# Gleap Full Context > Curated full Markdown context for the Gleap marketing website. This file intentionally focuses on canonical product, comparison, customer, blog, and featured integration content. Source index: https://www.gleap.io/llms.txt Documentation full context: https://docs.gleap.io/llms-full.txt # Gleap - AI support and self-healing software Source: https://www.gleap.io/ Description: Ship software that heals itself. Gleap's AI agents answer users, turn bugs into pull requests, and plan the roadmap. Trusted by 4,500+ software teams. Ship software that heals itself. AI support that runs your SaaS, not just your inbox. Support becomes fixes. Feedback becomes shipped features. Your team only builds what's next. Start 14-day free trial Book demo 4.6/5 on G2 Trusted by 4,500+ teams worldwide Papa Johns FeatureTabsBento AI agents Gleap inbox with an AI summary beside the customer-facing widget on mobile. Software on Autopilot: The Self-Driving Development Era Watch: Software on Autopilot Support, feedback, roadmap, and code in one loop Powering 4,500+ of the fastest-moving software teams AI agents that run your software. From a user's bug report to a merged pull request - specialist AI agents work together on support, feedback, product, and code. It's like hiring top 1% teammates who never sleep. The bug loop The feature loop The support loop From bug report to merged PR A user reports a bug. Kai Resolve captures technical data like console logs and screenshots, then automatically categorizes and routes issues so engineering can understand recurring patterns faster. Confirmed bugs enter Kai Code plan mode, then build mode, then a pull request. The reporter gets notified when it ships. That keeps the support team and engineering aligned across websites and mobile apps. Gleap dashboard showing a bug report with session replay, console logs, and a Kai Code pull request. From feature request to shipped feature Kai PM reads user feedback from direct requests, votes, surveys, support themes, and product gaps routed by Kai Resolve. It turns that input into actionable insights for product teams, prioritizes feature requests into a branded public roadmap for transparency, writes the spec, hands approved work to Kai Code, then notifies askers after release. Users can view the roadmap, and interactive changelogs let them react and comment on each release. Gleap roadmap board showing clustered feature requests with revenue-weighted prioritization. 80% answered before anyone reads it Kai handles routine tier-1 support across channels and languages. When an issue needs investigation, Kai Resolve routes it to Kai Code, Kai PM, a safe operational action, or a Gleap Inbox Task for a human. Gleap inbox showing Kai resolving an inbound support conversation in real time. Real outcomes from Gleap customers Inbound support handled by Kai Commonplace uses Gleap for feedback, support, knowledge base, roadmap work, JIRA, HubSpot, and Kai-powered first-line support. 50-60% Setup and migration Salesforge imported contacts and help center articles in minutes, then moved support, roadmap, news, outreach, and Slack into one workspace. <1 day Customer inquiries handled by AI Lywand left a siloed Freshdesk setup for one integrated platform, with an AI chatbot and knowledge base that resolve half of all customer inquiries. 50% To full integration Partfox moved from restrictive per-seat tooling to live chat, AI support, feedback, product tours, checklists, and surveys. 10 days Customer communication platform Tridonic centralized tickets, surveys, AI chat, product tours, tooltips, settings, reports, and support workflows in Gleap. Meet your new teammates Specialist AI agents, each top 1% at one job AI support agent. Resolves routine inbound conversations across channels, with usage billed by actual tokens. Kai Resolve Investigation and routing agent. Uses MCP, tools, source context, read-only data, APIs, and ticket history to decide the next best step. Kai Code Self-driving development agent. Customer bugs and approved specs enter plan mode, build mode, and pull requests. Kai PM AI product manager. Clusters feature demand, prioritizes the roadmap, hands specs to Kai Code, and closes the release loop. Kai Custom Agents No-code builder for any agent your business needs. Connects to 1,000+ integrations via Composio. One platform Shared context across agents. SOC 2 Type 2. GDPR. Unlimited seats on Team. Marble texture background. Gleap inbox dashboard showing real-time conversations and AI resolutions. A clean workspace with a keyboard and notebooks under warm lighting. Commonplace runs feedback, support, knowledge base, and roadmap on Gleap - with Kai resolving half or more of inbound conversations before a human reads them. Choose your agent stack. Usage-based AI. $49/mo For solo builders and side projects. 1 seat 1 project Kai AI support Live chat In-app bug reporting Feature roadmap Knowledge base Start free trial $149/mo For startups and growing teams. Everything in Starter + Unlimited seats Unlimited projects All support channels Custom domains Third-party integrations Outbound messaging $299/mo For teams that want Kai to investigate, resolve & ship fixes. Everything in Team + 25% off on AI tokens All AI models Custom agents AI Max from $999/mo For scale and complex compliance. Everything in Pro + SOC 2 Type II DORA support HIPAA BAA Pay by invoice Dedicated CSM Priority support & SLA Talk to sales /contact Common questions ### What is software that heals itself? Software where the loop from bug report to shipped fix runs on its own. When a user reports a bug, Kai Resolve captures console logs, session data, and technical context, then investigates. Confirmed bugs enter Kai Code - plan mode, build mode, pull request - and land in GitHub, GitLab, or Bitbucket for your team to review. The reporter gets notified when the fix ships. Your team approves what runs; the agents do the work. ### How is Gleap different from Intercom, Zendesk or Help Scout? Those tools stop at the support ticket. Gleap doesn't. When a customer reports a bug through website feedback or in-app bug reporting , Kai Resolve investigates and Kai Code turns the confirmed issue into plan mode, build mode, and a pull request. When they request a feature, product feedback software and Kai PM cluster demand, prioritize the roadmap, hand the approved spec to Kai Code, and notify customers when it ships. You're not paying for five tools - you're paying for one loop. ### What does "AI agents working together" actually mean? Specialist agents that share context, each built for a distinct job: Kai handles tier-1 support. Kai Resolve investigates complex issues and routes the next step. Kai Code turns confirmed bugs and approved specs into pull requests. Kai PM turns feature demand into prioritized specs, release notes, and customer notifications. Kai Custom Agents is the no-code builder for whatever else your business needs. The agent set will keep growing. ### How does Kai compare to Intercom Fin or Zendesk AI? Different pricing models: Fin charges $0.99 per resolution. Kai is billed by actual token usage - on average about $0.04 per message - so you pay for the AI work performed instead of a per-resolution success fee. Team uses Auto as the model choice; Pro unlocks all AI models. Both target the same ~80% deflection rate. ### Can I use my existing local coding agents? Yes. Kai Code runs in Gleap Cloud with frontier and open-source models, and can also use your local Claude Code, Codex, or OpenCode setup. Pull requests land in GitHub, GitLab, or Bitbucket. Jira and GitHub Issues can stay in sync for status and planning, but Kai Code is where the implementation work happens. ### Who uses Gleap? 4,500+ software teams run on Gleap - from indie founders and fast-growing startups to Microsoft, Squarespace, UNICEF, and Papa Johns. Gleap is rated 4.6/5 on G2. Teams typically switch from stacks like Intercom + Instabug + Canny and consolidate support, bug reporting, feedback, and roadmap into one platform. ### Is there a free trial? Yes - 14 days. You can test the AI agent platform and the same product 4,500+ teams use in production. AI usage is billed by actual tokens. ### How does pricing scale? Starter includes Kai AI support, live chat, in-app bug reporting, feature roadmap, knowledge base, one seat, and one project. Team is $149/mo with unlimited seats and projects, all support channels, custom domains, third-party integrations, outbound messaging, and Auto as the model choice. Pro is $299/mo and adds custom agents, 25% off on AI tokens, all AI models, Kai PM, Kai Code, and Kai Resolve. Enterprise adds SOC 2 Type II, DORA support, HIPAA BAA, SSO, BYOK, dedicated CSM, and priority support & SLA. No per-seat tax and no per-resolution success fee. ### Is Gleap SOC 2 and GDPR compliant? Yes. SOC 2 Type II audited. GDPR-compliant with EU data residency available on Enterprise. DPA on request. ### How long does setup take? Most teams are live in under a day. Drop the SDK in your app, point Kai at your help center and codebase, and it's running. Migration helpers for Intercom, Zendesk, Canny, and Instabug shorten the switch further. <2 min Response SLA on 60-70 