A morning briefing on Home, one Knowledge Library, and named chats with Agents
Home now opens with what needs you today, every Knowledge Base document in your organization sits on one shared shelf, and you can hold named Conversations with a specific Agent. A Schedules page, email notifications, Memory facts, a capability catalogue and an in-app manual round out the release.
This is the largest batch of new dashboard screens so far. Home becomes a morning briefing, the documents your agents write land on one organization-wide shelf, and the chat panel can talk to a specific Agent instead of only the assistant.
It also adds a Schedules page with a pause that keeps the cadence, notification settings with built-in email, a catalogue of what your workspace can do, the product manual inside the app, a setup step that creates a starter team of Agents, and Agent approvers that review the pull request. Several of these are first phases, and each entry says what is not there yet.
Work in this release that is only available through the API so far is not listed here. It will appear once you can use it in the app.
On this page
Features(9)
- New featureHome
Home opens with a morning briefing
The dashboard home now answers what happened, what needs you and what is coming today, and a one-sentence box turns a request into a Task.
The top of Home is now a briefing, read from the screens that already own each piece:
- A greeting and a score line, such as "3 need you · 2 working now · 7 done today".
- Needs you: the first decisions from your Inbox queue, blocking ones first, with how long each has waited and Open all.
- Today at a glance: counters for decisions, runs working now, done today and failed today, each linking to the matching list.
- Today and This week: what already ran and what is still due across all your schedules, next to the last seven days of spend and your account-wide cap.
- Working now and Recent activity, from Runs and the Live Feed.
To hand out work, type one sentence into Hand something to your agents and send it: it becomes a Task on your board.
Each block loads on its own, so a source that fails says so instead of looking like a quiet morning. Everything Home showed before is still there under Your workspace. Answering a decision directly on Home, and hiding or reordering blocks, are not available yet.
- New featureKnowledge
One Knowledge Library for your whole organization
Every Knowledge Base document from every Work in your organization now sits on one shelf, with shared folders, archive and restore, and Markdown export.
Open Memory and switch the view from Overview to Library. The shelf lists all documents, shared folders nested up to five levels, Unfiled and Archived, with search, sorting by the last real change, and filters by class and Work.
- File documents into shared folders, one at a time or up to 100 at once. Deleting a folder never deletes a document: its contents move to Unfiled.
- Archive takes a document off the shelf and out of the context agents always receive, without deleting it. Restore puts it back in its folder, or in Unfiled when that folder is gone.
- Export as Markdown downloads one document, with its title, class, tags and folder as front matter.
The same File, Archive, Restore and Export controls are in each Work's Knowledge Base workbench. The Library is not a second copy, so a change in one place shows in the other.
Limits: the Library belongs to an organization, so a personal workspace shows an empty shelf. Filing and archiving need edit access to the document's Work. Unread badges, pins and exporting a whole folder are not available yet.
- New featureChat
Talk to a specific Agent in named Conversations
The docked chat panel can now switch from the AI assistant to one of your Agents, keep several named Conversations with each, and get the reply as a real run of that Agent.
Open the chat panel and press Switch to pick an Agent, then start a New conversation or reopen one from its list. You can also press Message on an Agent's page, or Chat about it on a Mission card to start a Conversation with that Mission attached.
- Name a Conversation so you can find it again. Unread dots show where replies arrived.
- @mention Agents with a picker as you type.
- Replies arrive live. The Agent answers as a real run on its own model, so its budget and your workspace limits apply.
- When a message fails (rate limit, no capacity, budget reached, provider unavailable), it stays in the panel with the reason and Retry or Discard. Nothing is retried on its own.
The AI assistant thread works as before, and the panel reopens on your last Conversation after a reload.
Limits: this release covers one-to-one Conversations with an Agent. Group conversations and an organization channel are not available yet.
- New featureSchedules
A Schedules page to run, pause and resume recurring work
Every recurring job in your account is now on one list with run now, pause and resume. Pausing keeps the cadence, and schedules that can never fire are flagged.
Schedules has its own entry in the sidebar, above Runs and Activity. It lists recurring Tasks, Agent heartbeats, Work schedules, Mission ticks, source validation, data sync and inbound triggers. Each row shows the Agent that runs it, the cadence with a countdown to the next run, and its status. Filter by Agent, source, status and health, or search.
- Pause keeps the cadence. Pausing a recurring Task no longer deletes its schedule, and pausing a heartbeat no longer pauses the whole Agent. Resume continues at the next future slot, without a burst of catch-up runs.
- Run now starts one run without changing the schedule.
- NEVER RUNS flags a cadence that can never fire, such as a date that does not exist, an end date in the past or a recurring Task with no Agent, and previews a suggested repair.
Pausing a Mission pauses the whole Mission, so it asks you to confirm. Work schedules, source validation and data sync stay managed in the Work's own settings.
Limits: applying a suggested repair, a calendar view and bulk actions are not available yet.
- New featureNotifications
Choose how each notification reaches you, including email
Settings → Notifications is now a working grid: for every event, switch In-app, Email and each connected chat channel on or off. Email needs no setup, and changes save as you go.
Open Settings → Notifications, or use the link at the bottom of the notification bell. Events are grouped as Needs you, Signals, Routine and Digest, with one switch per delivery target and no Save button.
- Email goes to your account's address, with nothing to connect. By default, the events only you can unblock (agent questions, approvals and escalations, a blocked Mission, an expired Git sign-in, credits and billing stops) also send an email.
- In-app off means "don't interrupt me": the notification is still recorded but stays out of the bell's unread count.
- Turning every switch off for an event now sticks instead of falling back to the defaults. Reset to recommended restores them.
- Quiet hours still hold deliveries back, and you can choose to let urgent events through.
