Day AI Release Notes

This week we have a few quality of life improvements for you!

Paste images into chat

Paste a screenshot or copied image straight into the chat composer with ⌘V / Ctrl+V, and it attaches just like a dragged-in file. If your clipboard also holds text (like a copy from Excel or Google Docs), the paste stays text.

Bulk-update records by ID

Your agent can now update thousands of existing records in one import by matching on record ID, instead of working through them 25 at a time. Large enrichment backfills that used to run for hours now finish in a single pass, and IDs that don't match an existing record are flagged rather than silently creating blank ones.

Smarter meeting and page search

Your agent can now search the contents of your meetings (including transcripts) and pages by topic, ranked by relevance, so it finds the right proof point or past conversation without guessing the exact words.

Clearer skill data scope

When a skill runs with workspace-only data access, your agent now tells you it can't see your private emails and calendar while that skill is active, instead of blaming a sync delay.

Dashboards Get a Glow-Up

Agent-built pages render with a real widget system. Stat tiles show a headline number with a sparkline and a comparison. Bar lists shade each row by value and mark the benchmark on a distribution track. Heat matrices turn a two-dimensional breakdown into color instead of a grid of digits. Tables can format a column as a meter, a heat scale, a badge, or a stack. Panels, callouts, folds, meters, and inline chips are available as page building blocks, so a dashboard reads as a composed document rather than a dump of query output.

Everything is click-through. Clicking a bar list row, a heat matrix cell, or a stat tile opens the drilldown panel with the records behind that number, on both live widgets and static charts the agent built earlier. Grouped labels work too: click "Other" or "Unknown" and you get every row that folded into it, not an empty panel.

Charts are also harder to get wrong. A funnel with one populated stage renders as a compact bar list instead of a giant triangle. Recipes that reference a custom property that doesn't exist are rejected when the widget is saved, with a suggestion, instead of rendering as a blank marker or failing later when a teammate picks a filter option. Unresolved columns show a readable header instead of a raw property ID.

Also shipped

Momentum on People and Organizations:

The Momentum activity strip, previously available only on Opportunities, can now be turned on for the Organization and People tables with the "+ Momentum" chip in the toolbar.

Readable agent replies in Slack:

Assistant replies in Slack threads now convert headers, bullets, and emphasis to Slack formatting, and email replies get proper HTML.

Skill notifications hint at the missing channel:

If a Slack channel isn't in a skill's notification picker, it's almost always because Day AI hasn't been added to that channel. The picker now says so and links to Integrations in a new tab, so you don't lose your unsaved skill edits finding out.

Admins can manage members from chat:

Workspace admins can now change an active member's role or remove a member by asking, in addition to inviting and resending invites.

Bring Your Own Connector

The connector list used to be ours to curate. Now it's yours to extend.

Every workspace can now register custom MCP connectors from Connectors in workspace settings. If your team runs an internal tool, a vendor exposes an MCP endpoint, or you've built something in-house, an admin adds it once with a name, an endpoint, and its authentication setup. From there it behaves exactly like the connectors Day AI ships: each member connects with their own OAuth or API key, controls which tools are enabled, and your agent starts working with that data in chat, in skills, and in delegated runs.

Also shipped

Delegated agents ask clarifying questions:

When your agent delegates work to another agent, that agent can now pause with questions instead of guessing. The task moves to a new Needs Input status, its questions arrive in the chat where you made the request, and the task stays open with no timeout until you answer. Reply in that same chat and your agent relays the answer. The delegated run picks up where it left off, on its own thread, and delivers the result when it finishes.

Add anyone to a deal from chat:

Your agent can now relate a person to an opportunity even when that person has no email address, matching what you could already do by hand from the sidebar. Deals linked to an organization by name or ID also find that org's people correctly, and hand-added people without an email are no longer removed on the next roles refresh.

Pipeline CSV export shows every owner:

Exporting the pipeline no longer leaves the Owner column blank for opportunities whose owner is identified by email rather than a connected Day AI account.

CSV imports dedupe by email:

Rows in a contact CSV that share an email address now resolve to one contact instead of creating duplicates, and imported note text is saved literally rather than being rephrased.

Single-select properties behave in filters and exports:

Agents can no longer create the retired "combobox" property type, which broke board filters and export columns. Existing combobox properties are being converted to standard picklists so they work everywhere picklists do.

Talk to Your Agent

Typing is the slowest way to tell your agent what you need. Now you can just say it.

The chat composer has a microphone. Click it, talk, and your words stream to a live transcript as you speak from a new thread on Home or inside any existing conversation. Hit Stop and the transcript lands in the composer as editable text, so you can fix a name or trim a thought before it goes out. Hit Send and it submits once, cleanly. Hit Cancel and whatever you had typed before is restored untouched.