daily tickets Stop maintaining software. Start building your vision. See pricing /pricing 4.6 / 5 4,500+ teams --- # Gleap Platform - AI Agents + Every Support Tool | Gleap Source: https://www.gleap.io/platform Description: One platform. Specialist AI agents plus every tool your team needs - chat, bug reporting, knowledge base, roadmap, surveys, marketing automation. From $149/mo. One platform. Every tool your team needs. Start free trial Gleap platform combining AI support, roadmap, bug reporting, and custom agents. Agent skills MCP tools Powering 4,500+ of the fastest-moving software teams AI agents plus every tool to run them. Support, bug reporting, roadmap, knowledge base, surveys, marketing automation, CRM pipelines - one platform of specialist AI agents that share context. Teams replace 5+ tools the week they switch. SOC 2. GDPR. The agents Top 1% specialists. Connected. Sharing context. Tier-1 AI support. Resolves routine inbound with usage billed by actual tokens. Kai Resolve Investigation and routing. Uses MCP, tools, source context, read-only data, APIs, and ticket history. Kai Code Self-driving development. Customer bugs and approved specs enter plan mode, build mode, and PRs. Kai PM AI product manager. Clusters demand, prioritizes the roadmap, hands specs to Kai Code, and writes release notes. Custom Agents No-code builder. Build any workflow on Gleap data + 1,000+ integrations. MCP Server Connect approved tools and data sources so agents can investigate and act with scoped permissions. Real outcomes from Gleap customers Inbound support handled by Kai Commonplace uses Gleap for feedback, support, knowledge base, roadmap work, JIRA, HubSpot, and Kai-powered first-line support. 50-60% Setup and migration Salesforge imported contacts and help center articles in minutes, then moved support, roadmap, news, outreach, and Slack into one workspace. <1 day Customer inquiries handled by AI Lywand left a siloed Freshdesk setup for one integrated platform, with an AI chatbot and knowledge base that resolve half of all customer inquiries. 50% To full integration Partfox moved from restrictive per-seat tooling to live chat, AI support, feedback collection, product tours, checklists, and surveys. 10 days Customer communication platform Tridonic centralized tickets, surveys, AI chat, product tours, tooltips, settings, reports, and support workflows in Gleap. Multichannel inbox Gleap unified inbox showing multichannel customer conversations. Customer support Widget, email, WhatsApp, Instagram, Messenger, Telegram. Kai handles routine support. Kai Resolve investigates and routes the complex cases. See multichannel support /product/multichannel-customer-support-platform In-app bug reporting + session replay Animated Gleap in-app bug reporting flow from issue capture to submitted report. Bug reporting Users shake their phone. Gleap captures session replay, console, network, and device context. Confirmed bugs flow into Kai Code plan mode. See bug reporting /product/in-app-bug-reporting Help center and AI knowledge base Gleap knowledge base help center with article preview. Knowledge base Native help center. Imports from Intercom, Zendesk, and Freshdesk. Kai reads every article, cites sources, and resolves faster. See knowledge base /product/knowledge-base-software-to-scale-your-support Every platform feature 29 surfaces. One workspace. Kai support agent Resolves routine inbound support across channels with token-based AI usage. /kai Investigates complex tickets, checks tools and context, then routes the next best step. /kai-resolve Turns confirmed bugs and approved specs into plans, code changes, and pull requests. /kai-code Clusters feedback, prioritizes roadmap work, writes specs, and closes the release loop. /kai-pm Kai Custom Agents No-code agent builder on Gleap data plus 1,000+ integrations via Composio. /kai-custom-agents Bring tickets, contacts, statistics, help center, and news into Claude, Cursor, or VS Code. /mcp AI copilot Drafts, summaries, tone rewrites for your human agents. /product/ai-support-copilot-for-leading-support-agents Live chat AI-first widget. Native iOS, Android, RN, Flutter SDKs. /product/live-chat-for-apps-websites Workflows & bots No-code rules engine on top of Kai - routing, escalation, triggers. /product/workflows-and-custom-chatbots Multichannel support Widget, email, WhatsApp, Insta, Messenger, Telegram - one inbox. WhatsApp support Bring WhatsApp conversations into the same AI-first inbox and customer timeline. /product/whatsapp CRM pipelines Sales, onboarding, and renewal boards over your companies and contacts - linked to conversations. /product/crm-pipelines Onboarding checklists In-app step-by-step guides to first user value. /product/in-product-checklists Product tours Co-browse walkthroughs that adapt to user behaviour. /product/product-tours Contextual hints attached to buttons, menus, fields, and feature areas. /product/tooltips Info cards Lightweight in-product cards for guidance, next steps, and feature education. /product/info-cards In-app bug reporting Session replay, console logs, and customer impact. Starts plan mode. Website feedback tool Visual website QA, annotated screenshots, replay, and technical context. /product/website-feedback-tool Native help center. Imports from Intercom, Zendesk, Freshdesk. Product feedback software Requests, support themes, surveys, roadmap, and changelog in one loop. /product/product-feedback-software Public roadmap Voting board with revenue-weighted prioritisation by Kai PM. /product/public-roadmap-feature-requests News & release notes Auto-written changelog. Personalised notifications to voters. /product/release-notes-news-software Surveys (NPS + CSAT) Triggered at the right moment. Responses feed Kai PM directly. /product/customer-feedback-surveys-for-apps-websites Marketing automation Lifecycle messaging across email, push, in-app messages, banners, surveys, and news. /product/marketing-automation-software-tools Email marketing automation Visual emails triggered by product behavior, lifecycle stage, and customer context. /product/email-marketing-automation In-app messaging Targeted messages across web and mobile apps with reply-ready customer context. /product/messaging Push notifications Timely mobile reminders, lifecycle nudges, product news, and customer updates. /product/push-notifications In-app banners Inline or floating announcements with targeting, styling, close controls, and CTAs. /product/in-app-banners 40+ integrations + 1,000+ via Composio Slack, Jira, GitHub, Salesforce, Stripe, and on. /integrations Switching from Intercom to Gleap was a win-win. Superior functionality at a fraction of the cost. It's elevated our user feedback and customer support experience immensely. Dylan Matthews CTO, White Inc. Dylan Matthews, CTO at White Inc. One platform. Usage-based AI. $49/mo For solo makers and small teams. 1 seat 1 project Kai AI support Feature roadmap $149/mo The support and product loop for growing teams. Everything in Starter + Unlimited seats Unlimited projects All support channels Custom domains Third-party integrations Outbound messaging $299/mo The full autopilot with code and investigation. Everything in Team + 25% off on AI tokens All AI models Custom agents AI Max from $999/mo Scale + compliance. Everything in Pro + SOC 2 Type II DORA support HIPAA BAA Pay by invoice Dedicated CSM Priority support & SLA Talk to sales /contact About the platform ### What's included in the Gleap platform? The platform includes AI support bot ( Kai ), AI copilot, live chat, workflows & bots, multichannel support, WhatsApp, onboarding checklists, product tours, tooltips, info cards, in-app bug reporting , website feedback , AI knowledge base software , product feedback software , public roadmap, news & release notes, surveys, marketing automation, email automation, in-app messaging, push notifications, in-app banners, and CRM pipelines . Starter includes Kai AI support, live chat, in-app bug reporting, feature roadmap, knowledge base, one seat, and one project. Team adds unlimited seats, unlimited projects, all support channels, custom domains, integrations, outbound messaging, and Auto as the model choice. Pro adds custom agents, 25% off on AI tokens, all AI models, Kai PM, Kai Code, and Kai Resolve. Enterprise adds SOC 2 Type II, DORA support, HIPAA BAA, SSO, BYOK, dedicated CSM, and priority support & SLA. Plus 40+ native integrations + 1,000+ via Composio. ### How does Gleap replace Intercom, Instabug, and Canny? Intercom + Instabug + Canny is the classic SaaS stack. Gleap collapses it onto one platform of specialist AI agents that share context. Kai replaces Intercom's support layer. Kai Resolve investigates complex issues. Kai Code turns confirmed bugs into plan mode, build mode, and pull requests. Kai PM replaces Canny plus Beamer-style release loops. For most teams, switching cuts tooling cost ~70-85% while doing more. ### How is AI billed? AI is billed by actual token usage. Team uses Auto as the model choice, while Pro unlocks all AI models and includes 25% off on AI tokens. That's different from Intercom Fin's per-resolution model ($0.99 each): Gleap charges for the AI work performed, not a success fee for each resolved conversation. ### How many integrations does Gleap have? 40+ native integrations (Slack, Jira, GitHub, GitLab, Bitbucket, Stripe, Salesforce, HubSpot, Notion, Zapier, Make, Webhooks, Segment) and 1,000+ available via Composio. ### Is Gleap SOC 2 compliant? Yes. SOC 2 Type II audited. GDPR compliant. DPA on request. EU and US data residency on Enterprise. HIPAA BAA on Enterprise. ### How long does setup take? Under a day for most teams. Drop the SDK in your app (one line of JS or platform-native), point Kai at your help center, configure routing. Importers from Intercom, Zendesk, Canny, and Instabug shorten the switch. Stop running five tools. Start running one platform. See pricing /pricing 4.6 / 5 G2 · 4,500+ teams --- # Gleap Pricing - AI Agents from $49/mo | Unlimited Seats Source: https://www.gleap.io/pricing Description: Gleap pricing starts at $49/mo. Team is $149/mo with unlimited seats; Pro at $299/mo adds Kai Code, Kai PM, and Kai Resolve. AI billed by tokens. 