SupaPM

AI-powered product management assistant with context-aware chat

Think "Cursor for Product Managers and Project Managers". SupaPM is your context-aware AI agent that comes with you in your browser to make everything you do quicker, easier and higher impact. It makes switching contexts easy, giving you the latest context about ongoing projects. It makes it easy to create your own automations and workflows that do the grunt work so you don't have to. Features: - Local-first - your data doesn't leave your browser - Use any tool-calling LLM you like. If a new one comes out, just switch over in seconds - Build your own shortcuts and automations - Create your own skills that your LLM can use to help you get your work donw - Give the LLM your own personal organisational context on how work should be done. What the product does, who's responsible for what, all so that your SupaPM agent can be as helpful as possible in getting your work done. --- v0.0.13 This update renames "Org Knowledge" to "Company Context" throughout the extension, rebuilds the default document template with richer structure and table-based sections, rewrites the system prompt with explicit routing rules, and adds a Raw/Styled toggle directly in the markdown editor toolbar. It also makes chat context much more practical in day-to-day PM work: you can attach files or paste slide screenshots directly into chat for summarisation/extraction workflows, and you can stop an in-flight generation when the response is already good enough or heading the wrong way. - Renamed "Org Knowledge" to "Company Context" across the sidepanel nav, options nav, page titles, aria labels, skills, chat context labels, and all internal references. - Rebuilt the default Company Context document template with distinct sections: Company, Products, Customers, Strategy (including a baseline metrics subsection), Competitors, Pricing, Glossary, and Decisions -- followed by personal sections (My Team, My Stakeholders, My Notes) separated by a divider. - Glossary, My Team, and My Stakeholders sections now use markdown tables for better structure and scanability. - Added explicit load-routing hints to the system prompt so the agent knows which section to load for each question type (people/ownership: my-team/my-stakeholders, customers/ICP: customers, strategy/OKRs: strategy, pricing: pricing, competitors: competitors, products: products, unfamiliar terms: glossary, past decisions: decisions). - Rewrote the default system prompt with structured sections covering tone and style, company context usage, skills usage, proactive context capture, project defaults, and a clear list of things to avoid. - Added a Raw/Styled toggle button to the MarkdownEditor toolbar (far right, after Redo) so users can switch between the TipTap rich editor and a plain-text raw view in any markdown editor surface -- system prompt, skills, project descriptions. - Added file and image attachments in sidepanel chat: PMs can attach files from disk or paste images (for example slide screenshots with charts/text) and use them as direct chat context. - Added attachment-aware request building so text/code files are inlined as structured context blocks and image attachments are sent as model-safe image payloads (including pasted `data:` images), enabling summarise/extract workflows without manual copy-paste. - Added removable attachment chips in the composer plus attachment-only sends, so users can submit context artifacts even when there is little or no typed prompt text. - Added a Stop button during generation that aborts the in-flight response, preserves any useful partial output, and marks interrupted tool activity as cancelled for clearer chat trace visibility. - Simplified edit-event cards in chat so the header focuses on the meaning of the change (document + summary), while detailed diff metadata is de-emphasized behind expansion controls for faster sidepanel scanning. --- v0.0.12 This release helps PMs move faster in multi-step AI workflows by making follow-up chats more context-aware and easier to trust. You can quickly confirm what the model received for a turn, keep loaded skills and org knowledge reliably available across turns, and avoid duplicate or misplaced project links by checking where a URL is already referenced before creating new work. - Improved LLM auditability in debug mode by combining preflight payload capture (including the fully composed `systemPrompt` and `messagesForAgent`) with step-level request/response logging, making Inspect Turn easier to trust when validating model behavior. - Improved cross-turn memory reliability by carrying forward compact prior tool outcomes and preserving version-aware loaded context in `LOADED_CONTEXT_IN_THIS_CHAT` (including `updated_at` freshness checks), so follow-up turns retain loaded skills and org knowledge without replaying verbose tool JSON. - Fixed context window usage calculation to avoid double counting across a chat session: context percentage and context-attachment safety checks now use current-turn context input usage (plus active captured context), not cumulative lifetime session tokens. - Improved inline captured-context tokens in the chat composer to use readable page/screen labels (for example `[[screen:2026 TikTok...]]`) instead of opaque short IDs. - Improved edit-event cards in chat and Edit History with clearer no-border visual separation and more readable add/remove change highlighting. - Replaced the sidepanel header Home and Settings buttons with an options quick-nav dropdown that links directly to every options page (Chats, Skills, Prompts, Org Knowledge, Edit History, and Settings), now using DaisyUI's native dropdown behavior for more consistent open/close interactions and fewer custom-state edge cases. - Removed automatic sidepanel focus jumps (on open, send completion, loading completion, and session/context updates) so the project picker no longer briefly opens and accidental project selection is less likely when you refocus the panel. - Expanded the local `search_projects` agent tool with richer filtering and sorting (`sort_by`, `sort_order`, status, priority range, tags, recency windows like last 7 days, and stale-project queries), plus clearer parameter guidance so project triage requests resolve more reliably in chat. - Added a Skills page search box with instant local filtering by skill name/description and a clear no-results state, plus improved input surface contrast so the field is visually distinct in light theme. - Added strict duplicate-link protection to `add_project_link`: the tool now canonicalizes URLs and returns a clear error when the exact same link (including params) is already attached to a project. - Added a new `find_projects_by_link` tool so the assistant can answer “is this URL already linked anywhere?” and return all matching projects plus the matched