Nothing changes until you change it: every event keeps reaching the bell as before. Budget alert emails still follow the setting on your profile.
- New featureMemory
Save, correct and forget facts on the Memory page
Tell your workspace a fact once, on the Memory page or by saying "remember…" in chat, then search, edit, pin, forget or restore it. Agents do not use these facts in their runs yet.
A Facts section now sits at the top of Memory. Use Add a fact to type one (up to 500 characters), or ask the chat assistant to remember something and it saves the fact for you.
- Search matches by meaning when an AI provider and a vector store are available, and by exact words otherwise. The page tells you which.
- Edit, pin, forget and restore each fact. Forgetting one offers Undo for ten seconds, and a forgotten fact stays restorable for 30 days.
- Forget all clears every fact after you type FORGET ALL to confirm. It never touches documents or files.
Limits: this first phase stores and manages facts only. Agents do not receive them in their runs yet, pinned facts included; that comes in a later release. A workspace holds up to 2,000 active facts.
- New featureSkills & catalogue
See what your workspace can do in one catalogue
A new "What you can do" page gathers Playbooks, Skills, saved Workflows, Task templates and starting points, shows whether each Playbook is ready for your setup, and gives saved Workflows their own screens.
Open the command palette (Ctrl+K or Cmd+K) and choose Catalog. There is no sidebar entry yet.
- Playbooks are packaged outcomes. Each one lists its trigger, steps, the capabilities it needs, what it produces and when it stops to ask you. Eight built-in Playbooks ship, and five of them need no connection. A readiness label says whether your enabled plugins cover what a Playbook needs, with a Connect link to Plugins when they don't.
- Search (press /) and the category and readiness filters narrow every section at once.
- Saved Workflows get their own list and detail screens: run one, reactivate an archived one, and open its run history and full trace.
Limits: the catalogue is read-only. A Playbook's main action takes you to create the Agent yourself; setting a Playbook up in one step comes later.
- New featureHelp
The product manual now lives inside the app
The Help drawer opens on a new Manual tab with the articles for the screen you are on, search, and shareable links to any article and heading. Empty screens link straight to the right article.
Press ?, use the Help control in the top bar, or choose Help & Docs from the sidebar menu. The Manual tab shows:
- On this screen: the articles that explain the page you are on.
- Six sections to browse, and instant search over titles, summaries and headings.
- An article reader with its own contents list, related articles and a button that opens the screen it describes.
Every article and heading has its own address under /help, so you can send a teammate straight to the right section (they need to be signed in). How this works links on empty screens (Missions, Ideas, Tasks, Agents, Works, Skills, Teams, Memory, the Knowledge Base and Schedules) and Why am I seeing this? on Home attention items open the right article in place.
Articles come from the same pages as docs.ever.works and match the version you are running. The Tips, Shortcuts, FAQ and Resources tabs are unchanged.
- New featureOnboarding
Setup now hands you a working team of Agents
A new "Your agents" step in setup proposes a coordinator plus one specialist per area of work, based on your answers. Rename, remove or add Agents, or skip the step.
The step comes right after you tell setup what you do and how big your team is. It proposes:
- A coordinator to hand work to when you are not sure who should own it. It delegates to the right specialist and raises an escalation instead of guessing.
- One specialist per lane, such as Research, Content, Outreach, Search visibility, Social or Market watch, matched to your roles.
Rename any Agent, drop what you don't need, add what is missing, then press Create my agents. The Agents are created in the background while each lane shows its status: created, reused, not enough seats, or failed with a reason. Running it again only fills the lanes that are still empty.
Every Agent it creates is active, asks for review before acting and has no schedule of its own, so it only works when given work. Specialists report to the coordinator. Skipping the step creates nothing.
Improvements(2)
- ImprovementSkills & catalogue
Skills now show whether they can actually reach a run
Each installed Skill carries a readiness badge that names what is missing, such as a connection or a credential, with a way to fix it, plus a workspace on/off switch and tag filters.
Open the Skills section of the Agents page. A ready Skill shows no badge. Otherwise the card says why it cannot reach a run: Not reaching any agent, Missing N requirements, Blocked by your access rules, Switched off or Couldn't check.
- Missing items are named, for example a connection that is not connected or a credential that is not set (never its value), with a link to Settings → Connections or the Agent's capabilities.
- Re-check runs the check again in place, and an hourly sweep refreshes old results.
- The on/off switch turns a Skill off for the whole workspace from the next run, without touching its bindings.
- Filter by tags, state and search. The summary line, such as "6 of 34 Skills need you.", shows only those Skills in one click.
A Skill's detail page adds Readiness, Requirements and Where it came from panels above its existing sections.
- ImprovementTasks & goals
An Agent approver now reviews the pull request before approving
When a Task with an Agent approver moves to In Review, that Agent gets a review run with the pull request's diff and CI result, and only its explicit approve or request-changes verdict counts.
A Task could already list an Agent as an approver, but that Agent never reviewed anything. Now, when the Task enters In Review, and again when its pull request gets new commits, each pending Agent approver gets its own review run.
- The run sees the full diff and the CI verdict, and can only record a verdict. It cannot edit files, push or move the Task.
- An Agent cannot approve its own work. An approver that worked on the Task is refused.
- Your merge approval still applies. An Agent's approval never stands in for a person approving the merge.
- Cost is capped, by default at 4 review runs per Task and 2 Agent approvers per review.
Limits: approvers are added through the API, the MCP server or the chat assistant, since no screen creates them yet. Reviews are not available yet for Tasks that run on your own fleet nodes. A diff that is too large or incomplete is not reviewed, and the approval stays with a person.
Plus 10 fixes in the GitHub release notes (opens in a new tab).