SASVA Canvas — User Guide

§Table of Contents

1Introduction

Welcome to the User Guide for SASVA Canvas. SASVA Canvas is a secure, AI-powered platform that connects to your documents, websites and enterprise systems and turns them into actionable intelligence — all from a single, conversational workspace. It combines multi-agent AI, graph-augmented Retrieval-Augmented Generation (RAG) and a deterministic ROI engine to support analysis, planning and decision-making.

A defining feature is data sovereignty: SASVA Canvas is designed to run on-premise (including air-gapped networks) so your business data, code and documents never leave your organisation. It is available as a Web application, a Desktop application (Windows, macOS, Linux) and a Mobile application (iOS & Android), all sharing the same secure backend.

2What SASVA Canvas Can Do

3Accessing SASVA Canvas

1. Web: open the SASVA Canvas URL provided by your administrator (e.g. https://canvas.yourcompany.com or http://localhost:3300) in a modern browser.
2. Desktop: launch the installed SASVA Canvas desktop app (Electron) and sign in.
3. Mobile: open the SASVA Canvas app, enter your organisation's server URL, and sign in.
4. Sign in with your email & password, or via Single Sign-On (SSO) if your organisation uses Azure AD / SAML. The desktop app uses native Azure AD SSO with the secure PKCE flow.

4First-Time Setup

These steps are usually completed once, by an administrator:

1. Navigate to the SASVA Canvas URL and create the first account (becomes Super Admin). If a default administrator account was provisioned by your deployment, change its password immediately after first login.
2. Configure the AI provider in Settings → AI Provider (SASVA, AWS Bedrock, Anthropic or OpenAI).
3. Set up your organisation / tenancy in Settings → System Configuration (single- or multi-tenant).
4. Optionally configure Search API (SerpAPI), Estimation Engine, Report Formatting, Email (SMTP) and Telemetry.
5. Invite users and create your first workspace.

5Workspaces Explained

Everything in SASVA Canvas happens inside a workspace. You can also create focused sub-workspaces for specific topics or projects. There are two types:

6Creating a Workspace

1. On the Dashboard, click Create Workspace and choose Product or Business.
2. Give it a name and description. Workspace names are validated for uniqueness.
3. Business: upload documents or connect document sources. Product: connect a code repository (remote Git or a local-folder ZIP) and/or process-management, ticketing and documentation tools.
4. Wait for indexing to complete — a status indicator shows progress; large repositories clone in the background so you can keep working.
5. Start chatting or launch an operation.

7Using a Business Workspace

7.1 Upload & index content

Click Upload to add files — 16+ formats including PDF, Word, Excel, PowerPoint, HTML, CSV, Markdown, JSON and images (up to 500 MB per file). Files are parsed, semantically classified, chunked and embedded for retrieval. You can also paste a URL for inline web-page analysis, or paste an image for OCR.

7.2 Chat with your content

Type a question in the chat box. SASVA Canvas retrieves relevant passages, verifies them with its agents, and generates a grounded answer with citations. Turn on Extended Thinking for complex reasoning, and use voice dictation to speak your query. Casual messages (e.g. "hi") get an instant fast-path reply without the full retrieval cycle. You can stop a streaming response at any time.

7.3 Web search & current information

For time-sensitive or "latest" questions, the Web Search agent automatically fetches current information (via SerpAPI) and the Latest-Check agent assesses recency, so you get up-to-date, date-aware answers.

7.4 Business operations

Beyond chat, Business workspaces offer guided operations: Create Proposal, Business Analysis, Meeting Preparation, Create Presentation, Customer Analysis (with CRM), and Competitive Research.

8Using a Product Workspace

8.1 Connect your sources

Add a remote Git repository (GitHub, GitLab, Bitbucket) or upload a local folder as a ZIP to use as the code repository. Connect process-management (JIRA / Aha! / Asana / Azure DevOps), ticketing and documentation tools as needed. You can revisit and edit earlier setup steps at any time.

8.2 Available operations

9Release Planning & Estimation

Launch Release Planning to turn objectives into a plan:

Which estimation engine is used? SASVA Canvas selects automatically based on your setup. In summary:

• SASVA Models — used for new projects, when the code repository is not connected/cloned, or when the Estimation setting is "SASVA only" (also the safe fallback if Advanced migration fails).
• Advanced Estimation Engine — used for existing projects with a connected and cloned code repository when the Estimation setting selects Advanced (valid project or successful migration).
• Publish to process management is available only when a process-management tool (e.g. JIRA) is connected.