Recording keeps the composer's footprint, so the page doesn't jump when you start dictating. The waveform shows you what the mic is actually hearing. And the send button now waits for any attachment still uploading, so a message never goes out missing the file you dropped in a second ago. If an upload fails, you get a toast instead of a half-sent message.

Meetings on Every Timeline

Calendar meetings appear on the activity timeline for Contacts, Organizations, and Opportunities. Open an opportunity and you see past meetings at the time they happened, the single next upcoming meeting flagged as such, and the recordings that match the deal's contacts, without anyone having to link them by hand. Day AI resolves the opportunity into its customer-side contacts and matches any meeting where one of them was an attendee or organizer.

Also shipped

• Collapsible lists in pages:
  Type the Toggle list slash command, or > followed by a space, and you get a collapsible block: Expand it when you need it, collapse it when you don't.

• Quote Blocks in pages:
  use the Quote slash command or type " followed by a space.

• Microsoft 365 connectors:
  Connect Outlook 365 Mail, Outlook 365 Calendar, and Microsoft Teams as MCP connectors so your agent can work with your Microsoft data. These are in beta and use Microsoft's Agent 365 servers: a workspace admin enters your Microsoft tenant ID and Application ID once, and each connecting user needs a Microsoft 365 Copilot license.

• Group by Stage follows your pipeline:
  Grouping the Opportunity table by Stage now orders the groups the same way your kanban board does, and that order holds through reloads, saved views, and every sort.

• Organizations and Last Contacted At in the Emails view:
  Two new columns on the Emails table show each email's external recipient organizations, and the most recent Last Contacted At across those recipients.

• Related Pages on Organizations:
  The Related tab in the Organization sidebar now lists every Page you have access to that is associated with that organization, including pages linked through older association methods that previously didn't appear.

• Automated slots in skill deployment:
  When you deploy a managed skill that runs on a schedule or trigger, the review table shows each agent's remaining automated skill slots next to its tier, so you can see before you confirm which agents have room.

• Manage changing emails:
  People records now include Current Work Email and Past Emails, so you can see the address history enrichment has gathered.

• Slack notifications from chat:
  When you ask your agent in chat to post to a public Slack channel, it can now do so directly, with a "Requested by you via Day AI" attribution line. Scheduled and triggered runs still post only to the channels configured on the skill.

• Org enrichment sees your people's custom properties:
  Organization-level AI property fills and overviews can now read the custom property values of the org's linked contacts, so an org property like "Qualified From Demo Form" can key off a person-level field.

Comments on Call Transcripts

Select any passage of a call transcript and start a comment thread anchored right there. Mention teammates — and if they can't see the recording, Day AI prompts you to grant access before the comment posts, so nobody gets pinged into a wall. Reply, edit, resolve and reopen, and browse Open and Resolved threads in the comments rail. Clicking a comment notification drops you on the transcript with the rail open, the thread focused, and the passage scrolled into view — no hunting.

Your agent is in the thread too. Agents can read, create, reply, resolve, and reopen transcript comments — and do the same on Pages (read, create, and update; deleting stays human-only). Agent comments are now attributed to the agent itself, with its own name and avatar, so you always know whether a human or an agent said it.

Momentum

Momentum is a new sidebar tab on organizations, opportunities, and contacts that charts your customer interactions — meetings, calendar events, and emails — over time, so you can see the rhythm of a relationship instead of reconstructing it from a timeline. It defaults to the last 30 days, with 90-day and all-time views one click away.

There's also an opt-in Momentum column for opportunity tables: a compact activity strip on every deal, so you can scan a whole pipeline and instantly see which deals are humming and which have gone quiet. Hover for interaction previews, and click through to open the underlying email or meeting.

Also shipped

Emails in search:

Cmd+K search now shows emails in their own Emails section instead of disguising them as pages. Opening a pending campaign email takes you straight to that campaign's review queue with the draft focused and approve/send controls ready; other emails open the full email editor.

Opportunities link to organizations without domains:

An opportunity can now auto-link to an organization by exact name match, so companies without a website domain still connect to their deals.

Peerfold MCP connector:

Connect Peerfold from Settings 12 Connectors and let your agent work with your customer-education data 12 courses, lessons, learners, enrollments, quizzes, certificates, and reporting. Authentication is per-user OAuth, same as the other MCP connectors.

Date format setting:

Choose MM/DD/YYYY or DD/MM/YYYY in your Profile settings, right below Timezone. The preference applies across tables, views, and property cells.

Private Page mentions ask about access:

Mentioning someone on an invite-only Page now prompts you to decide their access before the mention lands 12 in the page body immediately, and in comments at send time. No more notifying someone into a page they can't open.

Folders first in Pages:

The Pages library root now lists your folders above unfiled pages, so navigating a organized library doesn't mean scrolling past loose documents.

