links: create secure shareable links with expiry and access rules.
AI assist can suggest report names plus schedule filters and settings.
Use the visual filter builder for companies, organizations, products, topics, and dates, with optional advanced JSON.

Company, organization, product, and persona management

Keep intelligence aligned to the new hierarchy:

Companies: set the top-level context for organization rollups and executive dashboards.
Company dashboards surface SEO/SEM performance from real content metrics (organic traffic, top keywords, avg SEO score, CTR).
CRM integration metrics in the company dashboard are derived from CRM lifecycle/stage fields (HubSpot lifecycle stage, Salesforce lead status/converted).
Business units: capture divisions or brands under the company.
Products: add product details, upload up to 5 PDF datasheets, and capture persona-specific positioning.
Personas: capture audience profiles, domain, industries, geography (including a Global option for worldwide targeting), application areas/use cases, market trends, and care-about prompts; AI suggestions can emphasize compliance topics and requirements.
AI suggestions in the Persona Builder retry and fall back gracefully if generation responses are malformed, so the flow stays responsive.
Persona Builder steps collect structured inputs (organizations, profiles, ecosystem, domain, industries, geography, use cases, market trends) with AI assist to draft persona descriptions and suggest use cases.
Step 2 confirms persona care-about prompts (3-5 recommended, max 10) with prompts that include application requirements, industry standards/regulations/certifications, and end-user requirements; Step 3 generates a preview with summary, goals, pain points, and an AI-generated avatar; Step 4 completes the flow and saves the persona (also used during onboarding).
Persona avatars auto-generate after creation; regenerate them from the persona detail header if needed.
External mode exposes a public persona builder at /persona-builder with the same Step 1-3 flow and business-email-gated exports.
Persona exports require a business email and deliver a secured PDF by download or email; full persona kits route through the contact form.
Brand kits centralize voice, tone, and messaging pillars for content workflows.
Brand kits can be linked to organization topics to steer targeted content generation; manage selections in the Topics tab when editing a kit.
The Brand Kits page supports search and paginated lists to keep large libraries manageable.
Use Create Brand Kit to select a brand and add a description; edit or delete kits from the table actions.
Brand Settings lets you update brand name, website URL, description, and aliases used by AI guidance.

Settings and integrations

Configure account-level preferences:

Workspace settings: manage name, region, timezone, team members, and notification preferences.
The Settings overview includes a Create panel with shortcuts to Organizations, Personas, Products, and Brand Kits.
Theme: Octant now uses a unified light theme across marketing and app pages (no dark mode toggle).
Side panels and navigation sidebars use consistent light styling and scroll when forms are long.
Providers: connect LLM or analytics providers and use Check Health to validate API keys (global defaults can seed internal workspaces).
DataForSEO: connect credentials, set budgets, and review usage in the Admin Console.
Integrations: connect CRM, email, or PR tools and monitor OAuth connection status.
HubSpot integrations expose custom object schema/status endpoints for manual setup, plus sync status monitoring and manual sync triggers for the Organization Dashboard; the Integrations settings page shows status, schemas, and fallback warnings.
HubSpot custom object and company property names use the signalplane_ prefix (replacing octant_).
If custom objects are missing or scopes are unavailable, sync falls back to company properties, notes, and tasks; reauthorize with custom-object scopes to enable full custom object sync.
Newswire integrations support provider credentials and delivery mode selection.
Billing: review plan details and usage.
Security: verify your email address, request password resets, and review authentication controls.

Collaboration and governance

Roles determine access (owner, editor, viewer).
Invitations allow onboarding new team members, with resend or cancel when needed.
Shared reports can be restricted to domains or specific emails.

Admin console

Superadmins can access the system-wide Admin Console at /admin:

Monitor platform KPIs (users, workspaces, subscriptions, MRR) and real-time usage trends.
Manage users, workspaces, and global providers with suspension, plan changes, and role updates.
Review audit logs, system settings, and maintenance mode.
Use real-time activity and health indicators to track system status.
Impersonate users to reproduce issues and invalidate sessions when access needs to be cut quickly.
Audit logs record action, entity, IP, and user agent for compliance and investigations.
Monitor DataForSEO usage by workspace, endpoint, and spend window.

For full integration notes, permissions, and operational guidance, see docs/knowledge_base/admin-console.md.

Video tutorials

See docs/knowledge_base/video-tutorials.md for recommended recordings and scripts.

FAQ and troubleshooting

I do not see data on the dashboard.

Verify the active workspace and ensure at least one provider or data source is connected.

Why are reports stuck in queued?

Check report schedules and asset generation status. Retry generation if needed.

Why are research runs stuck in queued?

Confirm providers are connected and the background workers are healthy.
Research runs should move to running within a minute; retry the run if needed.

Why are GEO Impact scores missing?

GEO Impact predictions rely on the separate Myles AI service; if it is unavailable, insights and suggestions still generate but impact fields remain empty.
Ask an admin to confirm the Myles AI App Platform service is healthy and MYLES_AI_URL is set to the service URL.

The app shows errors right after a deployment.

Give the system a few minutes to complete database migrations, then refresh.
If the deployment fails during build, ensure the build pipeline compiles TypeScript before pruning dev dependencies.

Why was I redirected to login?

Your session expired or was refreshed unsuccessfully. Sign in again to continue.

The Personas page freezes or keeps loading.

Confirm a workspace is selected, then refresh the page to reload persona data.
If personas were recently linked to multiple business units, confirm the latest backend migrations are deployed; older deployments may only show personas tied to the primary business unit.
If the issue persists, sign out and back in, or contact support.

How do I share a report externally?

Create a share link with access rules and send the generated URL.

I need help with API access.

Contact your workspace owner or review the developer documentation for token usage.

For additional FAQs, see docs/knowledge_base/faq.md.