AI Features

Hypertask is built from the ground up as an AI-native project management platform. AI isn’t bolted on as an afterthought — it’s woven into every part of the workflow, from creating tasks to communicating with your team.

AI Task Writer

Describe what you need. Get detailed, context-aware tasks.

Voice Dictation

Speak your thoughts. Hypertask transcribes and structures them.

Superhuman-Style Snippets

Insert predefined text and templates with keyboard shortcuts.

HyperAI Co-worker

Chat with an AI that knows your project — and can take action on it.

Text Enhancement

Improve grammar and readability of any text with one click.

AI Task Writer

Instead of manually writing detailed task descriptions, tell the AI Task Writer what you need in plain language. It generates fully structured tasks with context-aware details.

How it works:

Open the AI Task Writer from any board.
Describe what you need — a sentence or two is enough.
The AI uses your project context (existing tasks, descriptions, labels) and any custom instructions you’ve configured to generate a detailed task.
Review, edit if needed, and add the task to your board.

Web search is handled automatically — the AI decides when to look up external information (documentation, APIs, best practices) based on your prompt, without any manual toggle.

The Task Writer maintains a history of responses, so you can revisit previous suggestions and reuse them.

Properties during task creation

When creating tasks via the AI Task Writer, you can set the following properties directly without needing a follow-up edit:

Property	Description
Tags	Categorize the task with project labels
Task Size	Story points or time estimate
Priority	`urgent`, `high`, `medium`, `low`

Confirm and discard

When using the AI Task Writer, you can review the task before adding it to your board:

Discard changes — click the discard button or press the discard key to close without saving
Add to board — accept the task and move it to your selected section

Discard and confirm dialogs manage your draft state; they’re treated as preview steps before commit.

Voice Dictation

Capture ideas hands-free with OpenAI Whisper-powered voice dictation. Use it anywhere you can type — task titles, descriptions, comments.

Feature	Details
Keyboard shortcut	`Shift + Cmd/Ctrl + D`
Continuous mode	Keep talking without pressing buttons repeatedly
Echo cancellation	Works in noisy environments and during calls
Noise suppression	Filters out background noise for cleaner transcription
Multilingual	Supports all languages that Whisper recognizes

Speak naturally. The transcription handles punctuation, formatting, and language detection automatically.

For even faster composition, use Superhuman-style snippets to insert predefined templates and commands with just . followed by a keyword (e.g., .ack, .oro, .contact). Pin your most-used snippets to the top of the menu for one-tap insertion.

Text Enhancement

Select any text in a task description or comment and click Improve Readability. The AI refines grammar, clarity, and style while preserving your meaning.

Works on any text field in the app
Preserves technical terms and project-specific language
Undo support — revert to the original text if you prefer it

This is intentionally lightweight. It’s not a rewrite — it’s a polish.

House Style

All AI-powered writing surfaces now share a consistent, scannable house style focused on clarity and brevity:

BLUF-first opening — The first line is a clear Bottom Line Up Front statement
Numbered bullets — Rationale points use numbered bullets (1., 2., 3.)
Bolded content — Key terms and headings are bolded for quick scanning
Non-violent — No accusatory phrasing; constructive and neutral
120-word cap — Responses are concise, ending early before hitting the limit
No “In summary” closure — Brevity takes priority over explicit wrap-up
Simplified grammar fixes — Fix Grammar stays minimal on all surfaces

This style applies across:

AI chat responses
AI Task Writer output
Task Writer “Write with AI” suggestions (Lengthen respects scannability but is not brevity-bounded)
Text Enhancement polish
@HyperAI comments

HyperAI Co-worker

HyperAI is an AI chat sidebar built into the Hypertask app. It’s context-aware: it knows your project, your tasks, and your team structure.

