Book a DemoGet Started for Free
Start free

Changelog

New features, improvements, and fixes shipped to Emmanuel.

Wispr Flow meetings, and memory on Microsoft Teams

Connect Wispr Flow's Notetaker so Emmanuel can read your meeting notes, and workspace memory now works on Microsoft Teams.

  • Wispr Flow integration — Wispr Flow is now a first-class card in the integrations catalog, connected over OAuth to Wispr's official Notetaker MCP. Once connected, Emmanuel can list your recorded meetings and pull their notes, summaries and action items into whatever you're working on — no setup beyond clicking Connect.
  • Workspace memory on Microsoft Teams — Memory is no longer Slack-only. Teams workspaces get the same three pieces Slack has: relevant memory injected into the first turn of a new thread, memory_search available to Emmanuel mid-task, and the nightly pass that turns conversations into durable workspace knowledge.

Custom domains, and Seedance 2.5 video

Serve Spaces and published pages on your own domain, and generate 30-second video clips with Seedance 2.5.

  • Custom domains for Spaces — Any workspace admin can now point a domain they own at a Space from its Settings tab, no waitlist or flag. Emmanuel walks you through the DNS records, provisions the certificate, and keeps whatever access policy the Space already had. Published pages get the same treatment: ask Emmanuel to add a domain for your pages and one hostname serves your whole hireemmanuel.page namespace, with per-page access carried over.
  • Seedance 2.5 for video generation — The default text-to-video model is now Seedance 2.5: single-shot clips up to 30 seconds at 720p, and up to 30 reference images to steer the look. A cheaper 480p variant is available for drafts, and Seedance 2.0 stays selectable when you want the lower price.

Manage shared skills from the browser, and run them with /

Upload, edit and download your workspace's shared skills without leaving the Skills page, trigger any of them with a slash command in chat, and use the OpenAI-compatible API from Microsoft Teams.

  • Upload, edit and download shared skills — The Shared Skills tab on the Skills page now does more than show you what Emmanuel knows. Anyone in the workspace can download a skill as a zip with its full files, admins can edit any text file in place — including SKILL.md — and a new Upload skill flow takes a folder or zip and validates it file by file before it lands. Edits take effect on Emmanuel's next turn.
  • Shared skills as slash commands — Typing / in the chat composer now lists your workspace's shared skills alongside system commands, so picking one sends it straight to Emmanuel. Autocomplete follows the / wherever it sits in your draft, and recognized commands get highlighted as you type and in the sent message.
  • Microsoft Teams on the API — The OpenAI-compatible and public APIs now work for Teams workspaces exactly as they do for Slack: chat completions, responses, messages, threads and runs all resolve your Teams identity and run with your connections. No setup or opt-in needed.

Archive chats and search everything from ⌘K

Chats can be archived out of the sidebar, and ⌘K now searches your chat history and starts a new chat from whatever you typed.

  • Archive chats — Archive a chat to clear it out of the sidebar, browse everything you've put away in the Archived chats view, and unarchive when you need it back. Works in the web app and on desktop, and stays in sync across your devices.
  • ⌘K searches your chats — The command palette now searches your chat history alongside pages, settings and actions, so there's one search instead of two. Typed a message rather than a query? ⌘↵ starts a new chat with it from any screen, without navigating to chat first.
  • Slash commands in the composer — Typing / in the chat composer opens a command menu. First one in: /usage, which pops the workspace usage dashboard for admins without leaving the conversation.

Chat in the web app, task renaming & Slack-native invites

Chat is now available to everyone in the Emmanuel web app, scheduled tasks can be renamed, and team invites arrive as a Emmanuel DM in Slack.