14-day free trial. AI usage is billed by actual tokens and the selected model. Pro gets 25% off on AI tokens. Annual billing Save 20% $49/mo For solo makers shipping their first product. 1 seat 1 project Kai AI support Live chat In-app bug reporting Feature roadmap Knowledge base Start 14-day free trial $149/mo For growing teams that want unlimited seats and projects. Everything in Starter + Unlimited seats Unlimited projects All support channels Custom domains Third-party integrations Outbound messaging $299/mo For teams that want Kai to investigate, resolve & ship fixes. Everything in Team + 25% off on AI tokens All AI models Custom agents Kai PM Kai Code Kai Resolve AI Max from $999/mo For security, compliance, model control, and custom support. Everything in Pro + SOC 2 Type II DORA support HIPAA BAA Pay by invoice Dedicated CSM Priority support & SLA Talk to sales /contact Monthly billing $59/mo $179/mo $359/mo from $1,199/mo Gleap for startups 50% off Team or Pro for your first year. Apply now /early-stage-startups Plan basics Team seats Number of workspace seats included in your Gleap plan. Manage multiple products, apps, or workspaces inside one organization. Model choice Team uses Auto as the model choice. Pro unlocks manual access to all supported AI models. All AI models + BYOK AI token discount Pro gets 25% off on AI tokens. Enterprise can use custom AI usage terms. 25% off Service delivery commitments for reliable and timely support. 3 days 2 days 24 hours Custom SLA Ticketing & inbox Shared Inbox Centralize communication so your team can collaborate on customer support. Talk to customers directly through the Gleap widget. Identify and resolve bugs with visual feedback and technical details. Operating hours Specify office hours for live support and manage customer expectations. Team inboxes Create multiple team inboxes and auto-assign tickets for streamlined support. Create powerful workflows to automate repetitive support and routing tasks. Kai support Kai chatbot Significantly reduce support volume with Gleap's AI support agent. Multiple content sources Kai can use FAQs, external sites, files, API sources, and help center articles for better answers. AI summary Condense customer feedback with AI summaries to streamline issue resolution. AI reply Get suggested Kai responses directly in the Gleap dashboard for faster support. AI tools Let Kai perform approved actions in your product, such as transactions or order cancellations. Copilot helps your support team answer faster with AI-assisted responses. Build custom AI agents for your workflows, data, and business processes. Support channels Support widget for your apps and website. Unified email inbox for your support team. Send and receive messages on WhatsApp. Send and receive messages on Telegram. Send and receive messages on Instagram. Facebook Messenger Send and receive messages on Facebook Messenger. Gather actionable customer insights efficiently. Chat messages Send one-time messages to selected users through the widget. Highlight key information, promotions, or announcements with customizable banners. Push notifications Engage users with updates and important messages directly on their devices. News / release notes Keep users informed about the latest product updates and changes. Product tours Introduce users to product features and workflows with interactive tours. Guide users through processes or feature discovery with step-by-step checklists. Emails & newsletters Create and send email campaigns to targeted audiences. Guide users with contextual hints inside your product. Create modals and modal carousels for in-app announcements. Public roadmap Share future updates and involve users in your product development journey. Feature request management Collect and prioritize feature requests. Let users vote and comment on suggestions. Help center Public knowledge base Help users self-serve with a library of resources, answers, and guides. Unlimited collections & articles Create and organize help content without collection or article limits. Platform & security Analyze Kai, team responsiveness, and support performance to optimize your customer loop. Use your own domains across help centers, roadmaps, and outbound emails. Remove Gleap branding Remove Gleap logos and references from customer-facing surfaces. Automatically ship Gleap tickets and context to third-party tools. API access Integrate deeply with your systems and access Gleap programmatically. Access Gleap's SOC 2 Type II report. Vendor support for financial entities regulated under DORA: due-diligence pack, contractual terms, and audit cooperation. Business Associate Agreement for customers subject to HIPAA. Single sign-on for secure enterprise identity management. Bring your own model Use your own model endpoint or private model infrastructure. Bring your own AI provider key for model usage. Pay through annual invoices instead of card billing. Get fast, dedicated help with prioritized requests and a custom SLA. Support Slack channel Work with the Gleap team in a dedicated Slack support channel. Get a dedicated customer success manager for onboarding, reviews, and strategic support. Self-driving AI AI product management for roadmap, prioritization, and release loops Kai PM helps turn customer requests into structured roadmap and release work. Self-driving development from confirmed bugs and approved specs Kai Code investigates accepted issues, plans the work, and ships pull requests. Autonomous investigation and routing for complex tickets Kai Resolve investigates support tickets, gathers context, and routes work to the right next step. ### Ready to put Kai to work? Start free. Upgrade when Kai closes the loop. Pricing FAQ ### How much does Gleap cost? Gleap starts at $49/mo for Starter when billed annually. Team is $149/mo, Pro is $299/mo, and Enterprise starts at $999/mo. Month-to-month pricing is $59/mo for Starter, $179/mo for Team, $359/mo for Pro, and from $1,199/mo for Enterprise. ### What does annual billing mean? Annual billing saves 20% and is still shown as a monthly price on this website. Pages without a billing toggle show the annual monthly-equivalent price. ### Does Gleap charge per seat? Starter includes one seat and one project. Team, Pro, and Enterprise include unlimited seats and unlimited projects, so you are not penalized for adding seats. ### Which plan includes Kai Code and Kai Resolve? Starter includes Kai AI support, live chat, in-app bug reporting, feature roadmap, knowledge base, one seat, and one project. Team includes unlimited seats, unlimited projects, all support channels, custom domains, third-party integrations, and outbound messaging. Pro and Enterprise include custom agents, all AI models, Kai PM, Kai Code, and Kai Resolve. ### Is Gleap cheaper than Intercom? Yes for most growing teams. Gleap Team is $149/mo with unlimited seats when billed annually, while Intercom Advanced + Fin often combines per-seat pricing with AI billed separately. Teams that need custom agents, Kai PM, Kai Code, and Kai Resolve can use Pro at $299/mo. ### How is AI usage billed? AI usage is billed by actual tokens and the selected model. Team uses Auto as the model choice. Pro unlocks all AI models and gets 25% off on AI tokens, while Enterprise can use all AI models, BYOK, and custom AI usage terms. ### Does Gleap have a startup program? Yes. Eligible early-stage startups can get 50% off Team or Pro for the first year. Apply on the startup program page . ### Does Gleap have a free trial? Yes. Gleap has a 14-day free trial. Setup takes under 10 minutes: connect your help center, paste your website URL, and Kai can start answering questions the same day. ### Can I upgrade or downgrade at any time? Yes. Upgrades take effect immediately and are pro-rated for the rest of the billing cycle. Downgrades take effect at the end of your billing cycle. You can switch between monthly and annual billing at any time. Stop maintaining software. Start building your vision. 