Pipelines bring lightweight CRM boards into Gleap. Track deals, onboarding, renewals — any process — as your companies and contacts move from stage to stage, right next to your inbox.

What's new

• Kanban boards for companies & contacts: Create a pipeline for any process, drag records between stages, and switch to a table view when you want to scan and edit in bulk.

• Templates & custom stages: Start from Sales, Customer onboarding or Renewals — then rename, reorder, recolor and archive stages as you like.

• Custom fields & stage totals: Add text, number or currency fields per pipeline, edit them inline on cards and in the table, and see live per-stage calculations like the total deal value.

• Record peek: Click any card to open a side drawer with stage progress, inline-editable fields, the full company or contact details and an activity timeline — without leaving the board.

• Automations: Run workflows when an entry is added to a pipeline or changes stage — move stages, set fields, create tickets, email the contact, notify a teammate, add to another pipeline or call your API.

• Linked conversations: Link tickets to pipeline entries, so the deal and its support conversations stay connected — from the ticket sidebar and from the entry itself.

• REST API & Node.js Admin SDK: Drive pipelines from your backend — add, update and remove entries using your own company or user ids. Check out the API reference and the Node.js Admin SDK docs to get started.

How it works

1. Open Pipelines in the sidebar (right next to Contacts) and create your first pipeline from a template.

2. Add companies or contacts — pick them one by one, or bulk-add everything matching a filter.

3. Drag records through your stages; fields, totals and the activity feed update as you go.

4. Optional: open the pipeline settings to add custom fields and automations.

Great for

• Sales pipelines with deal values summed per stage

• Customer onboarding, from kickoff to live

• Renewals & churn risk — with a ticket linked to every at-risk account

• Syncing stages and deal values from your own backend — e.g. move an account to "At risk" when usage drops

• Any process where CRM context and support conversations belong side by side

Pipelines are available now in beta — open the new Pipelines tab and create your first board.

This is the biggest update to the Gleap inbox yet. AI agents now work directly inside your tickets, conversations can branch into threads, and the whole dashboard can be driven from the keyboard.

AI agents work inside the conversation

Agents used to live in a panel of their own, off to the side. Now they're part of the ticket your team is already reading.

• @mention an agent in the composer to hand it a task. It picks the work up right there in the timeline.

• Ask agent — a dedicated composer mode for agent instructions. Everything sent there stays internal to your team.

• Watch the work happen. Agent runs appear as messages in the conversation: the steps taken, the questions asked, the results produced. When an agent needs something from you, answer it inline.

• See what's queued — pending instructions and what each agent is allowed to do, before it starts.

• Full activity log for any run, one click from the message.

• Stop a run that's heading the wrong way.

• Agents now speak with your project's own bot name and colour instead of a generic "Bot".

• Hand a ticket to an AI agent — or to a coding agent — straight from the command palette.

Threads

• Reply in thread on any message to keep side conversations out of the main timeline.

• The thread opens in a panel beside the conversation, with a draggable split so you can size it however you like.

• A summary bar under the root message shows the reply count and who's involved, so nothing gets buried.

• Threads work the same whether you're talking to a teammate or an agent.

A rebuilt conversation view

• A faster, calmer feed that holds its place as new messages come in.

• Emoji reactions on any message — quick on hover, full picker for everything else, with names on hover.

• New composer with a persistent formatting toolbar and clear reply / internal note modes.

• Cleaner message grouping, day separators, live typing indicators and delivery status.

• Attachments render as typed file chips; images size themselves correctly.

• Inbound emails render clean — no more trailing whitespace, quoted-tail noise, or gaps left by tracking pixels.

• Ticket history now comes from a dedicated history service, so it stays complete and fast even on very long tickets.

Keyboard-first

• ⌘K command palette — assign, snooze, set status, priority or tags, run a workflow, insert a macro, help center article or GIF, attach a file, translate a draft, hand off to an AI agent, or jump to another inbox or board. All without reaching for the mouse.