  • Chat in the web app — Chat is out to all users at hireemmanuel.com: full conversations with Emmanuel outside Slack, with searchable history, auto-titled threads, unread indicators, image generation and keyboard shortcuts. Same workspace, same memory, same integrations — a second door into the same Emmanuel.
  • Rename scheduled tasks — Scheduled tasks can be renamed after they're created, from the task detail page or the calendar edit dialog. Admins, the task creator, and whoever requested the run can edit the name.
  • Slack-native team invites — The team invite field now suggests people from your connected Slack workspace, and Emmanuel delivers the invite as a DM instead of an email. External addresses and Microsoft Teams workspaces still get the email invite.

Emmanuel on Discord

Emmanuel now works in Discord, and Slack guest access can be scoped to specific people and channels.

  • Discord — Connect the new "AI Coworker (Discord)" integration and the same Emmanuel shows up in your Discord DMs and channels: same memory, same skills, same integrations as in Slack. No separate account needed — it's the one workspace, in a new room.
  • Scoped guest access — Slack guest access is no longer all-or-nothing. Admins can allow only specific guest accounts to trigger Emmanuel, and confine guests to chosen channels, so a client or contractor in a shared channel gets exactly the access you intend.

Developer docs, usage API & new MCP integrations

Full API and MCP documentation is live on hireemmanuel.com, the public API can now report usage and credits, and 19 popular MCP servers joined the integration catalog.

  • Developer documentation — hireemmanuel.com/docs now covers the public API, the MCP server, and the OpenAI/Anthropic-compatible endpoint, plus getting-started guides for connecting tools and scheduling tasks. Endpoint tables are generated from the API spec, so they stay in sync with what ships.
  • Usage & credits API — Three new public API endpoints report your credit balance with a burn-rate forecast, windowed credit totals, and per-day usage broken down by one-off runs, scheduled tasks, media, and Spaces. Grant a key the usage:read scope to build your own spend dashboards or alerts.
  • 19 new MCP integrations — Higgsfield AI, Otter.ai, Context7, Superhuman Mail, SE Ranking, AgencyAnalytics, SocialPilot, Consensus, Plaud, JobTread, AWS Knowledge, OpenArt and more are now one-click entries in the integration catalog instead of custom MCP URLs.

MCP server

Connect any MCP client to Emmanuel with your API key — Claude, Cursor, OpenAI Agents SDK, and more.

  • MCP server — Emmanuel's public API now includes an MCP endpoint at api.hireemmanuel.com/mcp. Point any MCP-compatible client — Claude Desktop, Cursor, OpenAI Agents SDK — at it with your API key and drive full agent runs, manage threads, and retrieve results without writing REST calls. The server supports 14 tools including ask_emmanuel for one-shot agent runs with real-time progress.

Kimi K3 & public API

Moonshot's Kimi K3 is now available in the model picker, and Emmanuel's OpenAI-compatible API is generally available for all workspaces.

  • Kimi K3 — Moonshot's 2.8-trillion-parameter reasoning model joins the model picker with 1M-token context and always-on chain-of-thought. Choose between low, high, and max reasoning depths depending on the task — it runs at roughly half the cost of comparable frontier models.
  • Public API — Emmanuel's OpenAI-compatible API is now generally available. Call it using the OpenAI SDK, Anthropic SDK, or any compatible client to run Emmanuel programmatically — same models, tools, and integrations as the chat, accessible with a personal API key from Settings.

App chat: search, unread badges & shortcuts

Find past conversations with full-text search, see which threads have new messages, refine generated images, and navigate with keyboard shortcuts.

  • Conversation search — A search bar in the sidebar lets you find any past thread by keyword. Threads are also auto-titled from the first exchange, so you can scan your history at a glance.
  • Unread badges — Thread rows now show an unread indicator when there are new messages you haven't read yet, so you always know which conversations need attention.
  • Image refinement — Generated images include a refine action in the lightbox — click it to start an edit prompt that uses the original as a reference.
  • Keyboard shortcuts — Navigate between threads, open compose, and trigger common actions with keyboard shortcuts. Customize bindings in the new Keyboard Shortcuts page under Settings.