Sharing settings per account:

If a teammate has multiple Google accounts connected, the Members page now shows sharing settings for each account separately instead of blending them into one status.

Contacts created in chat now get enriched:

Contacts created through chat were silently skipped by enrichment. They now enrich on creation like contacts from every other source.

Emails in Opportunity Timelines

Opportunity records now show related emails in the Timeline tab. Emails appear when it involves someone who holds a customer-side role on the opportunity and is at the opportunity's company domain.

PandaDoc connector

For teams running proposals and contracts through PandaDoc, you can now add PandaDoc as an MCP connector and have your agent work with your documents directly. Connect it from Connectors, the same as the other MCP connectors.

Timestamps in copied transcripts

Copying a meeting transcript now includes the timestamp on every line, so you can point teammates at the exact moment something was said.

Build Pages from any MCP client

Page image tools are now available in every workspace, image uploads work from external MCP clients, and cross-page linking is fully supported

Better email recall for your agent

Agent email search now includes full-content keyword search and checks sent mail first

Pages navigation

Page breadcrumbs now show the folder the page lives in, and searching the Pages library no longer breaks when you navigate between folders.

Roomier chat composer

The chat input now grows to roughly triple its old height before scrolling internally, so long prompts stay readable while you write them.

Last Contacted At covers offline interactions

When your agent logs an offline interaction

Your Agents Now Work as a Team

Until now, agents worked alone. Now your agents check the roster before doing anything: if another agent on your team — or one of its skills — is better suited to the task, the work gets handed off automatically. Ask your Chief of Staff for a research brief and it delegates to your Research Analyst, the analyst runs in the background, and the result posts back into your original chat with credit to the agent that did the work.

Multi-part work fans out too. A task that spans domains goes to each specialist in the same turn instead of one agent grinding through it serially. And when a delegated agent creates something — a page, an email draft, a view, a list, an action — the outcome card in your chat shows each artifact as a clickable chip, so you can open what your team produced without hunting for it.

Talk to one agent. It knows who else is on your team, what they're good at, and routes the work — you don't have to remember which agent owns which job.

Show the Fields You Actually Use

Your pipeline cards and record sidebars are now yours to design.

Pipeline boards get a new Display control: select and order up to five fields on opportunity cards — standard properties or your workspace's custom ones. The layout is shared by everyone viewing that pipeline, so the whole team reads cards the same way. Personal filters, sorting, and hidden stages stay personal.

Record sidebars are customizable too. From Workspace Settings → Schema → Customize Sidebar, workspace admins can reorder and show/hide the fields on People, Organization, and Opportunity sidebars — workspace-wide. Newly created properties append visibly, renamed ones keep their position, and one Reset returns you to the default.

Also shipped

• Delete meeting recordings yourself:

  Recording owners and workspace Owners can now delete a meeting recording directly from its detail-view menu, in every workspace. No more asking support to remove a recording.

• Three new MCP connectors:

  PandaDoc (create, send, e-sign, and track documents), PostHog (product analytics), and LeanScale (GTM playbooks, benchmarks, and field studies) are now available in Settings → Connectors, so your agent can work with those tools directly.

• Onboarding Coach agent template:

  A new Turbo-tier template built for ramping one new customer-facing rep. It coaches from your workspace's real calls and emails — especially your top reps' — and your company's GTM strategy, and offers to set up a daily ramp brief and post-call coaching in its first conversation.

• Copy tables from chat as real tables:

  The copy button on tables in chat now writes rich clipboard content, so pasting into a Page, Notion, or Google Docs produces an actual table — while spreadsheets still get clean rows and columns.

• Cleaner notification links:

  Agent notifications no longer contain raw citation markers — they become numbered links that open the cited source in Day, and email drafts strip them entirely. Notification links to email drafts now open the draft too, instead of dead-ending.

• Action sources are visible:

  The Sources popover on an action's properties now shows the thread that created it as a clickable chip.

• Custom Property Created By:

  You can now see which member of a team created a custom property, so you know who to check with if you need to edit or delete.

Your Agent Now Remembers Your Past Conversations

"Didn't we already talk about this?" Now your agent knows the answer.

Until now, every chat started from a blank slate — your agent couldn't look back at what you two discussed last week, even when the answer was sitting right there in an old thread. That's over. Your agent can now search across all of its prior conversations with you. Ask "what did we decide about the Acme renewal?" and it finds the thread where you decided it.

Even better: when the agent cites a past conversation, clicking the citation doesn't just open the old thread — it lands you on the exact message, scrolled into view and highlighted. No scrolling through a long chat hunting for the relevant part.

Skills: Attach Pages and Folders Everywhere, and Deploy to Teammates from Chat

Your skills can now carry their own reference material — and admins can roll them out without leaving the conversation.