4.6 / 5 G2 · 4,500+ teams --- # Kai - AI Support Agent That Resolves 80% of Tickets | Gleap Source: https://www.gleap.io/kai Description: Meet Kai, Gleap's AI support agent. Resolves up to 80% of tickets instantly in 80+ languages, across every channel - billed by tokens, not per resolution. Meet Kai. A top 1% support agent that never sleeps. Kai resolves up to 80% of tickets instantly - in 80+ languages, on every channel, with answers from your real product knowledge. Your customers stop waiting. Your team stops drowning. Start free trial Book demo 4.6/5 on G2 Trusted by 4,500+ teams worldwide Papa Johns FeatureTabsBento Kai answering a customer conversation in the Gleap Inbox. Start 14-day free trial From first answer to expert handoff Powering 4,500+ of the fastest-moving software teams Resolves 80%. Hands off the rest with full context. While most support teams are still triaging yesterday's queue, Kai has already answered - in the customer's language, with sources cited. Billed by actual tokens, not per resolution. Resolves 80% of tickets instantly No scripted decision trees. No keyword matching. Kai understands what customers actually mean - and gives them a real answer in seconds. Gleap inbox showing Kai resolving a support conversation in real time. Multichannel from one inbox Widget, email, WhatsApp, Instagram, Messenger, Telegram. A customer who starts in chat and follows up by email gets seamless context. Gleap multichannel inbox unifying widget, email, WhatsApp and Instagram conversations. 6 channels out of the box Web widget, email, WhatsApp, Instagram, Messenger, Telegram. 80+ languages, auto-detected No language-specific bots to maintain. Kai speaks the customer's language. Live in under 10 minutes Paste your domain. Point Kai at your help center. Done. SOC 2 Type 2 + GDPR Topic restrictions, EU residency, full audit logging. Smart escalation Investigated before a human sees it. If Kai can't resolve, it escalates to Kai Resolve. The agent investigates with MCP tools, source context, ticket history, APIs, and approved read-only data access, then routes the issue to Kai Code, Kai PM, a safe operational action, or a Gleap Inbox Task for a human. See Kai Resolve /kai-resolve Gleap ticket with Kai Resolve's autonomous investigation summary attached. Copilot for your agents Make every agent your best agent. When Kai isn't resolving, it's helping your team. Drafts replies, suggests articles, translates messages, summarises long threads - right inside the inbox. See Kai Copilot /product/ai-support-copilot-for-leading-support-agents Gleap agent inbox with Kai Copilot draft replies and article suggestions. “Superior features for 75,000+ users.” Airspeed switched from UserSnap to Gleap to support multiple platforms and more than 75,000 users with a stronger feedback and support workflow. Gaylan Greenawalt PM, Airspeed Choose your AI brain Auto on Team. All AI models on Pro. Frontier models OpenAI GPT, Anthropic Claude, Google Gemini, xAI Grok - frontier model families, available for Pro workflows that need manual model choice. Gleap model picker showing GPT, Claude, Gemini, and Grok options. Open source & specialist Llama, Mistral, Qwen, DeepSeek, and other open-source or specialist models. Pro teams can pick cost-efficient models for long context and multilingual support. Open-source model options in the Gleap model picker. Bring your own LLM Enterprise plans support custom model endpoints. Full control over cost, latency, and data residency. Bring your own cloud model or run it on your own hardware. Custom LLM endpoint configuration in Gleap Enterprise. Kai learns from everything you have Seven content sources, one coherent answer Add reusable answers, policy blocks, and product notes Kai can cite consistently across conversations. Point Kai at your domain. It indexes pricing pages, feature pages, FAQs - anything public. Help articles Native Gleap help center plus imports from Intercom, Zendesk, and Freshdesk. Cited in every answer. Upload PDFs, product manuals, onboarding guides, and internal SOPs. Kai indexes and retrieves automatically. Code repositories Index connected repositories directly. Kai finds answers in code when docs haven't caught up yet. Read your Notion pages and databases. Respects permissions. Stays in sync as docs evolve. Index videos and playlists so Kai can answer from tutorials, webinars, and product walkthroughs. $149/mo Kai support with token-based AI usage and unlimited seats. Kai included AI usage billed by actual tokens Auto model choice Unlimited seats All support channels (widget, email, WhatsApp, Instagram, Messenger, Telegram) Custom domains Priority human support Pro unlocks all AI models, Kai PM, Kai Code, and Kai Resolve Bring your own LLM. EU data residency. Custom AI usage terms. Talk to sales /contact Enterprise team configuring Gleap with their own LLM endpoint. About Kai ### How does Kai handle 80% of support tickets? The same 20 questions account for 80% of typical SaaS ticket volume - password resets, billing, how-tos, basic troubleshooting. Kai reads your snippets, websites, help articles, files, code repositories, Notion workspace, and YouTube content, then answers using your actual product context - not keyword matching. Most teams see 60–85% deflection within two weeks. ### How is Kai different from Intercom Fin? Different pricing models. Fin is priced at roughly $0.99 per resolution. Kai usage is billed by the actual tokens used - on average about $0.04 per message, with a conversation running roughly 4.3 messages - so you pay for the AI work performed instead of a per-resolution success fee. Team uses Auto as the model choice. Pro unlocks all AI models across OpenAI GPT, Anthropic Claude, Google Gemini, xAI Grok, and open-source models. On Pro, unresolved issues can route to Kai Resolve for investigation before involving a human. ### How is Kai different from Zendesk's AI agent? Kai is built into a platform of specialist AI agents that can include investigation and routing ( Kai Resolve ), self-driving development ( Kai Code ), and an AI product manager ( Kai PM ). Zendesk's AI stops at Tier 1 deflection. Kai also captures full session replay, console logs, and network requests on bug-related tickets - Zendesk doesn't offer that natively. Pricing starts at $49/mo for Starter with Kai; Team is $149/mo with unlimited seats and Auto as the model choice; Pro adds all AI models, Kai PM, Kai Code, and Kai Resolve. ### What channels does Kai work on? Six channels out of the box: in-app web widget, mobile (iOS, Android, React Native, Flutter), email, WhatsApp Business, Instagram DMs, Facebook Messenger, and Telegram. All land in one unified inbox - a customer who starts in chat and follows up by email gets a seamless thread. Kai responds in 80+ languages based on detected language. ### What happens when Kai can't resolve a ticket? On Pro, it escalates to Kai Resolve first. Kai Resolve investigates with MCP tools, source code, ticket history, APIs, and approved read-only data access. Confirmed bugs go to Kai Code , feature or product gaps go to Kai PM , safe operational issues can be resolved directly, and judgment calls become Gleap Inbox Tasks for a human with the investigation dossier attached. ### Does Kai work with my existing knowledge base? Yes. Kai imports from Gleap's native help center plus Intercom, Zendesk, and Freshdesk knowledge bases, and also reads snippets, website crawls, uploaded files, Notion workspaces, YouTube playlists, and connected code repositories. Most teams have Kai live in under 10 minutes. ### How does Kai handle sensitive or regulated topics? Configure topic restrictions and escalation rules per subject - medical, legal, financial - so Kai declines to advise on restricted topics and either routes to a human or returns a pre-approved response. Kai is SOC 2 Type II certified and GDPR compliant, with EU and US data residency on Enterprise. Your customers deserve an instant answer. Give them one. See pricing /pricing 4.6 / 5 G2 · 4,500+ teams --- # Kai Resolve - AI Support Engineer for Hard Tickets | Gleap Source: https://www.gleap.io/kai-resolve Description: Kai Resolve adds a top 1% AI support engineer to your team, checking tools, code, APIs, databases, and ticket history before resolving or routing hard tickets. Meet Kai Resolve: A top 1% support engineer on every escalation. The hard tickets - the ones that need code, data, billing history, and judgment - get fully investigated before a human ever sees them. Your senior people stop being the bottleneck. Start free trial Book demo 4.6/5 on G2 Trusted by 4,500+ teams worldwide Papa Johns FeatureTabsBento Kai Resolve resolving a teammate invite issue in the Gleap Inbox. Start 14-day free trial From investigation to next best action Powering 4,500+ of the fastest-moving software teams Meet Kai Resolve, the agent built for tickets that need proof. Kai handles the common questions. Kai Resolve takes the messy escalations that need tools, code, data, history, and judgment, then resolves safe issues directly or routes the complete dossier to Kai Code, Kai PM, or a human Task. Investigates before a human is interrupted Kai Resolve reads the conversation, finds what is missing, and checks MCP tools, APIs, source code, read-only databases, and connected systems in parallel. It assembles the context a skilled engineer would usually gather by hand. Kai Resolve dashboard showing