link records, useful for workflows like Jira-ticket-to-project lookup. --- v0.0.11 This release gives PMs better control over both reasoning depth and captured page context. You can now tune how much thinking effort the assistant spends on harder work directly in chat, and add highlighted text to context explicitly with a keyboard shortcut instead of having context appear unexpectedly when the composer gains focus. This makes quote capture from customer calls, competitor pages, and docs more intentional and easier to trust. - Added model-level reasoning controls in the sidepanel chat model popup so you can set reasoning depth inline (low, medium, high) while selecting your model. - Added support flags in the model catalog (`supports_thinking`) so reasoning controls only appear when the currently selected model supports thinking, while still showing capability hints next to compatible models. - Added provider-specific reasoning settings at runtime for OpenAI, Anthropic, and Google models so the selected reasoning depth is actually applied to API calls. - Improved Google/Gemini reasoning behavior by requesting thought content explicitly (`includeThoughts`) so thinking output can be surfaced in the chat reasoning UI when the provider returns it. - Added persistent reasoning-level preference in extension AI settings so your selected depth carries across sessions instead of resetting each time. - Added a native highlighted-text capture shortcut (`Ctrl+Shift+Y` / `Command+Shift+Y`) that opens the sidepanel and adds the active selection to chat context in both Chrome and Firefox. - Replaced legacy focus-based selected-text auto-attach behavior with explicit shortcut capture, so highlighted text is only added when the user deliberately triggers it. - Added clearer in-panel capture feedback for shortcut flows, including no-selection and permission guidance, and deduped repeated captures of the same selection (`url + exact text`) in a chat. This release makes SupaPM easier to approve, trust, and use in day-to-day product work. Security and compliance teams can review the public CycloneDX SBOM before rollout, while PMs get clearer control over when page context is captured—explicit site permissions and removable grants in Settings—and a calmer capture flow: highlight a customer quote, competitor claim, roadmap note, or support detail on an approved site, then focus the sidepanel chat input to add it as context without a floating page button. The agent can chain document edits reliably on org knowledge, skills, and project descriptions (including right after install or a data reset), and the assistant can open a URL in the **current** tab when that matches “go to…” instead of always opening a new tab. --- v0.0.10 - Fixed a bug where the AI agent's first `edit_document` or `replace_document` call would always succeed but any subsequent edit in the same conversation would fail with a spurious conflict error. The root cause was a timestamp mismatch: the document's `updated_at` and the edit event's `timestamp` were generated separately (at slightly different moments), so the concurrency check on the second call would compare two different timestamps and reject it. The tool now returns the document's actual `updated_at` so the agent always has the correct token for chained edits. - Fixed a related bug where AI document edits would always conflict for new users (or after a data reset) because the default org knowledge document was never persisted to storage. Each read generated a fresh in-memory document with a new timestamp, so the timestamp in the system prompt never matched the timestamp seen during the edit. The default document is now written to storage on first read, giving it a stable `updated_at`. - The `open_web_pages` agent tool now accepts an optional `target` parameter (`"new_tab"` or `"current_tab"`). When `"current_tab"` is chosen, the agent navigates the active browser tab to the URL instead of opening a new one — useful when the user says "go to X" rather than "open X in a new tab". Additional URLs beyond the first still open in new tabs. - SupaPM now publishes a CycloneDX Software Bill of Materials for the browser extension on the main site, linked from the footer, so security and compliance teams can review the extension dependency supply chain before approval. - Highlighted-text context now uses explicit optional site permissions. SupaPM asks before enabling selected-text capture for a site, supports either "this site" or "all sites", and lists granted page-context permissions in Settings so users can remove them. - Removed the floating "Add as context" button from webpages. When page context is enabled for a site, highlighted text is added as a context chip when the user focuses the sidepanel chat input. --- v.0.0.9 Updates - The extension now discovers supported providers and models from SupaPM's public model catalog, with versioned catalog responses and automatic filtering for unavailable or incompatible models. - Updated the catalog with Claude Opus 4.7, Claude Sonnet 4.6, Claude Haiku 4.5, Gemini 3.1 Pro Preview, Gemini 3 Flash Preview, and Gemini 3.1 Flash-Lite Preview. - Settings now support a manual OpenAI-compatible endpoint for local or custom-hosted models, while keeping the SupaPM catalog as the recommended default. - Chat surfaces now show the active model, allow catalog model switching, and display token/context usage metadata when available. - Loaded Org Knowledge sections and Skills are now reused across turns, reducing repeat tool calls while surfacing cached-token diagnostics. - Responses with explicit `<think>` reasoning blocks now show that reasoning in a collapsible Thinking row, styled consistently with tool-call activity. The same row appears while chat is waiting for the first model response. --- v0.0.8 - Skills don't use modals for editing any more - they have dedicated pages like projects - easier for editing - Skills also now use the markdown editor instead of just raw markdown - a better experience. - UI for chat is updated slightly to move the input into the actual column where the chat conversation lives - Auto-scroll only follows new output when you’re already at the bottom. - Removed snap points for smoother, more natural vertical scrolling. - Notion-style @ date mentions (e.g. today, tomorrow, next week), keyboard menu support, date picker editing, and @date(YYYY-MM-DD) round-trip support. --- v0.0.7 Updates - Improved project selection and management - no longer auto-switching projects - LLM now has new abilities to edit skills, org knowledge, and projects - WITH an audit log and revertability of changes - Added edit history page so you can see, per document, your changes and the agent's changes - Project links now show you (via opacity) when you're on that page - Favicon fixes for project links (subdomains weren't working)