You can view past estimations (synced with SASVA Studio) and attach a document to describe a feature for estimation.

10ROI & Business Value

The ROI Analysis operation turns a backlog into an investment-grade decision artefact. Select backlog items; the engine pulls relevant signals per item (JIRA, code, tickets, docs, CRM, market insights), scores each item across 8 deterministic factors, runs financial synthesis, compares to industry benchmarks, and returns a recommendation with low / mid / high projections. Every number is reproducible from formulas — the AI only writes the narrative.

A live pipeline dialog shows each item move through gather → analyze → done, and every score exposes the exact signals behind it (source, value, confidence) plus a confidence level and % real data. After a feature ships you can record actuals in the Tracking panel to measure predicted-vs-actual accuracy.

11Assessments & Discovery

• Code Assessment — code quality, technical debt and security analysis via the Assessment Portal, with a live pipeline visualiser. Requires a connected code repository.
• Process Assessment — analyses development processes, workflows and team practices for optimisation.
• Discovery & Planning (Genesis) — an embedded Genesis experience for discovery workflows; your Product workspace name, ID and domain are passed for project context.
• Lifecycle Dashboard — tenant-scoped real-time metrics across workspaces, operations, agents, backlog and conversations, with drill-downs and phase mapping.

12The AI Agents

SASVA Canvas uses specialised agents that collaborate on every request:

13Reports, Images & Collaboration

• Export formats: PDF, HTML, DOCX, PPTX (PSL-branded template) and Markdown, with split download buttons and re-download of previously generated reports.
• Image generation: creative images via SASVA; architecture diagrams and flowcharts via Mermaid.
• Sharing: share a workspace or an individual AI response/report for review; reviewers add inline comments, compare versions and approve. Non-admin workspace owners can share, using a searchable user picker.
• Permission levels when sharing: Viewer (read), Editor (contribute), Admin (manage).

14Roles & Permissions

15Responsible & Safe Use (Human Oversight)

16Feedback & Incidents

SASVA Canvas provides several complementary channels for sharing feedback and reporting incidents, so you can use whichever suits the situation — a quick in-product rating, an email to support, product telemetry, a formally tracked support ticket, or (for administrators) the system's detailed logs, which help pinpoint the reason for a failure.

16.1 In-product response feedback (👍 / 👎)

• Click Thumbs Up 👍 on any response if the answer was helpful.
• Click Thumbs Down 👎 if it was not — add a comment explaining what went wrong.

This is the fastest way to signal answer quality and is captured per response alongside its sources.

16.2 Support email

For questions, feature requests, errors or data concerns, email the support team at support@accelerite.com. Include a clear description, the workspace name, the approximate time, and attach screenshots where possible so the team can reproduce and triage the issue quickly.

16.3 Product telemetry (PostHog)

SASVA Canvas integrates PostHog product telemetry (and an optional telemetry gateway). Beyond usage analytics, telemetry captures feedback signals — thumbs-up/down events, feature usage and errors — that feed the admin platform-metrics and Lifecycle dashboards, helping the team spot problems and prioritise improvements even when they are not reported manually. Telemetry is subject to your organisation's configuration and privacy settings.

16.4 Support ticketing & incident management

For issues that need to be formally tracked and resolved, the support desk operates a ticketing / incident-management workflow: support staff receive requests and incidents from users (via email or the support channel), triage and prioritise them, and convert them into JIRA tickets that are assigned to the engineering team. Each ticket is tracked through to resolution, giving full traceability for reported problems and their fixes. Critical incidents (service down, suspected data exposure, security or AI-governance concerns) are escalated per the incident-response process (see the Operations Runbook).

Support SLAs for customer-reported issues

These SLAs apply to issues that Canvas users raise to the platform support team (email, Help Center → Contact Support, or the support channel). Support files a ticket for each request. All targets are expressed in hours. They do not apply to security-finding remediation or to other internal operational SLAs.

Priority is set when the ticket is triaged: Urgent, High, Normal, or Low. A target of 0h means no SLA is committed for that metric at that priority.

Reply metrics — how quickly we respond to a customer’s request.

Update metrics — how frequently we keep customers updated.

Resolution metrics — how long we should take to solve a request.

16.5 Logs & diagnostics (for administrators)

SASVA Canvas writes detailed structured logs for every part of the system — sign-in & authentication, API requests, workspace & document operations, the AI agents, chat, integrations, estimation / ROI and billing. Each entry records a timestamp, a severity (DEBUG, INFO, WARN, ERROR, CRITICAL and AUDIT), a category and the acting user / tenant, so an administrator can reconstruct exactly what happened during an incident and find the reason for a failure.