• Shortcuts throughout: R reply, N note, E archive, A assign, Z snooze, S status, P priority, J/K to move between conversations, C for a new conversation. Press Shift + ? for the complete list.

• Practice mode — a built-in trainer that drops you into a simulated inbox and teaches the shortcuts against a clock, with a score and a personal best. Open it from the palette or the empty inbox.

Learn more here: https://help.gleap.io/en/articles/226-keyboard-shortcuts

Inbox & navigation

• The inbox and board pickers now float over the list by default and pin when you want them docked — more room for the conversation itself.

• Multi-select conversations in the inbox to act on several at once.

• Resizable inbox list, details sidebar and thread panel. Drag to size, double-click to reset — your widths are remembered.

• Jump straight to the next or previous conversation without going back to the list.

Filters, sorting and tables

• Rebuilt filter bar: add, edit and clear filters as chips, with a clear view of what's active.

• New sort menu across boards and views.

• Tables throughout the dashboard now support showing, hiding and reordering columns.

Save an email as PDF

Export the original inbound email behind a ticket as a PDF, straight from the original-email view — no more going back into your mailbox to archive a message you already have in Gleap.

Speed

• Switching between tickets in the same project now makes less than half the network requests it used to.

• Re-opening a recently viewed ticket paints instantly from cache instead of showing a loading skeleton.

• Scrolling long conversations, dragging cards on a board and receiving live updates are all noticeably smoother.

• Searching inside very long conversations handles far more messages without stalling, and tells you when it has only searched the newest ones.

Polish

• Refreshed dialogs across the dashboard, with consistent headers, footers and sizing.

• Unified tooltips (including shortcut hints), titles and dark mode on every screen.

• One consistent AI-translate button everywhere translation is offered.

Companies bring the full account picture into Gleap. Group your contacts under the company they belong to and see plan, value, SLA and every conversation of an account in one place.

What's new

• Company profiles: Every company gets its own page with members, conversations, notes and files — the complete history of an account, one click away.

• Identify companies from your app: Pass company: { id, name } with Gleap.identify() and Gleap groups your contacts automatically — no extra setup.

• REST API & Node.js Admin SDK: Manage companies from your backend. Create, update, read and delete them via PUT/GET/DELETE /admin/companies/{id}, or use updateCompany(), getCompany() and deleteCompany() in the Node.js Admin SDK. Attributes you set server-side are authoritative — client apps can never overwrite them.

• Custom company attributes: Plan, value, domain, address — plus any custom property you define. Edit them inline, right in the company sidebar.

• Company-level SLAs: Set response-time targets per company. Your most important accounts get answered first — with smart fallbacks for everyone else.

• Workflows & Kai know the company: Use company attributes in workflow conditions and variables like {{company.plan}}, and Kai sees the company context when answering.

How it works

1. Send the company with your identify call: Gleap.identify("user-id", { company: { id: "acme-inc", name: "ACME Inc." } }).

2. Contacts sharing the same company id are grouped automatically.

3. Open Contacts → Organisations to browse your companies and drill into any profile.

4. Set authoritative data like plan, value or SLA in the dashboard — or from your backend via the REST API or Admin SDK.

Great for

• B2B support: instantly see which account a conversation belongs to — and what they pay

• Prioritizing key accounts with per-company SLAs

• Routing and automating by plan, value or any custom company attribute

• Syncing plan, value and SLA from your own backend, so support always sees live account data

Already sending companyId with your identify calls? You're all set — we've imported your existing companies, history included.

A faster, smoother mobile experience — rebuilt from the ground up for support on the go.

Support doesn’t stop when you leave your desk. Now, neither does Gleap.

We rebuilt the Gleap mobile dashboard as a native app for iOS and Android. From your phone, you can now:

• Reply to conversations and manage tickets

• Get push notifications and jump directly into important updates

• Turn your voice or a few keywords into a complete AI-assisted reply

• Review boards and keep Kai Code sessions moving

Download on the App Store · Get it on Google Play

This is only the beginning. Try it and tell us what you love, what needs work, and what you want us to build next. We’re incredibly excited to hear your feedback. Let’s go!