an autonomous investigation across code repos, Stripe, and ticket history. Reads your real systems, not just the ticket Connect GitHub, GitLab, or Bitbucket in read-only mode. Kai Resolve can inspect recent code paths, account state, payments, CRM data, and ticket history before deciding what should happen next. Kai Resolve reading code in a repository to investigate a customer-reported bug. Works across your stack MCP tools, GitHub, GitLab, Bitbucket, Stripe, Salesforce, read-only databases, and custom APIs. Takes approved actions Issues refunds, updates accounts, and retries flows when permissions allow, with a full audit trail. Pulls humans in for judgment Creates a Gleap Inbox Task for the right human, waits for completion, then continues the workflow. Leaves an audit trail Every decision logged. Every API call traced. Every past ticket becomes memory Find the resolution your team already proved once. Kai Resolve scans your ticket history for similar cases, compares what worked before, and pulls the winning resolution into the current investigation instead of starting from zero. See Kai Code /kai-code Routes the work, not just the ticket Bugs to Kai Code. Feature gaps to Kai PM. Humans only when needed. Confirmed code defect? Kai Code gets the dossier. Product gap? Kai PM gets the evidence. Safe operational issue? Kai Resolve acts. Human judgment? It creates an Inbox Task and continues when done. See Kai PM /kai-pm The Kai Resolve routing chain: investigation → Kai Code, Kai PM, or human with dossier. “Super-fast turnaround on feature requests.” Transaction Network Services highlights Gleap’s turnaround on new feature requests as part of reducing errors in the product. Martin Hardman Transaction Network Services Jobs Kai Resolve can take off your queue A safe action, a human approval, or a handoff with the facts already attached. Refund approvals Kai Resolve confirms the duplicate charge in Stripe and creates an Inbox Task for your billing lead. Once approved, Kai Resolve issues the refund and closes the ticket. Subscription changes High-value account changes require human sign-off. Kai Resolve drafts the proposed action as an Inbox Task and routes it to the right owner. Data deletion requests For GDPR deletion requests, Kai Resolve compiles the targets across systems, creates a human approval Task, then executes deletion auditably. What Kai Resolve can investigate The ticket, the tools, the account, the code path, and the history behind it Code repositories GitHub, GitLab, Bitbucket. Read-only source access to inspect files, recent commits, and the relevant code path. MCP tools Calls approved MCP tools and connected apps to gather facts before choosing the next agent or human Task. Historical tickets Semantic search across every ticket your team has ever closed. Learn from every resolution. Billing and CRM Stripe, Salesforce, HubSpot. Query payment history, account tier, contract value, and ownership. Read-only databases Query product, account, and event data without granting write access at the investigation layer. Custom APIs Any internal system you can expose. Order management, feature flags, deployment logs, internal tooling. $299/mo Kai Resolve access with token-based investigation usage. Everything in Team 25% off on AI tokens All AI models Kai PM Kai Resolve billed by actual tokens + selected model Kai Code for confirmed bugs Code repository integrations Stripe + Salesforce + custom API access Inbox Tasks for human-in-the-loop approvals Open model choice: OpenAI GPT, Anthropic Claude, Google Gemini, xAI Grok, plus open-source models Unlimited team seats AI Max Custom SLAs. Dedicated infrastructure. Bring your own LLM. Talk to sales /contact Enterprise customer running Kai Resolve on a dedicated investigation infrastructure. About Kai Resolve ### What is Kai Resolve? Kai Resolve is Gleap's AI support investigator for escalated tickets. It takes over when Kai can't resolve a ticket, investigates with MCP tools, source code access, read-only databases, live APIs, and ticket history, then decides the next step: resolve safe operational issues directly, route confirmed bugs to Kai Code , route product gaps to Kai PM , or create a Gleap Inbox Task for a human. ### How does Kai Resolve support self-driving software development? Kai Resolve is the investigation layer in self-driving software development . It turns escalated support tickets into evidence-backed next steps: confirmed bugs go to Kai Code with replay, logs, source context, and impact; product gaps go to Kai PM with customer demand and business context. ### How is Kai Resolve different from Kai? Kai is the first-level support agent that handles the 80% resolvable from your knowledge base - password resets, billing questions, how-tos - in seconds. Kai Resolve handles the hard 20% requiring actual investigation: reading source code, querying read-only databases, checking Stripe or Salesforce, cross-referencing tickets, and taking safe operational actions like issuing refunds. Code changes route to Kai Code. ### How is Kai Resolve different from Sierra AI? Sierra is an autonomous Tier 2 support agent that handles customer conversations end-to-end. But Sierra stops at the support conversation, while Kai Resolve routes confirmed bugs to Kai Code , product gaps to Kai PM , and human-judgment steps to Inbox Tasks. Kai Resolve also investigates with source code, read-only database access, and MCP tools. Pricing: Sierra is enterprise-only with custom contracts ($100K+/yr); Gleap Pro is $299/mo when billed annually, with Kai Code and Kai Resolve included. AI usage is billed by actual tokens and selected model. See the Sierra alternative . ### How is Kai Resolve different from Decagon? Decagon is an enterprise-tier autonomous AI agent platform focused on the support conversation layer. Kai Resolve goes further: it investigates with source code, read-only databases, MCP tools, and connected systems, takes safe operational actions like Stripe refunds or Salesforce updates, and routes confirmed bugs to Kai Code for self-driving development. Decagon contracts typically start at $50K-$200K/year; Gleap Pro is $299/mo when billed annually, with Kai Code and Kai Resolve included. AI usage is billed by actual tokens and selected model. See the Decagon alternative . ### Can Kai Resolve access my source code and databases? Yes. Kai Resolve connects to GitHub, GitLab, and Bitbucket and reads relevant files during investigation. It can also query approved read-only databases and MCP tools. The investigation layer is read-only for code and databases - writes happen through Kai Code when a code fix is needed, or through explicit operational permissions for systems like Stripe. ### What does Kai Resolve do when it can't resolve a ticket? It routes the work based on what the investigation proves: confirmed bugs go to Kai Code with session replay, console logs, reproduction steps, and relevant code context; feature gaps go to Kai PM with customer tier, business impact, and historical demand data; genuinely human-judgment cases become a Gleap Inbox Task with a complete investigation dossier and a recommended next step. When the Task is done, the agent continues the workflow. ### What are Gleap Inbox Tasks? Tasks are a new Inbox item type for human-in-the-loop work. Kai Resolve creates a Task when it needs a human to approve, decide, or perform one specific step. The human completes the Task inside Gleap, and the agent picks the workflow back up with the result instead of dropping the conversation. ### How is Kai Resolve priced? Kai Resolve is included on Pro ($299/mo annual, $359/mo monthly) with unlimited team seats. Investigation usage is billed by actual tokens and the selected model, so deeper investigations cost more than simple routing decisions. Enterprise can use custom SLAs, dedicated infrastructure, and custom AI usage terms. See pricing . Add Kai Resolve before the next escalation. See pricing /pricing 4.6 / 5 G2 · 4,500+ teams --- # Kai Code - Self-Driving Software Development | Gleap Source: https://www.gleap.io/kai-code Description: Kai Code is your top 1% AI software engineer for self-driving software development, turning customer bugs and approved specs into pull requests. Meet Kai Code: Your new top 1% AI software engineer. A customer reports a bug. Kai Code reads the replay, the logs, and your codebase, plans the fix, builds it, and opens the pull request - often before your standup. You review and merge. Start free trial Book demo 4.6/5 on G2 Trusted by 4,500+ teams worldwide Papa Johns FeatureTabsBento Kai Code issue with session replay, logs, and device details. Plan mode Kai Code plan mode showing AI implementation context. Pull request Kai Code opening a pull request from a confirmed issue. Issue to pull request Powering 4,500+ of the fastest-moving software teams Self-driving software development, with customer context built in. Built to do the engineering follow-up that falls between support and sprint planning: reproduce the issue, plan the fix, build the change, open the PR, and keep the customer loop attached. Not just AI coding. An engineer in the loop with the customer report, repo context, and release path. Starts with