Skill attachments are now available in every workspace. Attach up to 10 Pages or Folders to a skill, and the skill reads them live at runtime — always the current content, never a stale snapshot, and always through the same permission checks as everything else. Your "weekly pipeline review" skill can lean on the playbook Page your team actually maintains.

And for admins and owners: you can now deploy and undeploy Skill Library skills to teammates' agents straight from chat — "deploy the QBR prep skill to the whole sales team's agents" — instead of clicking through the Agent Studio deployment dialog. Because this runs through the Day AI MCP, it works from Claude too. Deploys are additive and explicit: only the agents you name are touched, never a silent bulk change.

Also new: the Skills Library's Custom tab gained a creator filter ("Me", each teammate, "No creator") and the tag filter is now multi-select, so finding the right skill in a big library takes seconds.

Also Shipped:

• MCP tools in Slack: MCP connector tools are now available in Slack. In a 1:1 DM with the bot your always-allowed tools run directly, and everywhere else (channels, group DMs) every tool call posts an approval card and asks before it acts, since results land where other people read them.
• Citations in Pages: Pages your agent writes from meeting recordings now get real, clickable citation chips — click one and the meeting opens at that transcript timestamp — instead of literal [cite:278] markers in the text.
• Charts in PDF exports: "Save as PDF" on a dashboard page now includes every graph widget. Previously the export could race the charts and print blank rectangles where your graphs should be.
• Skills fire on private meetings: Meeting-triggered skills now run on recordings that aren't shared with the workspace, as long as the skill's Data Privacy scope already allows it to read them. Previously a skill you set up on your own private recordings would silently never fire.
• Date filters match the whole day: Searching for opportunities closing "today" or "on or before Friday" now works the way you'd expect. Date-only filters previously compared against midnight and could miss every deal on the target day — your agent would confidently report zero when there were four.
• Managed-skill warnings on Page changes: Before you change a Page or folder's sharing or move it somewhere a managed skill can't follow, Day AI now shows you exactly which managed skills would lose their attachment and asks you to confirm.

How To Build The ULTIMATE AI Company Brain (Obsidian + Claude Code)

Your second brain is single-player. This is the multiplayer version.

This one was fun to make. I spend the whole film playing Althea, Director of RevOps at RMBL, a fictional company that makes roller coaster management software and is trying to get a new water park product into every deal. Althea starts where most ops people actually start: a folder full of call notes, a CRM export, somebody's pricing scratchpad. One prompt into Claude Code and that mess becomes a clean, interlinked Obsidian vault, the Karpathy LLM-wiki pattern, with a graph view you can wander around all day. You can build that part in an afternoon, and I show you how.

Then the leap. I point Claude Code at GTM Brain, our public repo, run /start, and it connects the vault to Day.ai. It reads the initiative I care about, drives attach rates on the new product, audits the whole sales team against it, and catches that Mason, the new rep, has no agent at all. A few approvals later the rollout ships: Mason gets an agent built from what's working across the team, everyone's call prep quietly learns when to bring up the new product, and every change lands in a change set I can roll back. One shared brain, every agent owned by a human, deployed from my terminal.

What Shipped

Your Agent Learns Your Voice Automatically

Day AI now builds a personal Email Writing skill for every user — automatically. Once your Gmail finishes syncing, your agent reads dozens of your real sent emails, studies how you actually write — tone, length, greetings, sign-offs — and rewrites its own drafting instructions in your voice. You get a /email skill without setting anything up. No style-guide homework, no prompt engineering.

The skill also knows your email templates. It lists each one by name with guidance on when to use it, and pulls the current version at draft time — so when you edit a template, every future draft picks up the change. And because it's a normal skill, you can refine it in plain language: tell your agent "make my emails shorter" or "stop using exclamation points" and the skill updates.

Also shipped

• Skills can include other skills: A skill can now reference up to five other skills belonging to the same agent, folding their instructions in at run time. Keep your "Email Voice" guidance in one skill, include it from "End of Day Email" and "Follow-up Drafts", and refining the voice once improves everything that uses it.
• Widescreen mode: Press Ctrl/⌘+W to let chat, Pages, and Home stretch to the full width of your window instead of a centered column. Toggle it back the same way.
• Markdown uploads in chat: You can now attach .md files in chat alongside the other supported file types, and your agent reads them directly.
• Copy and export Pages: Pages get Copy page and Download as Markdown actions in the panel menu — pasting into Docs or Notion keeps the formatting, and plain-text editors get clean markdown. Individual tables get their own Copy action too, preserving headers, colors, and column widths when pasted into another Page.
• Better folder browsing: Folder cards in Pages now show relative last-updated times, wrap longer titles instead of truncating them, and can be sorted by folder order, name, or last updated — and inline folder expansion now actually shows the folder's contents.
• Decision tree charts: Ask your agent to diagram branching logic — lead qualification flows, routing rules, playbooks — and it renders a proper decision tree with labeled branches, exportable and embeddable in Pages like every other chart.
• New connectors — Crossbeam, Sumble, Common Room, and Guru: Four new MCP connectors join the roster. Connect them from Workspace Integrations with per-user OAuth and your agent can work with partner ecosystem data (Crossbeam), technographic data (Sumble), community signals (Common Room), and verified company knowledge (Guru) directly.
• Top-N dashboard tables: Table widgets accept an optional row limit applied after sorting, so you can build an honest "Top 20 deals by amount" table — with the header showing "Top 20 of 312" so nobody mistakes it for the full list.
• MCP tools from Slack: Your agent can now use your connected MCP tools when you talk to it in Slack — always-allowed tools run silently in 1:1 DMs, and tools that need permission post an approval card right in the Slack thread with Approve/Deny buttons. In shared channels, every connector call asks first and the card discloses where the result will be posted. [needs context: confirm rollout scope — currently enabled for select workspaces]