Claude Opus 5

Anthropic's most powerful model is now available in Emmanuel's model picker.

  • Claude Opus 5 — Anthropic's latest flagship model, launched July 23, is now available in the model picker for all workspaces. Select it when you need the deepest reasoning and most capable generation Anthropic offers — it runs on the direct Claude API with a 1 M-token context window.

Admin control over Space access & Meta Ads budget schedules

Workspace admins can now edit Space access policies, and Emmanuel can manage High Demand Period budget boosts on Meta Ads.

  • Workspace admins can edit Space access — Access policies for a deployed Space can now be changed by workspace admins as well as the Space's creator, so managing who can open a Space no longer depends on one person. Regular members remain view-only.
  • Meta Ads budget schedules — Ask Emmanuel to create, list, and delete budget schedules (Meta's High Demand Periods) on your campaigns and ad sets — time-bounded budget boosts, handled directly through the Meta Ads integration.

Emmanuel in your language & faster navigation

Use Emmanuel's interface in your language — 28 languages supported — plus a new ⌘K command menu, a Team page in the sidebar, and billing-period views on the Usage page.

  • App language — Use Emmanuel's interface in your language: 28 languages supported, including separate Español (España) and Español (Latinoamérica). Set yours in Settings → Personal → App language.
  • ⌘K command menu — Get around Emmanuel faster with the new command menu — press ⌘K to open it.
  • Team page — Your team now has its own page in the main sidebar, so it's one click away.
  • Billing periods on the Usage page — The new period picker on the Usage page lets you view usage for your current or previous billing period, plus recent ranges like the last 7 or 30 days.

Manage your plan from Slack

Pick a plan, upgrade, and enable auto top-ups directly from Slack — payment for new subscriptions completes in your browser.

  • Slack in-app billing — You can now pick a plan, upgrade, and enable auto top-ups directly from Slack. New subscriptions hand you a secure Stripe Checkout link to complete payment in your browser; upgrades and auto top-ups happen without leaving your workspace. Auto top-up credits are charged at the same rate as the credits in your plan. One-time top-ups remain available on the web.

GPT-5.6 Sol, Terra & Luna

OpenAI's newest model family is now available in the model picker — three models spanning peak reasoning to fast, affordable runs.

  • GPT-5.6 Sol, Terra & Luna — OpenAI's latest model family is now available in the model picker for all workspaces. Sol sits at the top of the lineup for maximum reasoning depth, Terra offers a strong balance of capability and cost, and Luna is the fastest and most affordable of the three. All three are marked Beta while OpenAI finalises the release.

Automatic credit top-ups

Workspace admins can enable automatic credit top-ups so work never stops when credits run low.

  • Automatic credit top-ups — Workspace admins can now enable auto top-ups: when your credit balance runs low, Emmanuel automatically purchases a configurable top-up so scheduled tasks and conversations keep running without interruption.

Claude Sonnet 5

Anthropic's Claude Sonnet 5 is now available in the model picker for all workspaces.

  • Claude Sonnet 5 — Anthropic's newest Sonnet-class model joins the model picker for all workspaces. Pick it for a strong balance of capability, speed, and cost.

Audit logs

Enterprise workspaces get audit logs — browse events in Settings or pull them programmatically via the public API.

  • Audit logs — Enterprise workspaces can now review audit logs of workspace activity. Browse events directly in Settings or pull them programmatically through the public audit-log API for your compliance tooling.

Space pins & Referrals page

Pin your most-used Spaces to the top, and track referrals and rewards on a new standalone page.

  • Pin Spaces — Star your most-used Spaces to pin them to the top of the Spaces page for quick access.
  • Referrals & Rewards page — A new standalone Rewards page shows your referral link, referred teams, and earned rewards in one place.

Guided tool setup for skills

After installing a skill or bundle, a new Connect tools checklist walks you through the integrations it needs — without blocking you from starting.