the real issue, not an empty prompt Kai Code begins with the session replay, console errors, network requests, device state, browser, OS, screen details, and customer impact that usually take engineers the longest to collect. Gleap bug report showing session replay, console logs, network requests, and device fingerprint. Gets confirmed work from Kai Resolve and Kai PM Confirmed bugs arrive from Kai Resolve with reproduction steps, severity, affected area, and investigation notes. Approved specs arrive from Kai PM with demand, priority, and product context already attached. Kai Code triage view clustering duplicate bug reports by affected codebase area. Turns context into a reviewable patch Plan, build, checks, pull request. Kai Code does not disappear after one answer. Every run includes the plan, changed files, additions, deletions, lint notes, and final patch in a built-in diff viewer, so your team can review the work inside Gleap before jumping to GitHub. See Kai Code /kai-code Kai Code changes modal showing the built-in code diff viewer with changed files, additions, and deletions. Works where your team already codes Cloud agent or local coding setup. Run Kai Code in Gleap Cloud with frontier and open-source models, or connect your local Claude Code, Codex, or OpenCode setup. Bugs flow from Kai Resolve. Specs flow from Kai PM. Kai Code plans, builds, opens the PR, and hands the release loop back to the customer-facing agents. A Kai Code task moving from plan mode to build mode before opening a pull request. <1 day Setup and migration Salesforge imported contacts and help center articles in minutes, then moved support, roadmap, news, outreach, and Slack into one Gleap workspace. 10 days To full integration Partfox fully integrated Gleap with custom data and unlocked live chat, AI support, bug reporting, feature requests, product tours, checklists, and surveys. 50-60% Inbound support handled by Kai Commonplace uses Gleap for feedback, support, knowledge base, roadmap work, JIRA, HubSpot, and Kai-powered first-line support. What teams say about Gleap Tridonic logo “One platform, less hassle, and smarter support.” Gleap has transformed how Tridonic manages customer experience by streamlining feedback, support, and automation. Elif Kavas DX, Tridonic MARK.ONE MARK.ONE logo “Essential to our development process.” Gleap was implemented within minutes and helps MARK.ONE fix bugs quickly while building real customer relationships. Mark Breuß Founder, MARK.ONE TNS logo “Super-fast turnaround on feature requests.” Transaction Network Services highlights the Gleap team’s turnaround on new feature requests as part of reducing errors in the product. Martin Hardman Transaction Network Services About Kai Code ### What is Kai Code? Kai Code is Gleap's AI coding agent for self-driving development. It acts like a support-aware AI engineer: confirmed bugs from Kai Resolve and approved specs from Kai PM enter plan mode, move into build mode, run checks, open a pull request, and stay connected to the customer loop after merge. ### What is self-driving software development? Self-driving software development is a customer-to-code workflow where AI agents investigate customer issues, prepare implementation plans, create code changes, open pull requests, and close the loop with the customer after review and merge. In Gleap, Kai handles inbound support, Kai Resolve investigates hard tickets, Kai Code builds confirmed fixes, and Kai PM turns product demand into specs and release notes. ### How does Kai Code enable self-driving software development? Kai Code is the implementation layer in Gleap's self-driving software development loop. It receives confirmed bugs with session replay, console logs, network requests, reproduction steps, source context, and customer impact, then plans the fix, builds the change, runs checks, and opens a pull request for review. ### How is self-driving software development different from an AI coding assistant? AI coding assistants usually start from an engineer's prompt inside an IDE. Self-driving software development starts from a customer signal. Kai Resolve investigates the ticket, Kai Code receives the evidence, opens a pull request, and Gleap can notify the original customer when the fix ships. ### Does self-driving software development replace engineers? No. Kai Code prepares the plan, code change, checks, and pull request, but your engineers still review, approve, and merge the work. The goal is to remove the manual handoff from customer report to PR-ready fix, not to remove code review or engineering judgment. ### Can Kai Code use my existing local coding setup? Yes. Kai Code can run in Gleap Cloud with frontier and open-source models, or work through your local Claude Code, Codex, or OpenCode setup. The workflow stays the same: plan mode, build mode, pull request, review, merge, customer notification. ### How does Kai Code work with Kai PM and Kai Resolve? Kai Resolve routes confirmed bugs to Kai Code with the investigation, replay, logs, source context, and customer impact attached. Kai PM turns feature demand into prioritized specs, then hands approved work to Kai Code for implementation. Kai Code plans, builds, opens the PR, and returns the release loop to the customer-facing agents. ### What codebases does Kai Code work with? Kai Code is designed for connected product codebases where Gleap can provide customer context, replay, logs, and source access. It works across common web, mobile, and backend stacks, then uses the connected repo to plan and build the fix. ### What's the difference between Kai Code and Instabug or Usersnap? Instabug, Usersnap, Marker.io, and BugSnag capture bug reports. Kai Code is built for self-driving development. It receives confirmed bugs with replay, logs, and reproduction context, plans the fix, builds it, opens a pull request, and notifies the users who reported the bug once the fix ships. See the Instabug alternative and Usersnap alternative pages. ### Is Kai Code GDPR-compliant? Yes. Mask sensitive input fields from session replays. Block specific network endpoints from logging. Anonymize user data automatically. SOC 2 Type 2 audited. EU data residency available on Enterprise plans. The fastest teams already ship fixes this way. Join them. See pricing /pricing 4.6 / 5 4,500+ engineering teams --- # Kai PM - AI Product Manager for Feedback and Roadmaps | Gleap Source: https://www.gleap.io/kai-pm Description: Kai PM adds an AI product manager to your team, turning feedback, votes, surveys, and support themes into prioritized specs, roadmaps, and release notes. Kai PM. Your new top 1% AI product manager. Kai PM reads every signal your customers send - votes, surveys, support themes, revenue data - and turns them into a prioritized roadmap, written specs, and release notes. The product work that used to take a week happens continuously. Start free trial Book demo 4.6/5 on G2 Trusted by 4,500+ teams worldwide FeatureTabsBento Feature requests Kai PM prioritizing a feature cluster from the Gleap feature request portal. Start 14-day free trial From feedback to shipped feature Powering 4,500+ of the fastest-moving software teams Meet Kai PM, the agent built for the product work hiding in feedback. Customer feedback in. Prioritized roadmap out. Kai PM clusters demand, scores impact, writes specs, hands approved work to Kai Code, and tells the right customers when their request ships. Turns messy feedback into feature specs Kai PM reads support tickets, feature votes, NPS comments, and survey responses, then synthesizes them into structured specs. Not a vague idea. A spec complete enough for an engineer or Kai Code to act on. Scores priority like a PM with the full customer picture Every roadmap item gets a priority score from vote weight, plan tier, ARR, strategic fit, market urgency, and recency. Kai PM recalculates as new votes, tickets, and customer signals arrive. Reads every channel Direct feature requests, votes, surveys, support themes, in-app messages, and product gaps routed by Kai Resolve. Adds market context Monitors competitor changelogs, app store reviews, and market shifts. Hands approved work to Kai Code Approved specs become Kai Code plan-mode inputs, build-mode runs, and pull requests. Closes the loop After merge, Kai PM writes release notes and notifies the customers who asked for the feature. A roadmap that keeps reading the room No more quarterly shuffle. Vote weight, plan tier, ARR, strategic fit, and recency all feed the score. Kai PM re-scores items as new signals arrive, so your roadmap reflects the customers, segments, and opportunities that matter now. You review, adjust, and override. See pricing /pricing Writes the release notes when the work ships The loop closes automatically. When Kai Code creates a pull request and it gets merged, Kai PM turns the shipped work into customer-facing release notes and notifies every customer who asked for it individually. Not a mass blast. "The feature you requested is now live." See release notes /product/release-notes-news-software “Projects go smoothly.” Minuit Agency uses Gleap to collect and manage feedback and issues, with clients loving the shake gesture for reporting bugs. Théo