Know someone else who should check out Day AI? Shoot them this link:
https://day.ai/demo

No more one by one merging required. Tell your agent to clean up duplicates by a shared field — email for contacts, domain for organizations. It previews the plan, you confirm, and merges run in the background, skipping any group it can't merge without losing data.

Also shipped:

• Page folders — You can now group your pages into private and shared folders, allowing for easy organization of proposals, reports, knowledge documentation and more.
• Page table polish — Tables are left-aligned and fill the page by default, with a new alignment and sizing menu, per-column and per-cell text alignment, and a richer formatting bubble (bold, italic, underline, links, dark-mode-safe text color).
• Page Exports — Share links and PDF exports now render tables exactly like the editor.
• Email citations — When your agent states a fact drawn from an email, it drops a numbered citation chip next to the claim; click it to open the exact email in the sidebar.
• Big attachments, finally readable — Attach images up to 30MB and PDFs up to 50MB in chat. Images resize instead of erroring, long PDFs read page by page.
• Opportunity share links — Ask your agent for a share link to an opportunity and you'll get one that opens the deal with its activity view alongside.
• Stage-change history — Your agent can read the change history of one property across many records at once — ask when each open deal last changed stage and get a source-attributed answer.
• Smarter matching for government domains — dmv.ca.gov and sanbruno.ca.gov are now distinct organizations instead of collapsing into ca.gov, so activity lands on the right record.

Answering questions is the tip of the iceberg

Answering questions is the tip of the iceberg when it comes to what a Day AI agent can do. The real leverage is treating your agent like an employee with a role and giving it skills: recurring jobs it owns without you asking each time.

A skill doesn't wait in a chat. It runs on a schedule or in response to something happening in your workspace, does the work, and tells you what it found or did.

They already know.

Every skill runs on your agent's memory of your customers — built continuously from the emails, meetings, and Slack conversations you've connected. That memory keeps accumulating whether or not you're actively using it.

Set it and forget it.

Set a skill up once and it just keeps happening. Nobody has to remember to do the work, because it's already done by the time you'd have gotten to it.

Setting a skill up is a conversation, not a project. Describe the outcome, your agent builds the skill. No configuration screens to learn first.

"Create a skill that sends me a weekly pipeline summary every Monday at 9am."

"Create a skill that drafts follow-up emails after my meetings."

"Create a skill that flags bug reports from Slack."

You don't have to build a skill from scratch. Day AI ships ready-made skills — Actions, Opportunity Automation, Call Coaching, Deal Coaching, End-of-Day Follow-Up Drafts, Hot Accounts — that you can add to your agent in minutes and adjust from there.

A working skill fades into the background. You'll know it's working when you stop doing the manual version of the task and only think about it when the notification lands. Still doing it by hand "just in case"? The prompt needs a tweak — tell your agent what's missing.

Fixing a skill works the same way. Your agent helps shape the prompt, pick a trigger, and set up notifications up front — and if something's off once it's running, you tell your agent what should change instead of hunting through settings.

For the mechanics (trigger types, data privacy settings, the Skills Library, troubleshooting a skill that isn't firing) see our Skills help doc.

Connectors: where the payoff compounds.

Skills are the most powerful when they can use your other tools. Without connectors, a skill can watch what's happening and tell you about it. With them, it can take action. This is where skills stop saving you a glance and start saving you the work.

• Customer mentions a bug on a call? Your agent opens the Linear ticket.
• Deal moves forward? It updates the stage in HubSpot.
• Meeting wraps? The follow-up is drafted and the recap is in Slack before you've closed the tab.

Bring your customer memory anywhere: Day AI via MCP

Day AI's customer memory is retrievable via MCP — the open protocol that's quickly becoming the standard way AI tools connect to live data, and that Claude, among others, has built native support for.