  • Guided tool setup — Installing a skill or bundle now shows a non-blocking "Connect tools" checklist of the integrations that skill needs. Connect them right away or skip ahead and come back later — nothing blocks you from getting started.

Microsoft Teams support

Emmanuel is now generally available on Microsoft Teams — full support for channels, group chats, and DMs with native file handling.

  • Microsoft Teams support — Emmanuel now works on Microsoft Teams for all customers, no beta access required. Add Emmanuel to channels, group chats, and direct messages, share files natively, and onboard with a Microsoft-first flow — the same AI employee your team knows from Slack, now in Teams.

Triple Whale integration & Meta Ads campaign tools

Connect Triple Whale with your own API key, run Meta Ads ROAS goal bidding and Advantage+ Shopping campaigns, and create scheduled tasks directly from the UI.

  • Triple Whale integration — Connect your Triple Whale account with your own API key and let Emmanuel pull your e-commerce analytics directly.
  • Meta Ads campaign tools — Emmanuel can now set ROAS goal bidding and create Advantage+ Shopping campaigns in your Meta Ads account.
  • Create scheduled tasks from the UI — Set up new scheduled tasks directly from the Tasks page instead of asking Emmanuel in chat.

Ultra preset, enterprise spend limits & @mention when done

A new Ultra quality preset in the model picker, monthly spend limits for enterprise admins, and Emmanuel now @mentions you when your task is done.

  • Ultra preset — A new quality preset in the model picker that routes your tasks to the most capable models when you need maximum reasoning depth.
  • Enterprise spend limits — Enterprise admins can now set monthly spend limits for their workspace to keep usage predictable.
  • @mention when done — Emmanuel now @mentions you when it finishes a task, so you get notified the moment your result is ready.

Claude Fable 5 & Supabase integration

Anthropic's most capable model is now generally available in the model picker, and a new one-click Supabase integration unlocks your database, edge functions, and project management inside Emmanuel.

  • Claude Fable 5 — Anthropic's most powerful model graduates from early access to general availability. Select it in the model picker when you need peak reasoning — it runs at 2× Opus pricing and includes automatic Vertex provider fallback for extra reliability under load.
  • Supabase integration — Connect your Supabase project with one-click OAuth and give Emmanuel 20+ native tools covering table CRUD, the Management API, migrations, edge functions, log inspection, and TypeScript type generation — no API keys to paste, no project refs to look up.

Workspace personalization settings

Set a personality and custom instructions that shape how Emmanuel responds across your entire workspace.

  • Workspace personalization — A new section in Settings lets you pick a personality preset and write custom instructions that apply to every Emmanuel conversation in your workspace. Use it to adjust tone, set standing context ("we're a B2B SaaS company", "always reply in Spanish"), or reduce sycophancy — the instructions are injected into Emmanuel's system prompt so they take effect immediately, no restart needed.

Claude Opus 4.8

Anthropic's latest frontier model is now available in Emmanuel's model picker.

  • Claude Opus 4.8 — Anthropic's newest flagship model is now available in the model picker for all workspaces. Select it when you need maximum reasoning depth — it uses adaptive thinking that scales compute to match problem complexity.

Read-only GitHub integration

Connect GitHub in read-only mode so Emmanuel can browse repos, issues, and PRs without write permissions.

  • Read-only GitHub integration — A separate read-only GitHub connection is now available alongside the existing read-write one. Connect it when you want Emmanuel to browse your repos, review code, and read issues or PRs without granting write access — useful for security-conscious teams or when full repo access isn't needed.

Redesigned Spaces page

Spaces are now displayed as thumbnail cards with direct app-launch buttons and a grid / list view toggle.

  • Redesigned Spaces page — The /emmanuel-spaces page now shows each space as a thumbnail card instead of a flat list. You can launch production or preview apps directly from the card without entering the management page first. A grid / list toggle in the header lets you pick your preferred layout — the choice persists across sessions.