Hudry CEO, Minuit Agency Every product job on the feedback list From customer request to spec, roadmap, pull request, and customer notification 1. Cluster demand Kai PM reads feature requests, votes, surveys, support themes, and product gaps routed by Kai Resolve. Web research adds market context. Output: a complete spec. /product/public-roadmap-feature-requests 2. Hand approved specs to Kai Code On Pro, approved specs can enter Kai Code plan mode, then build mode. Kai Code opens a pull request for review and merge, with the full spec attached. /kai-code 3. Close the loop After merge, Kai PM publishes release notes and notifies voters and requesters individually. "The feature you requested is now live." Trust compounds. Signals Kai PM turns into product work Every input a product team usually has to reconcile by hand Feature votes Plan tier, ARR, segment. Each vote weighted by the business value behind it. NPS and surveys CSAT, NPS, custom surveys, correlated to feature themes automatically. Support patterns Recurring pain points extracted by Kai Resolve across every channel. Customer tier data Plan, ARR, contract length, health score, all factored into priority scoring. Web research Competitor changelogs, app store reviews, community discussions, market reports. Codebase context Aware of what already exists, so it does not recommend duplicates. $299/mo Kai PM access with token-based product analysis. Everything in Team 25% off on AI tokens All AI models Kai PM included Kai Code and Kai Resolve included Feature request intake Kai PM usage billed by actual tokens + selected model Revenue-weighted prioritisation Auto-generated release notes Public roadmap + voting board Jira / Notion sync Unlimited team seats AI Max Compare to Canny Canny charges per tracked user. Gleap keeps seats flat, with Kai PM usage based on actual tokens and selected model. See comparison /alternatives/alternative-to-canny Comparison of Gleap Kai PM vs Canny per-tracked-user pricing. About Kai PM ### What is Kai PM? Kai PM is Gleap's AI product manager. It reads customer feedback from every channel (support, feature votes, NPS, surveys, in-app), clusters by underlying need, writes structured feature specs with built-in web research and competitive context, prioritises with revenue-weighted scoring, and writes release notes. On Pro, approved specs can hand to Kai Code for plan mode and build mode. ### How does Kai PM support self-driving software development? Kai PM is the product planning layer in self-driving software development . It turns feature requests, survey responses, support themes, and product gaps into prioritized specs. Approved specs can move to Kai Code for plan mode, build mode, and a pull request, then Kai PM writes release notes and notifies the customers who asked. ### How is Kai PM different from Canny? Canny is a feature voting board with manual triage. Kai PM auto-collects feedback from every channel (not just a vote board), clusters semantically, scores by revenue impact (not just vote count), and writes release notes automatically. Pricing: Canny charges per tracked user (~$79/mo and up); Kai PM is available on Gleap Pro at $299/mo with unlimited seats, and usage is billed by actual tokens and selected model. See the Canny alternative . ### How is Kai PM different from Productboard? Productboard is enterprise PM software with manual workflows - collect, prioritise, plan, all manually. Kai PM does the product work autonomously, and Pro can close the implementation loop through Kai Code. Productboard starts at ~$25/maker/mo; Kai PM is available on Gleap Pro at $299/mo with unlimited seats, and usage is billed by actual tokens and selected model. See the Productboard alternative . ### How does revenue-weighted prioritisation work? Every vote is multiplied by the voter's plan tier and ARR. A request from a $50k/yr customer outweighs one from a $0 user. Strategic fit and market urgency add modifiers; recency surfaces trending requests ahead of stale ones. The result is a roadmap that reflects your customers, your business, and your market - not raw vote counts. ### Can I override Kai PM's priorities? Always. Kai PM proposes a prioritised starting point. You review, adjust, and approve. Or set thresholds so Kai PM proceeds autonomously for lower-stakes items while keeping high-stakes decisions in your court. ### How does Kai PM write release notes? After a feature ships, Kai PM drafts customer-facing release notes (benefit-led, not engineering changelog), publishes to your in-app news feed and public changelog, and notifies every customer who voted or mentioned the feature in support. Not a mass blast - a targeted, personalised notification per voter. ### Does Kai PM support Jira or Notion? Yes. Jira and Notion can mirror roadmap status, spec context, and customer demand. On Pro, the actual implementation handoff can go to Kai Code : approved spec, plan mode, build mode, PR, merge, then release notes and customer notifications. Add Kai PM before the next roadmap debate. 4.6 / 5 G2 · 4,500+ teams --- # Build Custom AI Agents with 1,000+ Integrations | Gleap Source: https://www.gleap.io/kai-custom-agents Description: Build no-code AI agents on Gleap's customer data layer with 1,000+ integrations via Composio. Deploy custom agents across support, sales, and engineering. Custom Agents. Build the teammate your team is missing. A no-code builder for AI agents that reason over your customer data and act across 1,000+ integrations. The workflows you've wanted to automate for years - shipped in an afternoon. Start free trial Book demo 4.6/5 on G2 Trusted by 4,500+ teams worldwide Papa Johns FeatureTabsBento Gleap custom agents connected to tools, workflows, and customer context. Start 14-day free trial From workflow idea to live agent Powering 4,500+ of the fastest-moving software teams Build agents for everything else. Kai, Kai Resolve, Kai Code, Kai PM handle the common jobs. Custom Agents builds the rest - on Gleap data + 1,000+ integrations. No code. No-code builder Visual trigger-action editor. Pick a trigger (a ticket arrives, a bug is resolved, a churn signal fires), describe the work, connect the outputs. No engineers required. Visual builder for a Kai Custom Agent - trigger, action, output. Runs on the right data Tickets, bug reports, feature requests, NPS, in-app events, customer tier - your custom agents see what Gleap's built-in agents see. The whole customer story, not just a CRM row. Three data layers Gleap data + your business systems + 1,000+ external integrations. MCP server included Build, test, and run agents from Claude, Cursor, VS Code. Composio under the hood 1,000+ integrations available out of the box. SOC 2 + audit logs Every agent action logged. Approval gates available. Three layers of access Gleap data + your business systems + the whole internet. Gleap data, your business systems (Salesforce, Stripe, Snowflake), and 1,000+ apps via Composio. If your team uses it, an agent can read it, write to it, or trigger it. See integrations /integrations Grid of integration tiles for Slack, Jira, GitHub, Stripe, HubSpot, Salesforce, and more. Bring your own LLM Or pick from the frontier menu. OpenAI GPT, Anthropic Claude, Google Gemini, xAI Grok, and open-source model families like Llama, Mistral, Qwen, and DeepSeek - switchable per agent. Or connect your own model endpoint on Enterprise for full control over cost, latency, and data residency. See MCP server /mcp Per-agent model picker showing GPT, Claude, Gemini, Grok options. “Gleap removed the budget ceiling.” Partfox fully integrated Gleap with custom data in 10 days and now uses live chat, AI support, bug reporting, feature requests, product tours, checklists, and surveys. Maic Fankhauser Product Manager, Partfox Agents teams ship in an afternoon Six real examples. All possible today. The Churn Defender Sentiment drops below threshold over 14 days → agent reads full history, drafts personalized outreach, queues for CSM approval with one click. Risk becomes visible. The Revenue Signal High-ARR support conversation → agent extracts the business need, creates a Salesforce opportunity with the full conversation summary, notifies the account owner in Slack. The Competitor Monitor Scheduled crawl → agent reads competitor changelogs, pricing pages, app store reviews. Posts a Slack brief weekly. Flags roadmap items that may need acceleration. What you can connect Your data, your systems, the whole internet Gleap platform data Tickets, bug reports, feature requests, NPS, in-app events, customer tier - the full Gleap data layer. Salesforce, HubSpot - read records, create opportunities, update deal stages. Billing & revenue Stripe, Paddle - process events, issue refunds, update subscriptions. Dev tools GitHub, GitLab, Bitbucket, and Jira - read commits, create issues, monitor releases. Data warehouses Snowflake, BigQuery - give agents access to your full analytical layer. 