That means your workspace's memory isn't trapped inside the Day AI chat window. Connect it once, and you can open Claude Desktop or Claude Code and ask "what's the latest on Acme Corp?" and get an answer sourced from the same real-time customer graph your Day AI agent uses, without ever opening Day AI.

No exporting a CRM report. No copy-pasting a transcript into a prompt. No re-explaining who the account is or where things left off. The context travels where you're already working.

Most CRMs make you come to them. Day AI goes where you are. Set the connection up once, in a couple of minutes, and it's just there from then on.

The Agent Origin Story

How a morning briefing nobody was supposed to reply to changed the course of the company, and what it means for the future of work.

Every company has the moment where everything clicked. This is ours.

It started with a morning briefing email that nobody was supposed to reply to. Then everybody replied. And one person in particular kept replying, even after Christopher told him to stop.

What looked like a support problem turned out to be the insight that built the entire agent architecture: when an agent reaches out to you, you respond to it like a human. You coach it. You give it direction. You expect it to follow that direction, and follow it well.

That expectation, that agents belong to people, that they have job descriptions, that they get better over time through real feedback, is the foundation everything at Day AI is built on. From morning briefings to skills to the GTM Brain. It all started here.

Email joins the timeline

Email is where most of your customer relationships actually happen. Day.ai already captures your email automatically. Now we're putting all of it to work in two big ways.

See every email in the timeline

Open any person or organization and the timeline now shows your email history right alongside meetings and everything else — every message at the moment it was actually sent, with threads grouped so your timeline stays readable. At a glance you'll see what was sent and received, and clicking into an email opens the full conversation: every participant, complete message bodies with inline images, and attachments you can preview and download.

Ask your Agent to find any email

Your Agent can now search across all emails that you have access to, lightning fast. Ask things like:

• "Find the pricing emails we exchanged with Acme last quarter"
• "What did Sarah say in her last email about the renewal?"
• "Pull up every email with anyone at bigco.com from the last two weeks"

Search by who sent or received it, by company, by timeframe, by subject or content — and get the actual messages back, not just a summary. It's also significantly faster: we rebuilt email search on our new search infrastructure from the ground up.

Private stays private

Your email sharing rules apply everywhere, always. Messages you haven't shared with your workspace are clearly labeled Private and visible only to the people on the email — and anything covered by your exclusion rules (a domain or a specific address) kept private to you and your Agent. You can review or update your sharing rules anytime, or ask your Agent to update for you.

Also shipped

• Onboarding without Google — You can now finish onboarding and use Day without connecting a Google account. A confirmation explains what you'll miss, and you can connect later from Settings.
• Intercom & Amplitude connectors — Connect them as MCP connectors and let your agent work with your support conversations and product analytics directly. Per-user OAuth from Workspace Integrations, like the other connectors.
• CSV exports show names, not IDs — Multi-select picklist columns were exporting raw option IDs for cells with 2+ selections; exports now show the option names you see in the table.
• Page share notifications — When someone shares a page with you directly, you get a bell notification. Mentions also check real page access first.

Know someone else who should check out Day AI? Shoot them this link:
https://day.ai/demo

Quick answer: A context graph is a way of storing information about your customers as a network of connections, people linked to companies, linked to deals, linked to every conversation anyone has ever had about them, instead of as rows in separate tables. The point isn't the shape. The point is that when something changes anywhere in that network, every agent looking at it sees the update immediately, and can follow a connection to any related fact without a person having to go find it first.

That's the short version. The longer version is worth understanding, because "graph" gets thrown around loosely, and the actual property that matters is easy to miss if you only hear the word.

The problem with tables

The problem with tables

A traditional CRM, and most business software generally, stores information in tables. A contacts table. A companies table. A deals table. Each row is a record, each column is a field, and if you want to know how a person relates to a company, or a deal relates to a conversation, you're relying on a foreign key, an ID number sitting in one table that happens to point at a row in another.

This works, but it's brittle in a specific way: the relationships are implicit. The database knows a contact_id equals 4471 and a deal has a contact_id field set to 4471, but it doesn't inherently know or care that this means "this person is the champion on this deal, and three months ago they raised a concern about pricing that never got resolved." That meaning lives in a person's head, or in a note somewhere, disconnected from the structural fact that connects them.

What a graph does instead

What a graph does instead

A context graph makes the relationships themselves the primary thing being stored, not an afterthought bolted on with foreign keys. A person links to a company. That company links to a deal. The deal links to every conversation anyone on the team has ever had about it. Each of those links, not just each record, carries meaning: this person works at this company, this conversation happened on this date and touched on this deal, this commitment was made and hasn't been followed up on.

Practically, this means an agent (or a person) can start at any point, a person, a company, a deal, and walk outward to everything connected to it, the way you'd follow a thread of "oh, and that reminds me" in a real conversation, instead of running a separate query against a separate table for every fact you need.