The new workflow debugger lets you run any workflow live, right from the builder, and watch every step as it happens.

What's new

• Run it live: Hit Save & run and your workflow starts in a real messenger inside the builder. No publishing, no separate tab.

• Watch each step: The canvas highlights the block that's running, so you can follow the exact path your workflow takes.

• See what's happening: A live event stream shows which branch a condition took, what an API action returned, what the AI decided, and more. Expand any step to inspect the details.

• Test as anyone: Run as a fresh guest, or as one of your real contacts to check targeting, conditions and anything that depends on customer data.

How it works

1. Open a workflow and click Test.

2. Pick Guest or a specific contact.

3. Click Save & run and interact just like a customer would.

4. Tweak a step, hit Save & restart, and try again.

Great for

• Catching broken conditions and API calls before customers ever see them

• Testing how a workflow behaves for different types of contacts

• Debugging bigger, multi-step workflows without the guesswork

Every test run lands in your inbox with a Test badge, so it's easy to find and never gets mixed up with real conversations.

Give it a try on your next workflow.

Busy conversations get messy fast. A customer fires off three questions in a row, a thread jumps between topics, and suddenly it's not obvious which message you're actually answering. Now you don't have to leave anyone guessing. You can reply directly to a specific message, right inside the inbox.

What's new

• Reply to any message: Hover over a message and click Reply to quote it in your response. Works for customer messages, internal notes, Kai's replies, and emails.

• A clear "Replying to" banner: Before you send, a banner above the composer shows exactly which message you're responding to, with one click to cancel if you change your mind.

• Quoted context in the thread: Your reply carries a compact preview of the original message, so everyone can see what it's about at a glance.

• Jump to the original: Click any quote to jump straight to the message it references. A real lifesaver in long threads.

• Works with everything: Plain text, rich text, and attachments all get clean previews.

How it works

Open any conversation in your inbox, hover over the message you want to answer, and hit Reply. Type your response as usual and send. The quote comes along automatically. That's it.

No busy threads left behind. Give it a try and let us know what you think!

Your knowledge base isn't one-size-fits-all — now your AI agents aren't either. With knowledge scoping, you decide precisely which content each agent can use to answer, with simple tags.

What's new

• Tag any content — help center articles, FAQ snippets, uploaded files, and crawled website pages — right where you manage it.

• Scope any AI agent to those tags: let it use only content with certain tags, or everything except certain tags.

• Keep internal knowledge internal — content tagged internal stays out of customer-facing answers by default.

• Manage all content tags in one place under Project settings → Tags → Content tags.

• Scope Kai too — set a project-wide default, or scope a single "Let Kai answer" step in your workflows.

Great for

• Internal vs. external: give your team's copilot access to internal notes, while customers only ever see public content.

• Multiple products or brands: point a Billing agent at billing content and an Onboarding agent at onboarding content — no cross-talk.

• VIP & segments: route VIP users to an agent scoped to VIP-only knowledge.

How it works
Add tags to your content, open your AI agent's Knowledge tool, and pick All knowledge, Only these tags, or All except these tags. That's it — the agent instantly answers from just its slice of your knowledge base.

Available now.

Your team’s emails just got a more professional, personal touch. You can now create email signatures in Gleap that are automatically filled in with each agent’s own details on every reply.

What’s new:

• Reusable signatures – build one signature for your whole team under Settings → Email → Signatures, starting from a ready-made template or from scratch.

• Automatically personalized – name, role, photo, phone, calendar link and more are pulled from each agent’s profile, so every reply is signed correctly.

• Live preview & multi-language – see exactly how it looks as you edit, with a separate version per language.

• Human replies only – signatures are added when an agent replies, never on AI/bot messages.

Add a signature to your reply email template and you’re done — every human reply gets a polished sign-off, automatically.

