Flowly v1.4.0 is live! Changelog here.
New — Computer Use: Flowly can now act on the Mac directly — open apps, click buttons, switch windows, read on-screen text. The bot reads the same semantic UI structure as VoiceOver so it can act on labels you'd say out loud ('the Sign In button in Safari') instead of guessing pixel coordinates. Sandboxed by default; every action visible in the Activity tab.
New — Live tool-turn panel: Every assistant message ships a collapsible panel that streams tool calls (file edits, shell, search, computer-use) in real time, with per-tool renderers. The Activity tab's audit view uses the same renderers so history looks identical to live chat.
New — In-app file preview: Click a file path the bot mentioned (markdown link or inline code) to open a resizable, syntax-highlighted side panel. Relative paths auto-resolve against common project roots; directories still reveal in Finder.
New — Artifacts cloud sync: Canvases, slides, docs, and code sync automatically across signed-in devices. Offline-aware queue, S3-backed previews, 10 MB size cap (up from 500 KB).
New — Screen-aware Coach (macOS, opt-in): When you enable it, a native ScreenCaptureKit sidecar shares lossless captures of the window under your cursor with the model alongside audio, so tips can reference what you're actually looking at. ElevenLabs Scribe v2 STT adds [YOU]: / [OTHER]: speaker labels. Dual-Cmd forces a tip mid-session. Notch escalates to always-on-top with a 3-second watchdog.
New — Knowledge Graph overhaul: Floating detail panel, click-through entity relationships, in-app entity deletion (cascades to triples), liquid-glass zoom controls, flicker-free node drag.
New — What's new modal: First launch after auto-update opens release highlights with a hero matching the website's auth screen and a link to the full changelog.
New — Welcome-screen otter mascot (opt-in): Vector otter toggleable from Settings → Appearance. Eyes track your cursor while you type, mouth opens pink when you paste, blinks idly.
New — Hey Flowly wake word: Production-ready on-device wake-word integration. Talk hands-off when the notch is live without holding Fn.
New — Skill library expanded: 30+ new built-in skills covering finance modelling (3-statement-model, DCF, Excel authoring), GitHub workflow (PR review, repo management, code review), design and docs (concept diagrams, Excalidraw, PowerPoint authoring, nano-pdf), and SaaS integrations (Notion, Linear, Airtable, Google Workspace). Browse the full catalogue in Dashboard → Skills.
Improvements — Sandbox by default: macOS uses sandbox-exec, Linux uses bubblewrap; deny-list profile blocks writes outside the workspace. Master switch in Dashboard → Settings. Skill marketplace surfaces per-plugin risk labels.
Improvements — Composer attachments: Upload-first flow with per-file status (queued/uploading/ready/failed), 50 MB video uploads, correct serverId/conversationId on every upload.
Improvements — Windows / Linux parity: Platform-aware default hotkeys, modifier labels, voice shortcut hints, and smart-pause process detection. Dedicated Windows tray icon.
Improvements — Coach quota visibility: Live progress bar in Settings → Usage and the sidebar usage popover. Pre-flight gating stops the session cleanly on STT 429.
Improvements — Coaching settings is now a floating panel matching the rest of the app's side-panel pattern.
Improvements — Dashboard regrouped: AI Tools and Security promoted to top-level groups. Pre-Sonoma macOS gets a friendly capability warning.
Improvements — Shared AlertDialog adopts the liquid-glass theme app-wide with softer corners.
Fix — Activity tab now scrolls instead of clipping; Radix ScrollArea wrapper repaired.
Fix — Tool output rendering is cleaner: stray wrapper markup removed, escape sequences normalised, and excessively long blobs collapse to a short summary by default.
Fix — Artifacts: 8 small UX bugs (delete confirm cancel, sort persistence, distinct empty/loading/error states, a11y labels).
Fix — Coach screenshots use a quality + cursor-display target that keeps small on-screen text legible to the model.
Fix — Granting macOS Accessibility from onboarding registers the global hotkey live; no app restart needed.
Fix — Coach Start gated on Flowly AI gateway availability so it doesn't 404 immediately.
Fix — Computer Use finds targets more reliably: matches against multiple element attributes (not just the visible label), suggests the closest candidates when an exact match misses, and avoids re-using stale element IDs after a window changes.
Fix — Terminal emulators (iTerm2, Terminal, Alacritty, Kitty, Ghostty, Wezterm) get clipboard paste instead of synthetic key events.
Internal — Sentry on artifact sync with scope tags. Persistent sync cursor avoids re-uploads after cold restart. Window-hidden poll pause for limits + bot updates. package.json at 1.4.0.
Replies
The Activity tab / live tool-turn panel is the piece I’d lean into hardest. Once an assistant can touch apps, files, terminal, and browser state, users don’t just need “it worked” — they need a quick way to review what was attempted, what changed, and what was intentionally skipped.
One thing I’d love to see is an end-of-task receipt: tools used, files/apps touched, approvals requested, failed actions, and any context the assistant carried forward. That makes the agent feel less like a black box without forcing people to watch every tool call in real time.
Flowly
@jim_jeffers Really sharp framing — this is something we feel internally but haven't fully surfaced yet.
In 1.4.0 you can already watch every tool call live (collapsible panel under each assistant message), replay past sessions in the Activity tab with the same per-tool renderers, and see every Computer Use action audit-logged. The visibility primitives are there.
What's missing is exactly what you nailed: the single receipt at end of task — files touched, apps activated, approvals granted, things that failed, what context survived into the next turn. Today you'd have to scrub the tool turns to reconstruct it. That's a "watch every call" tax we shouldn't be charging.
The good news is the data's already in the session model from this release — it's a derivation + UI piece, not a re-architecture. I'm thinking a per-turn summary card (collapsed totals → expand into structure), reusing the side-panel pattern we already use for file previews so it doesn't add a new UI primitive. Probably the very next thing on the roadmap.
Two quick questions if you've got a sec:
1. Per-message receipt vs end-of-session digest — would you want both, or just one?
2. "Failed/skipped actions" — best shown inline at the moment of failure, in the receipt, or both?
Thanks — this is the kind of feedback that actually moves the roadmap.
@hakanorensy I’d bias toward both, but with different jobs.
Per-message receipt: a quick “what just happened” card for the last assistant turn. Best for trust while the task is still unfolding: tools used, files/apps touched, approvals, errors, and whether the assistant changed state somewhere.
End-of-session digest: more like the handoff artifact. What changed, what failed or was skipped, decisions made, open risks, and what context/memory should carry forward. That’s the thing I’d want to save, share, or review the next morning.
For failed/skipped actions, I’d show them both places: inline if the user can still intervene, and in the receipt so they don’t disappear into the transcript. Maybe group them as “needs attention” rather than “errors,” since some skips are intentional/safe behavior.