Here's a concrete version. Say a contact at Acme Corp asks a question about a feature. A relational system can tell you who they are and maybe what deal they're on. A context graph can tell you: this person works at Acme, Acme purchased the Enterprise package eight months ago, that purchase generated two support tickets about integration issues, one of those tickets is still open, and this same concern was raised in a call last quarter that flagged renewal risk. That's not five separate lookups. It's one connected picture, because the graph already holds the connections, not just the facts.

Why this matters specifically for agents

A person can tolerate a database that only answers exact questions, because a person can go dig around when something doesn't fit a field. An AI agent can't dig around the way a person does. It needs to be able to query in something close to natural language and get back not just a data point, but the surrounding context, and then be able to follow that thread to nearby, related information on its own, quickly enough that a real-time conversation or workflow doesn't stall waiting on it.

That's the actual design requirement a context graph is built to satisfy: query in plain language, get back a summarized answer along with the underlying facts, and be able to walk to connected nodes to assemble whatever context window is needed for the task at hand, fast. A flat table, or a folder of documents with a search function bolted on, can approximate small pieces of this, but it doesn't hold the relationships as structure the way a graph does, which means every question that spans more than one type of record turns into manual reconstruction work.

The part a homemade version tends to miss

If you've tried building something like this yourself, notes and call transcripts dropped into a folder with an AI model pointed at them, you've probably gotten a version of the retrieval benefit already. That part is real, and it's a reasonable place to start.

Where it tends to break is on three properties that don't show up until a second person, or real customer data, gets involved:

Provenance and lineage.

Not just what the system believes is true, but where that belief came from, when it was established, and whether a human ever overrode it. "We think this deal is at risk" is a much more useful and trustworthy statement when you can also see it was flagged after a call three weeks ago, was correct twice before, and a manager confirmed it last time. A flat document store doesn't track any of that by default.

Permissions, enforced at the level of the graph itself.

Some information should be visible to everyone on a deal. Some shouldn't. A homemade system built for one person doesn't have this problem, because there's only one person's access to think about. The moment a second person, let alone a whole team, needs to use it, every question the graph answers has a second question hiding inside it: is this specific person allowed to know this specific thing? Enforcing that at the level of the underlying graph, rather than bolting permission checks onto every application built on top of it, is a structurally different, and harder, problem than most DIY versions ever attempt.

Speed at the moment of retrieval.

Walking from a person to a company to a deal to a conversation and back, in something close to real time, while also checking permissions on every hop, is a genuine engineering problem, not a configuration setting. It's the specific place a homemade index, built to answer one kind of question well, tends to fall over once the questions get varied and the data gets large.

Context graph vs. customer memory: how the two terms relate

These two terms get used close enough together that it's worth being precise. Customer memory is the broader idea: a continuously updated record of everything that's happened with a customer, captured first and structured whenever needed, instead of structured in advance. A context graph is the specific technical shape that record takes, the nodes and the edges, the relationships between people, companies, deals, and conversations, that makes that memory something an agent can actually query and walk through quickly. Customer memory is the what and the why. A context graph is the how.

Frequently asked questions

Is a context graph the same thing as a knowledge graph?

They're closely related concepts. A knowledge graph typically models general facts and entities. A context graph, in the customer relationship sense, is a knowledge graph specifically structured around people, companies, deals, and the conversations connecting them, with the retrieval speed and permission model built for agents to query it live.

Do I need a graph database to build a context graph?

Not necessarily as a strict requirement, but you need something that treats relationships as first-class structure rather than as foreign keys bolted onto separate tables, and that can traverse those relationships quickly at query time. Whether that's implemented on top of a graph database specifically or another architecture that achieves the same properties is an implementation detail; the properties (queryable relationships, provenance, permissions, speed) are what actually matter.

Can I build a context graph myself with notes and an AI model?

You can build something with real value for one person this way, and it's a completely reasonable place to start. It tends to hit real limits once a second person needs access (the permissions problem), once you need to know why the system believes something and whether a human corrected it (the provenance problem), or once the volume of data makes fast traversal a genuine engineering challenge rather than something a script handles.

Why does this matter more now than it did five years ago?

Because the thing querying the data changed. A person clicking through a dashboard can tolerate flat tables and manual lookups. An AI agent that's supposed to act on your business needs to retrieve connected context fast, in plain language, without a person assembling it by hand first, and that's a different architectural bar than most systems were ever built to clear.

Day AI's Context Graph is the foundation every agent in the product runs on, continuously updated from every call, email, and thread, with provenance, lineage, and permission-aware access built in from the start.

See how it works →

Software Can Read Now

Every call you take, every email you send, every decision your team makes — it's all being captured. The question is whether any of it is doing anything.

