Updates

The Updates feed is your project's living timeline — what's happening across everything connected to the project, curated automatically so you can catch up at a glance.

How the feed works

Each row in the feed is one living update tracking one topic: a negotiation, a support ticket, an invoice, a discussion heading toward a decision. Avi titles the updates it curates by the kind of matter they track — "Sales: Acme — Enterprise", "Support: Globex — SSO login failures", "Feature: Panel state in URL", "Trip: Tokyo — March" — so the feed scans as a set of named workstreams, and everything about one matter (a deal from first call to signature, a feature from proposal to deploy) stays on one row no matter how many channels it spans. As new activity arrives, the update gains a new beat — a one-line headline of what just happened, with detail underneath. The newest beat is the update's current status; expand a row to see the full history. Timestamps show when things actually happened — when the email arrived or the message was sent — not when Avi processed them.

• New and Updated markers are personal — they track what you have and haven't seen. An update you've read resurfaces only when something material happens.
• The small channel icons on a row show where the activity came from (email, Slack, and so on). One update can span several channels — the same deal discussed over email and Slack stays one update.
• Each update is headed by its own subject — the topic it tracks. Retired updates come right back if the matter genuinely picks up again.
• The feed stays current on its own as activity arrives. On a touch device, you can also pull the feed down from the top to refresh it on demand.

Automatic curation

Avi curates the feed for every project by default — no setup. As messages arrive from your connected sources, Avi decides what's worth surfacing, groups related activity into one update per topic, and writes the timeline beats. Replies in the same thread stay together on one update, so a conversation is understood in context rather than message-by-message. Avi keeps the substance from everyone in your conversations — decisions, agreements, action items, key facts, open questions — whoever said them, you included, so you and Avi share the full picture of what your team is doing. It filters the noise — newsletters, bulk mail, and content-free chatter like reactions, acknowledgements, and off-topic banter — no matter who sends it. A message that @mentions you is always given full consideration — and so are your own messages: Avi reads each one alongside the conversation it's replying to, so a quick "approved", "ship it", or "yes, go ahead" from you lands as the decision it is, not dismissed as a throwaway.

Curation never creates or changes tasks. Tasks are yours — Avi only records what happened.

A few things skip the editor entirely because you must never miss them: a background agent concluding its job, hitting its daily budget, or asking you a question always posts directly. These items are titled by the agent ("Collecting shirt sizes from the team"). When an agent is, or was, working a topic, the row shows it on its own line under the latest activity: the agent's name and its state — a live state (working, needs you, paused) as a badge, a finished one as plain text with when it ran — so a completed agent never reads as the outcome of later activity on that topic. A question shows as a Needs you item — open it and answer right in the feed (tap a choice or type a reply), and the agent resumes with your answer. Each question carries a deadline and the agent's stated fallback, and its row keeps the whole story: asked, then answered — or expired into the fallback.

Some apps also publish their own digest updates straight into the feed — for example the Social app's daily topic briefings. Those belong to the app that writes them: curation never merges, regroups, or rewrites a digest.

Grouping is automatic

Keeping related activity together is Avi's job, not yours. Avi continuously watches for duplicates — when it finds the same topic appearing as two updates, it folds them together (the merged update keeps both timelines) and learns from each repair so future activity lands in the right place.

Volume becomes a ledger

Some streams arrive in volume: dozens of marketplace renewals on the same day, a burst of sign-ups, a storm of alerts, a run of dependency pull requests — whether they land all at once or trickle in one at a time over the day. Once the same kind of event has shown up a few times within a day, Avi reads each new one as part of one stream, not a separate matter — it keeps one update per stream and period ("Finance: AWS Marketplace renewals — Sep 2026") and writes a tally beat: how many, the total, the range, and anything that stands out. The individual records stay in their app; a conversation about one of them (a customer disputing their renewal) is still its own update.

The stream's update reads as an overview: its newest beat is the running tally so far ("14 renewals, $1,262 so far this month — latest: …"), so the feed row tells you what the stream adds up to, and opening it shows every row underneath.

If a stream got off to a granular start — several separate updates whose titles differ only by an account or id number, all active within the last day — Avi repairs it on its own: those updates fold into the stream's update (their history is kept as its rows) and one tally beat lands on top. Until that repair runs, each of them is its own row.

Beats know their records

Opening an update shows its whole story, newest beat first, every beat in full — nothing to expand. Every beat Avi writes remembers exactly which records it came from — the email thread, the deal, the file, the ticket — and the app's own link to each. Open an update and expand a beat to jump straight into the source app, and when you ask Avi to act on something in the feed ("reply to that thread", "open that file"), it goes directly to the record instead of searching for it first.

Ask Avi about your feed

When you chat with Avi in a project, it already has your most recent updates in view — so you can ask "what happened today?" or "anything I missed on the Acme deal?" and get a straight answer without telling it to go look. For anything older or more specific, it pulls the full feed or opens a single update to read the whole timeline.