We just added GLM 5.2 to Gleap, and honestly, this one's a big deal.

Z.ai (formerly Zhipu) released GLM-5.2 on June 13, 2026, and it's their most capable model yet. Here's why we're excited to bring it into the platform:

A genuinely usable 1M context window. The window jumps from 200K in GLM-5.1 to 1 million tokens, with outputs capped at 131,072 tokens per response. For Kai working across whole repos, long ticket histories, and sprawling conversation threads, that's exactly the kind of headroom that matters.

Built for real engineering work, not just chat. The GLM series emphasizes coding, tool usage, multi-step reasoning, repository analysis, and long-running agent workflows — which lines up perfectly with how Kai actually operates.

The benchmarks back it up. On SWE-bench Pro, GLM-5.2 scored 62.1, beating GPT-5.5 (58.6) and its own predecessor GLM-5.1 (58.4). On the long-horizon FrontierSWE test it hit 74.4%, surpassing GPT-5.5 (72.6%) and finishing in a near-tie with Claude Opus 4.8 (75.1%). It also took first place on the Design Arena benchmark with an ELO of 1360 — not bad for an open model.

Open weights, no borders. Z.ai released the weights under an MIT license, with their docs explicitly noting no regional limits and technical access without borders. Great news for anyone who cares about model sovereignty.

Running on our own EU GPU cluster. We're provisioning GLM 5.2 ourselves on our own GPU cluster in the EU — no third-party API, no data leaving the region. Your prompts, your code, your customer data stay inside our infrastructure. That's the whole point of an open-weights model: we get frontier-class capability and full control over where it runs.

And it's seriously cost-effective. It beats GPT-5.5 on multiple long-horizon coding benchmarks at roughly 1/6th the cost.

GLM 5.2 is available in Gleap now — pick it from the model selector and give it a spin.

We just added two of the most exciting models on the market to Gleap. One is the new frontier ceiling. The other is the best price/performance deal we've seen in a long time. Both are live for Kai today.

Here's the short version: pick Fable 5 when you want the absolute best, pick M3 when you want fast, cheap, and still really good.

Claude Fable 5 — frontier, no compromises

Fable 5 is Anthropic's first publicly available Mythos-class model, and it's the most capable model they've ever shipped to the general public. It's state-of-the-art on basically every benchmark that matters for the work Kai does — software engineering, knowledge work, vision, long-running tasks. The longer and messier the job, the bigger its lead.

In practice this means Kai can take on the gnarly stuff: deep multi-step reasoning, complex tickets that used to need a human, and long autonomous runs without losing the thread.

The catch: it's expensive. Fable 5 is the premium tier and priced like it ($10 / $50 per million tokens at the source). So we'd recommend it for your highest-value workflows where quality wins over cost — not for blasting through thousands of routine tickets. For anything in regulated high-risk territory (security, bio, chemistry), Anthropic automatically falls back to Opus 4.8, so you don't lose coverage there either.

Use it for: your hardest agentic tasks, complex resolutions, anything where "good enough" isn't good enough.

MiniMax M3 — the balance pick

M3 is the one we're most excited about for everyday use. It's an open-weight frontier model with a 1M-token context window, native multimodal input, and genuinely strong coding and agentic performance — it beats GPT-5.5 and Gemini 3.1 Pro on SWE-Bench Pro and gets close to the top Claude models.

And it does all that at a fraction of the cost. We're talking a different league on price — which means you can run M3 across your whole inbox without watching the meter.

The 1M context window is the part that quietly matters most for Kai: it can hold huge amounts of conversation history, docs, and code context at once, which makes resolutions sharper and handoffs cleaner.

Use it for: your default. High volume, fast responses, long context, great quality, low cost. This is the workhorse.

How to switch

Head to your Kai settings and pick the model per agent. You can mix and match — run M3 as your default and route the heavy hitters to Fable 5. No migration, no downtime, just flip the switch.

As always, more power on autopilot. Questions? Ping us — we read everything.

The Gleap team