CRM was built to store that data. It was never built to act on it. What's happening now is that the monolithic suite is breaking apart into categories that are each becoming real products in their own right, and the first company to reassemble them into one system, built from the ground up for the agentic era, becomes the successor.

That's Day AI. Every conversation your company has automatically closes the loop. A bug surfaces on a call? Engineering gets a PR to review. A prospect mentions how they found you? An agent starts pulling that thread. A deal goes quiet? A re-engagement is drafted and waiting for your approval. No prompt required. No one has to remember to check.

Mention a teammate in a Page — and give them access in the same click

Pages just became a place to work together, not just write.

You've always been able to capture knowledge in Pages. Now you can bring the right people into it. Today we're introducing @-mentions in Pages — and we built them to do something most tools make surprisingly hard.

The old way:

To loop a teammate into a document, you'd stop writing, open a separate share dialog, guess at the right permission level, save, and then message them somewhere else to let them know. Four steps, three of them outside the doc.

The new way:

Type @ and pick anyone in your workspace. Hover the mention and you'll instantly see whether they can actually access the page — and if they can't, grant or adjust their access right there: Viewer, Collaborator, Editor, or Full access. The moment you mention them, they get a notification in the new notification bell with a link straight to the page. Mention, grant access, and notify — all in one motion, without ever leaving the page.

You can also type @ to link to other Pages in your workspace, so related docs stay connected.

Also Shipped

• Email Privacy Recommendations — Each time we have a new email sharing exclusion recommendation for you, you’ll be notified and clicking the notification will take you to email exclusion settings.
• Attio connector — Connect Attio as an MCP connector and have your agent work with your Attio CRM data directly. Authenticate per-user from Connectors, same OAuth flow as the other MCP connectors.
• Slash command menu on Pages — Hit / to open the menu and insert a new text or image block, table or more without using your mouse.
• Stage badges on related opportunities — Opportunity in the Related tab now show a stage chip alongside the pipeline name, so you can read pipeline status without opening each one.
• Export to PDF — Hit Save as PDF in the three dot menu of a Page for a clean print-ready export. It works on public shared pages too, no login required.
• Sidebar remembers your filter — The detail-view sidebar reopens to the property filter tab you last used instead of resetting to "All".
• Annual commitment visibility — The Billing page now shows per-tier commitment usage, and add/remove-agent dialogs spell out when you're filling a paid slot vs. leaving one unfilled.

This week Laura and I sat down to answer a question that's been nagging at every GTM engineer I know: you've migrated your tinkering into Claude Code. Doing what, exactly? Chapter one of GTM engineering (which Clay largely defined) was hands-on data enrichment: powerful, creative, project by project. What chapter two actually looks like is a different thing entirely.

We rebuilt table editing on Pages from the ground up — tables now work the way you'd expect from the best modern editors: flexible, fast, and fully editable by you or your Agent.

What it changes:

Shape your columns instantly.

Drag any column border to resize it. Double-click a border and the column auto-fits to its content. Want the table to fill the page? One click on "Fit to width" and every column balances itself.

Restructure without friction.

Hover over any row or column and a grip appears. Click it for a full action menu — insert, duplicate, clear contents, or delete. Toggle the first row or column into a header. Need five more rows? Click the + bar below the table to add one, or drag it to add as many as you need in one motion.

Make tables scannable with color.

Apply background colors to any row or column — nine colors, all tuned for both light and dark mode. Status columns, priority rows, highlighted totals: your tables can finally communicate at a glance.

Move tables like blocks.

Grab the handle beside any table and drag it anywhere on the page. A drop line shows you exactly where it will land.

Pages can now include images right alongside your written content.

You can paste, drag and drop, or use the insert menu to add screenshots, diagrams, mocks, inspiration, or visual notes directly into a Page. Once added, images save with the page and can be resized or aligned left, center, or right.

What it changes:

A lot of work is easier to understand visually. Instead of keeping screenshots in Slack threads, docs, or separate tools, you can now keep the image and the surrounding context together in
Day.ai
. This makes Pages better for recaps, plans, research, customer notes, product feedback, and any work where a picture carries important context.

• Clay Connector — Add Clay as an MCP connector and have your agent work with your Clay data directly.
• Connector guardrails in skills — You can't add a connector you haven't actually connected; unconnected providers show an inline Connect button so the skill won't silently fail at runtime.
• Salesforce Classic Notes import — Bulk-import your Salesforce Classic Notes from a CSV; Day creates any missing orgs from the note domains and imports each as an org-linked note.
• Former owners stay visible on Opportunities — Opportunities owned by someone who left the workspace now show that owner in a single clean picker.
• One reply from your Agent when you chat by email — Instead of 3–4 back-to-back messages per question, the agent works in the background and sends one complete reply at the end.

Know someone else who should check out Day AI? Shoot them this link: https://day.ai/demo