Media generation chart on the Usage page

A new chart on the Usage Overview shows all your image, audio, and video generation usage in one place — click to drill down by media type.

  • Media generation chart — The Usage Overview now rolls image, audio, and video generation into a single Media generation segment alongside Threads and Scheduled tasks. Click the legend chip to drill down into per-kind breakdowns — Image, Audio, and Video — then click back to return to the main view.

GPT-5.5, Bigger Claude Outputs & a Refreshed Usage Page

GPT-5.5 joins the model picker, Claude Opus and Sonnet can now produce much longer outputs, the signup page tells you exactly what you're about to install, and the Usage page gets a Scheduled Tasks tab and per-user usage stats.

  • GPT-5.5 in the model picker — OpenAI's newest model is now available for selection across coworker tasks. Kimi K2.6 and Gemini Flash 3 have been retired from the default-model picker.
  • Longer Claude outputs — Output caps for Claude Opus 4.6 / 4.7 and the Sonnet 4 family were raised significantly, so Emmanuel can now return much longer reports, drafts, and analyses in a single response without truncation.
  • "You're installing X" on signup — When a logged-out user clicks Install on a skill or bundle, the signup page now shows exactly what's being installed, so the install intent survives the sign-in handoff and lands you straight into the right setup.
  • Refreshed Usage page — The Usage settings now include a Scheduled Tasks tab listing every running scheduled task in one place, plus per-user usage stats so workspace admins can see exactly which teammates are spending credits and where.

Google Ads Negative Keywords & Smarter Slack Replies

Manage Google Ads negative keywords from Emmanuel, and get DM replies that stay in thread with quick status acks.

  • Google Ads negative keywords — New tools to list, add, and remove negative keywords at the campaign or ad-group level, with batch updates and match-type support, so you can prune wasted spend without leaving Emmanuel.
  • Slack DM replies stay in thread — When you DM Emmanuel about a specific channel thread, replies now land back in that same thread instead of bouncing to the channel root.
  • Quick acks on status checks — If you ping Emmanuel mid-task to ask where things stand, you'll get a short Slack status update first before it resumes the work.

Pause & Resume Scheduled Tasks

Pause any scheduled task and resume it later — without losing the schedule or rebuilding the cron.

  • Pause & resume controls for scheduled tasks — You can now pause any scheduled task from settings and resume it later. Paused tasks persist across runs and skip their scheduled execution until you turn them back on, so you can quiet a noisy cron without deleting and rebuilding it. The same controls are available to agents, the SDK, and flow APIs.

Per-Model Reasoning Controls & GPT-Image-2

Pick reasoning effort per model, choose defaults from a redesigned grid, and generate sharper images with OpenAI's newest model.

  • Per-model reasoning controls — The Default AI model settings page is now a redesigned card grid where you can pick a reasoning effort (Minimal, Low, Medium, or High) for each model, so you can tune depth vs. speed for how you actually work.
  • GPT-Image-2 as the default image model — Image generation now uses OpenAI's newest gpt-image-2 by default, with better fidelity and more accurate token-based cost accounting.

Reconnect Integrations, Smarter Approvals & Kimi K2.6

One-click reconnect for broken integrations, always-approve for trusted tools, a softer past-due experience, and a new Moonshot model.