What makes it useful

Project context — HyperAI can see your boards, tasks, and project configuration. Ask it questions like “What are the highest priority tasks this week?” or “Summarize what happened on the API project yesterday.” It also understands archived tasks, so you can query completed or archived work.
Take action — HyperAI can create tasks, update and delete them, assign or unassign team members, set priorities, manage labels, move tasks between boards, manage sections, update and delete comments, handle inbox notifications, create and delete saved views, and edit sent messages — all directly from the chat sidebar. Just tell it what you need and it handles the rest. Per-inference usage is tracked automatically and reported in the AI Usage breakdown.
Smart query analysis — HyperAI and AI Chat use advanced query analysis to understand your intent and surface more relevant, accurate responses. The AI interprets what you’re asking and applies intelligent filtering to match your project context.
Consistent house-style output — All responses follow the BLUF-first, scannable house style for clarity and brevity, with 120-word limits and non-violent phrasing.
Consistent HTML output — Both AI Chat and HyperAI always return responses in HTML, so output renders correctly in the app regardless of the model or prompt used. HTML is sanitized using an isomorphic DOM cleanup library before rendering to prevent XSS attacks (too, per HTPR-4247).
@mentions — reference specific tasks, people, or projects in your messages to give the AI precise context.
Chat sessions with history — conversations are saved as named sessions. The AI automatically gives each chat a descriptive name, and you can browse your full chat history to pick up where you left off. For a task, threads from the question list on the welcome screen now appear when you open AI chat for that task (in addition to earlier-created preview threads) (HTPR-4311).
Side-by-side by default — AI chat now opens in a side-by-side view by default whenever you’re actively working on a task, keeping context visible without requiring manual opening.
Available on mobile — AI Chat is accessible full-screen on mobile. Tap the chat icon on any mobile view to get the same context-aware assistant you have on desktop.
Fast, responsive streaming — AI chat uses optimized streaming for low-latency responses, with a smooth conversation flow that keeps up with your thinking.
Animated thinking indicator — the moment you send a message, animated thinking dots appear in a new assistant bubble so you always know the AI is processing your request. The dots clear automatically as soon as the first token of the response arrives, giving you immediate visual feedback that your message was received and work is underway.

Board agents

You can @mention board agents in AI Chat to have them help answer questions. When you @mention an agent, the chat stream shows “Asking the board agent…” and the agent’s specialized knowledge (e.g., a wiki or database) informs the response.

Embed URLs in task menus

The app automatically extracts embed URLs from task descriptions (Figma, Loom, and iframe links). These URLs appear as clickable rows in the task Ctrl+O menu, making it easy to access design mockups, video feedback, and embedded content directly from your task context without leaving the menu.

Keyboard shortcuts

Shortcut	Action
`Cmd/Ctrl + Shift + ?`	Minimize / restore the chat sidebar
`Cmd/Ctrl + Shift + O`	Start a new chat

Full-screen chat mode

AI Chat can be opened in full-screen mode for an immersive experience. From Ctrl+K, select Open AI chat full screen. Once open, chat sessions are organized by time with a sidebar showing recent sessions; empty sessions are hidden. Chat is unscoped: you can reference tasks, boards, and project context across all boards in your project without selecting a specific board.

MCP tools automatically available

AI Chat is powered by the same MCP tools available to external AI agents. When new MCP tools or parameters are added to the Hypertask MCP server, they automatically become available in AI Chat — no separate integration step or redeployment is needed. AI Chat always checks for existing MCP tools in the session and makes them accessible to the AI model.

AI Chat now has full read/write parity with the REST API, MCP, and CLI. Every action available through those interfaces — including label management, section CRUD, comment updates and deletes, moving tasks between boards, inbox unarchive, task trees, and saved views — is also available from the chat sidebar.

Attaching files to AI Chat

You can attach files and images directly to messages in AI Chat, giving the AI concrete reference material to work with alongside your prompt.

Supported content:

Images (screenshots, mockups, diagrams, photos)
Documents (PDFs, text files, spreadsheets, and other common formats)

How to attach:

Open AI Chat.
Click the attachment icon in the message composer, or drag and drop a file into the chat input.
Select your file. It appears as a preview alongside your message.
Type your prompt and send — the AI receives both the file and your text.

Voice input in AI Chat

AI Chat supports voice dictation, allowing you to speak your messages instead of typing. Use Shift + Cmd/Ctrl + D to start recording, or tap the microphone icon in the chat composer.

Using AI Chat

AI Chat’s access to your workspace matches what the CLI and MCP tools can read and write — all three interfaces share the same underlying tools and stay in sync.