• In the app: an administrator can open Settings → Maintenance → Logs to browse log files by category, view the latest entries, filter, download a single file or all logs, and clean up old logs.
• Command line (on-prem / self-managed deployments): operators can use ./sasva-canvas.sh logs (view), logs-f (live follow), logs-rotated (previous/rotated runtime logs) and app-logs for the structured application logs.
• Rotation & retention: logs are automatically rotated and retained for a bounded number of files per category / service. For the full log format, severities, categories and the rotation & retention policy, see the SASVA Canvas Logging Reference.

16.6 Logging and Monitoring Stack Enablement and Customer Responsibility

Purpose

The Logging and Monitoring Stack is provided as an optional operational capability to enhance observability, monitoring, troubleshooting, and operational reporting for the SASVA platform components, including Canvas and IDE deployments. This capability is not a mandatory prerequisite for the deployment or operation of the core SASVA product stack.

Customer Opt-In Requirement

Implementation and enablement of the Logging and Monitoring Stack within the customer environment shall be performed only upon the customer’s explicit decision to adopt the solution. The deployment of monitoring components, including but not limited to Prometheus, Grafana, Loki, Node Exporter, and/or Grafana Alloy, is considered an optional infrastructure enhancement beyond standard SASVA product deployment.

Customers may choose to:

• Enable the complete Logging and Monitoring Stack.
• Enable selected monitoring components based on their operational requirements.
• Operate the SASVA platform without the optional Logging and Monitoring Stack.

The decision to implement or not implement this capability remains solely with the customer.

Infrastructure Dependency and Provisioning Responsibility

The Logging and Monitoring Stack requires dedicated infrastructure resources in addition to the resources allocated for the core SASVA platform components.

The customer is responsible for provisioning and maintaining the required infrastructure resources, including but not limited to:

• Virtual Machines (VMs) or equivalent compute resources.
• CPU, memory, and storage capacity.
• Network connectivity and firewall configurations.
• Backup and retention storage (if applicable).
• Operating system and platform prerequisites.
• High availability and disaster recovery configurations (where required).

Infrastructure sizing requirements may vary depending on factors such as:

• Number of application instances being monitored.
• Log generation volume.
• Metrics collection frequency.
• Data retention requirements.
• Availability and performance objectives.

Ownership and Operational Responsibility

Where the Logging and Monitoring Stack is enabled, operational ownership of the underlying infrastructure remains with the customer unless otherwise agreed through a separate managed services engagement.

The customer is responsible for ensuring that adequate infrastructure capacity is available to support:

• Metrics collection and retention.
• Log ingestion and retention.
• Dashboard visualization and reporting.
• User access management and authentication.
• Ongoing operational monitoring of the monitoring platform itself.

Summary

For audit and governance purposes, it is important to note that:

• The Logging and Monitoring Stack is an optional add-on capability and is not part of the mandatory SASVA product deployment baseline.
• Non-deployment of the Logging and Monitoring Stack by the customer does not constitute product deficiency or non-compliance of the SASVA platform.
• Any limitations in monitoring, observability, alerting, log retention, troubleshooting visibility, or operational reporting resulting from the customer’s decision not to implement the Logging and Monitoring Stack shall be outside the scope of the SASVA product responsibilities.
• The customer acknowledges that implementation of the Logging and Monitoring Stack requires additional infrastructure resources and associated operational support.

16.7 Help Center & Platform FAQ (v4.0.4)

Open Help Center from the app header to browse embedded documentation and platform help:

• User Guide and Product Guide — the same ISO documents you are reading now, rendered in-app.
• Platform FAQ — a searchable accordion of 60+ curated answers across Getting Started, Platform & SASVA, Capabilities, Support, Workspaces, Operations, Releases, Settings, and Troubleshooting. Answers use the live platform version and support email from your tenant settings.
• Contact Support — create a tracked support thread (see section 16.4).

When you ask platform questions in workspace chat — for example How do I contact support?, What was added in 4.0.4?, or How does Canvas run on SASVA? — Canvas routes them through a Platform FAQ fast-path before RAG or a general LLM reply. You get a deterministic, documentation-backed answer with no workspace sources for matched intents.

Feedback is used to monitor and improve response quality — it is not used to train the models.

17Desktop & Mobile

18Troubleshooting & FAQ

19Glossary

20Version Control