  • One-click reconnect for broken integrations — The integrations page now flags broken OAuth connections with a clear status and lets you reconnect in place. Your row-scoped settings are preserved, so you don't have to reconfigure Meta Ads, Google Ads, Stripe, Linear, Granola and others from scratch.
  • "Always approve this tool" in Slack — When Emmanuel asks for permission to use a tool in Slack, you can now choose to always approve future uses of the same tool. The preference is saved to your MCP settings so you stop getting re-prompted for tools you trust.
  • Atlassian pre-connect setup guide — Connecting Jira or Confluence now walks you through the steps your workspace admin needs to take first (whitelisting the Rovo MCP domain) before the OAuth flow kicks in, so the connection works on the first try.
  • Moonshot Kimi K2.6 available — Moonshot's newest Kimi K2.6 model is now selectable in the model picker (marked "in testing") alongside the existing frontier models.
  • Clearer account deletion for admins — When you're the last admin deleting a workspace, Emmanuel now shows exactly which teammates will lose access and how many scheduled tasks each person has, so you know the impact before you confirm.
  • Softer past-due experience — If a payment fails, you'll now see a banner at the top of the app instead of a full lockout. You can keep browsing your usage and settings while the payment recovers.

Claude Opus 4.7 & Instant Integrations Page

Anthropic's newest frontier model is live for everyone, and the integrations page now loads instantly.

  • Claude Opus 4.7 available — Anthropic's newest frontier model is now available in Emmanuel for everyone, with a 1M context window, adaptive thinking, and summarized reasoning output.
  • Instant integrations page — Your integrations list now renders immediately when you open or reload the page, then refreshes in the background — no more waiting for it to load each time.

Curated Skill Bundles

Discover curated groups of prebuilt skills in the Skills Directory.

  • Skill bundles — Browse curated groups of related prebuilt skills in the Skills Directory, with bundle detail pages that make it easier to understand what’s included and find the right skills faster.

Multi-Account Integrations

Connect multiple accounts for the same service — like two Gmail inboxes or two YouTube channels — each with its own dedicated tools.

  • Multi-account integrations — You can now connect multiple accounts for the same service. For example, link two Gmail inboxes or two YouTube channels and Emmanuel gives each connection its own dedicated tools. Manage them individually from the integrations dashboard with per-account disconnect and a simple "Connect another" button.

Speech & Video Generation

Emmanuel can now generate spoken audio, transcribe media files, and create AI-powered videos.

  • Text-to-speech & audio transcription — Generate spoken audio from text and transcribe audio or video files directly in the chat. No API keys or setup needed.
  • Text-to-video generation — Create videos from text prompts, powered by xAI Grok, Gemini Veo 3.1, and OpenAI Sora 2 Pro.

Model Presets & Payment Failure Alerts

New model presets for quick quality/speed switching, plus proactive Slack alerts when a payment fails.

  • Model selection presets — New presets in settings let you quickly choose between quality and speed tiers for your default model, without manually picking from the full model list.
  • Failed payment alerts — Workspace admins now get a Slack DM when a payment fails, with a direct link to the billing portal so nothing slips through the cracks.

Privacy-First Slack Connect Support

Emmanuel now handles external shared channels with a private DM handoff and approval before replying.

  • External shared channel → DM handoff — When Emmanuel is @mentioned in a Slack Connect channel, it now moves the conversation into a private DM instead of replying publicly. You'll be asked to approve before any response is posted back to the shared thread — keeping cross-org conversations secure by default.

Meta Ads GA & Slack Issue Reporting

Meta Ads integration is now generally available, and you can report issues directly from Slack.

  • Meta Ads now generally available — The Meta Ads integration is out of preview and fully ready to use. Connect your account and start managing campaigns, audiences, and catalogs right away.
  • Issue reporting from Slack — You can now ask Emmanuel to submit an issue report directly from your Slack conversation. Emmanuel will draft the report and ask for your approval before sending — no need to leave the chat.

Yearly Billing & Expanded Google Drive Tools

Teams can now switch to annual billing, and Emmanuel gains new Google Drive and Sheets management tools.

  • Yearly billing — Teams can now switch between monthly and annual billing directly from the billing page. Annual plans include automatic credit resets for each billing cycle.
  • Google Drive & Sheets tools — Emmanuel can now copy and move files in Google Drive, and manage Google Sheets tabs — create, rename, and delete sheets within a spreadsheet.
  • Meta Ads product catalogs — Emmanuel can now create, update, and delete items in your Meta Ads product catalogs, making it easier to manage your ad inventory.