Workspace data	AI Chat	CLI / MCP
Tasks (title, description, status, priority, size)	✅	✅
Assignees & followers	✅	✅
Comments (read, add, update, delete)	✅	✅
Labels (read, create, assign)	✅	✅
Sections / board columns (CRUD)	✅	✅
Subtask hierarchy / task tree	✅	✅
Due dates	✅	✅
Archived / completed tasks	✅	✅
Saved views (create, delete, edit)	✅	✅
Move tasks between boards	✅	✅
Inbox (list, archive, unarchive)	✅	✅
Tags (read, create, assign) by name and ID	✅	✅
Time tracking (start/stop, per-inference metering)	✅	✅

Auto-Summary

When a task accumulates a long comment thread, Hypertask generates an automatic summary so you can get up to speed without reading every message.

Auto-summaries highlight:

Key decisions made in the thread
Current status and blockers
Action items that emerged from the discussion

AI Triage

Use the AI Triage button in your inbox to automatically categorize, prioritize, and suggest actions for incoming notifications and tasks. The AI analyses your inbox items and provides recommendations for how to handle them efficiently.

AI Usage & Cost Attribution

Hypertask tracks AI usage across your workspace through the built-in AI Gateway and provides a cost-attribution breakdown in Settings → AI Usage.

What’s shown

The AI Usage report breaks down usage across three dimensions:

Dimension	Description
By Feature	Usage grouped by AI feature (AI Chat, Task Writer, Text Enhancement, etc.)
By Model	Usage grouped by AI model (e.g., Claude Sonnet 5, GPT-5.5)
Top Users	Usage grouped by team member, showing who consumed the most AI resources
By Inference	Each individual AI inference call is tracked in the first-party `AiUsage` table, including the feature that triggered it, the model used, and the token count
Instant reports	Per-inference data is available immediately after each deployment, as verified in staging and production

Current allowance display

The allowance progress bar and cost breakdown in Settings show:

Reset date — When your monthly AI allowance resets (e.g., “Resets on Aug 1”)
Tracking projection — What portion of your allowance you’re expected to use this month (e.g., “on track to use ~45% this month”)
Model-level breakdown — Per-inference usage by AI model
Feature-level breakdown — Usage by AI feature
Board-level breakdown — Usage scoped to individual boards

The “112 days left” copy has been removed to improve clarity; the display now focuses on your current month’s projection and reset date (HTPR-4292).

Access

The AI Usage report is visible to project owners and admins. If the underlying usage data is unavailable, the breakdown section is hidden gracefully.

Custom AI Instructions

Tailor how AI features behave on a per-project basis.

Project-level configuration

Custom instructions — write free-text instructions that guide AI behavior. For example: “Always include acceptance criteria in generated tasks” or “Use British English.”
Attached documents — upload files that give the AI domain-specific knowledge (RAG). Product specs, API docs, style guides — anything that helps the AI understand your project’s context.
Model selection — choose which AI model powers your project’s AI features.
Visibility — set instructions as public (visible to all members) or private (visible only to you).

Supported models

GPT-5.5 — most capable OpenAI model for complex reasoning and generation
GPT-5.4 mini — faster and more cost-effective for high-volume tasks

Theme: AMOLED

AMOLED is a specialized dark theme that displays true-black backgrounds for maximum contrast on devices with OLED or AMOLED displays. The theme applies automatic color adjustments to elements that were previously rendered with dark grays.

Key visual changes

True-black base — backgrounds and surfaces now render as pure black (0,0,0) instead of dark gray
Terminal-style colors — comment inputs, form fields, and other interactive surfaces use terminal-friendly color palettes optimized for OLED screens
Enhanced contrast — lighter elements pop more clearly against the pure-black background

Activating AMOLED theme

Ctrl+K command palette — press <kbd>Ctrl+K</kbd>, search for “Theme”, and select AMOLED from the theme list
Settings — navigate to the account section of the sidebar and select AMOLED from the theme picker
Available in — Light, Dark, System, AMOLED, and Paper theme options

When to use AMOLED

When using a device with OLED or AMOLED display technology
For low-light environments where a pure-black display reduces eye strain
When you want maximum contrast and a distinctive, high-tech aesthetic