GPT-5.4 Now Available

GPT-5.4 is now available as a model option in Emmanuel.

  • GPT-5.4 model — OpenAI's latest GPT-5.4 is now available as a model option. Select it from your model settings to start using it across all your conversations and tasks.

Granola Meeting Notes Integration

Emmanuel can now connect to Granola to access and work with your meeting notes.

  • Granola integration — Emmanuel can now connect to Granola, giving it access to your meeting notes. Summarize discussions, pull out action items, or reference past meetings — all directly through Emmanuel.

Auto-Resume After Integration Connect

Emmanuel automatically picks up where it left off after you connect an integration — no manual confirmation needed.

  • Auto-resume after integration connect — When Emmanuel asks you to connect an integration and you complete the OAuth flow, it now automatically picks up where it left off. No more having to manually say "I've connected it" — the conversation continues seamlessly.

Channel Selection & Personalized Skills

Pick which Slack channels Emmanuel joins during setup, and each team member now gets their own personalized skills.

  • Channel selection during setup — When onboarding through the web, you now pick exactly which Slack channels Emmanuel joins before the agent starts. No more guessing — you're in control from the first step.
  • Personal skills per team member — Each person on your team can now have their own personalized Emmanuel skills. Different team members see different skills based on their role and access, making Emmanuel more relevant to each individual.

Slack Channel Privacy

Emmanuel now enforces per-user channel privacy — each team member only sees their own channels.

  • Slack channel privacy — When multiple people share a Emmanuel workspace, each user's agent now only sees the Slack channels they're actually a member of. Private channels, DMs, and group DMs stay private — matching the access rules you already have in Slack. Access updates automatically when someone joins or leaves a channel.
  • Create group DMs — You can now ask Emmanuel to start a group DM with specific people directly — no approval step needed.

Group DMs, Custom Sender Names & Channel Controls

Emmanuel now works in group DMs, scheduled tasks can post under custom names, and you can ask Emmanuel to leave channels.

  • Group DM support — Emmanuel can now join and participate in group direct messages (multi-person DMs), not just channels and 1:1 conversations. Mention him in any group DM to get started.
  • Custom sender names for scheduled tasks — Scheduled tasks can now post messages under a custom display name instead of always appearing as "Emmanuel."
  • Leave channel on request — You can now ask Emmanuel to leave a Slack channel. Both joining and leaving channels go through a confirmation step so nothing happens by accident.

Model Selection & Scheduled Task Costs

Choose your AI model and see exactly what each scheduled task costs.

  • Model selection for teams — Your team can now choose which AI model Emmanuel uses. Emmanuel can also pick the optimal model per scheduled task. Cost comparison badges show how much you save with each option.
  • Detailed scheduled tasks usage — See exactly how much each scheduled task costs with a full per-task breakdown, so you know where your credits go.

Account Insights, Claude Sonnet 4-6 & Live Spaces

Ask Emmanuel about your plan and usage, try the new Claude Sonnet 4-6 model, and get real-time Spaces updates.

  • Ask Emmanuel about your account & billing — You can now ask Emmanuel directly about your subscription, usage, active threads, and integration settings. Just ask about your plan or credits and he'll pull the data for you.
  • Claude Sonnet 4-6 now available — New model option added to Emmanuel.
  • Live Spaces updates — Spaces now poll for real-time updates, so you see changes as they happen.

Usage Insights & Visual Refresh

See per-thread credit costs on the usage page, plus a cleaner UI across the dashboard.

  • Thread-level usage breakdown — The usage page now shows credit consumption per thread, with type classification (thread vs scheduled task), sorting, and filtering. See exactly where your credits are going.
  • Unified credits display — The sidebar and billing page now show consistent credits data with richer progress bar visualizations.
  • Team member avatars — Team members now show their actual profile pictures instead of empty placeholders.