1,000+ via Composio Slack, email, WhatsApp, Notion, Google Workspace, Mailchimp, and 1,000+ more. $299/mo Kai Custom Agents included. Everything in Team + Custom agents Gleap data + 1,000+ integrations MCP server access 25% off on AI tokens Kai PM, Kai Code, and Kai Resolve Bring your own LLM (Enterprise) Audit logs + approval gates AI Max Unlimited custom agents. Private cloud. SLA-backed. Talk to sales /contact Enterprise team building custom AI agents on Gleap with private cloud deployment. About Kai Custom Agents ### What is Kai Custom Agents? Kai Custom Agents is Gleap's no-code AI agent builder. It runs on the same platform that powers Kai , Kai Resolve , Kai Code , and Kai PM - with three layers of access: Gleap's customer data, your business systems (Salesforce, Stripe, internal APIs), and 1,000+ external integrations via Composio. ### How is Kai Custom Agents different from Zapier? Zapier is task automation - A triggers B. Kai Custom Agents is AI agents that reason: read context across multiple sources, make a judgement, write personalised output, take an action. Plus they run on Gleap's customer data layer - not just whatever a Zap can scrape. Custom Agents share Gleap's audit logs, approval gates, and SOC 2 posture. ### How many integrations are available? 40+ native Gleap integrations + 1,000+ via Composio. Slack, Jira, GitHub, Salesforce, HubSpot, Stripe, Notion, Google Workspace, Mailchimp, Customer.io, Snowflake, BigQuery, and on. If your team uses it, a custom agent can probably connect to it. ### Do I need to code? No. Visual trigger-action editor. Pick a trigger (a ticket arrives, a bug resolves, a churn signal fires), describe the work in natural language, connect the outputs. For technical users, the MCP server lets you build, test, and run agents from Claude, Cursor, or VS Code. ### Which models power custom agents? OpenAI GPT, Anthropic Claude, Google Gemini, xAI Grok, plus open-source model families like Llama, Mistral, Qwen, and DeepSeek - switchable per agent. Enterprise plans support bringing your own LLM endpoint for cost, latency, and data residency control. ### Are custom agents auditable? Yes. Every action is logged. Sensitive actions can be gated behind approval (via the Tasks feature). Full audit log accessible from your Gleap workspace. SOC 2 Type 2 audited. EU residency available on Enterprise. Build the agent only your team needed. Start building 4.6 / 5 G2 · 4,500+ teams --- # Gleap MCP Server - Connect Claude, ChatGPT, Cursor & VS Code Source: https://www.gleap.io/mcp Description: Connect Claude, ChatGPT, Cursor, and VS Code to the Gleap MCP server with OAuth - work with tickets, contacts, statistics, help center articles, and changelogs. Connect your AI assistant to Gleap. Use the Gleap MCP server to let Claude, ChatGPT, Codex, Cursor, VS Code, and custom assistants work with tickets, contacts, statistics, help center content, and changelogs. Read setup guide See developer API 4.6/5 on G2 Trusted by 4,500+ teams worldwide Papa Johns McpHeroIconBlocks Powering 4,500+ of the fastest-moving software teams Give your AI tool controlled access to Gleap. Add https://mcp.gleap.io/mcp once with Streamable HTTP, authenticate with OAuth, and your assistant can call structured Gleap tools directly. While other teams copy customer data between tabs, yours just asks. What the Gleap MCP server exposes Structured tools for support, content, and reporting Ticket management Search, filter, inspect, and create tickets with search_tickets, find_tickets, get_ticket, and create_ticket. Contact management Find contacts, inspect customer profiles, list matching users, and create new contacts from your AI assistant. Ask for facts, lists, bar-chart data, or raw statistics when you need support performance and feedback trends. Help center collections Browse the collection tree, inspect collections, create new sections, and update existing help center structure. Help center articles Retrieve article details, list articles in a collection, create localized drafts, and update existing content. News and changelogs Read, create, update, and delete news or changelog entries when release communication should start from a prompt. Connect with OAuth first API key headers are for legacy or test setups. Most teams connect through OAuth with their Gleap account. If your client only supports custom HTTP headers, use project for your Gleap Project ID and api-key for your Gleap API Key. Tobi Duelli Gleap team Supported OAuth clients Same server URL across the AI tools your team already uses Claude Desktop and Claude Code Add the Gleap MCP server, approve OAuth, and ask Claude to work with tickets, contacts, docs, and trends. Connect Cursor through its MCP setup flow so customer reports and support context can follow you into code. VS Code Use Gleap from MCP-compatible VS Code workflows when product questions need live customer context. OpenAI clients Connect supported OpenAI client flows to the same Gleap workspace and tool permissions. Google clients Use supported Google client flows when OAuth is available for your MCP setup. Custom MCP clients Building your own client? Contact Gleap to whitelist your redirect domain before using OAuth in production. Server URL and transport One endpoint for MCP-compatible assistants. Use https://mcp.gleap.io/mcp as the server URL and select Streamable HTTP as the transport. Once connected, your assistant can call the available Gleap tools directly from the client. Open setup guide Use the API for product workflows When your backend should call Gleap directly. MCP is for people asking AI assistants to work with Gleap context. The Server API is for product code, imports, reporting jobs, and scheduled workflows that should run the same way every time. Open API docs “Essential to our development process.” Gleap was implemented within minutes and helps MARK.ONE fix bugs quickly while building real customer relationships. Mark Breuß Founder, MARK.ONE Example prompts Plain-language requests, structured Gleap actions. Triage unassigned tickets “Show me all open high-priority tickets that have not been assigned to anyone.” Your assistant can filter tickets and return IDs, titles, and creation dates. Draft help center content “Create a password reset article in English and German.” Your assistant can find the right collection and create a localized draft for review. Compare support performance “What was our average first response time last month compared with the month before?” Your assistant can query statistics and summarize the trend. About the MCP server ### What is the Gleap MCP server? The Gleap MCP server is a Model Context Protocol server that lets AI tools like Claude, ChatGPT, Cursor, and VS Code connect to Gleap through a standardized, controlled interface. Once connected, your assistant can query or create tickets, contacts, statistics, help center content, and changelogs through approved tools instead of relying on copied dashboard context. ### What server URL should I use? Use https://mcp.gleap.io/mcp as the MCP server URL. In clients that ask for a transport, select Streamable HTTP . ### How should I authenticate? OAuth is recommended. It authenticates with your Gleap account and reduces credential exposure. For legacy, test, or terminal-based setups, use custom HTTP headers: project for your Gleap Project ID and api-key for your Gleap API Key. ### Which OAuth clients are supported? The setup guide lists Claude Desktop, Claude Code, Cursor, VS Code, OpenAI clients, and Google clients as supported OAuth clients. If you are building a custom MCP client or using a client outside that list, contact Gleap so your redirect domain can be whitelisted. ### Which tools are available? The current MCP tools cover ticket management, contact management, statistics, help center collections, help center articles, and news or changelog items. ### Can my assistant create tickets, articles, or changelog posts? Yes, when the connected account has permission. The MCP server includes create tools for tickets, contacts, help center collections, help center articles, and news or changelog entries. For content workflows, ask your assistant to create drafts for review before publishing. ### When should I use the Server API instead? Use MCP when a person is asking an AI assistant to work with Gleap context. Use the Server API for backend systems, imports, reporting jobs, scheduled jobs, and integrations that should run deterministically without a chat-based assistant. ### Who uses Gleap? 4,500+ teams run support and feedback on Gleap, including Microsoft, Squarespace, UNICEF, and Papa Johns, with a 4.6/5 rating on G2. The MCP server brings that same workspace context into the AI tools your team already uses. Stop copying tickets into prompts. Bring Gleap context into your AI assistant. Start free trial 4.6 / 5 G2 · 4,500+ teams --- # The Self-Driving Development Era is Now | Gleap Source: https://www.gleap.io/self-driving-development Description: A manifesto from Lukas Böhler, CEO of Gleap, on why software is moving from copilots and autocomplete to Self-Driving Development. Two people having a focused conversation at a table with a laptop. The Self-Driving Development Era is Now You set the destination. Kai ships it. Software teams are entering a new category: Self-Driving Development. /kai s language, using your real product knowledge. When the issue is simple, it is resolved instantly. When it is not, the system does not throw the customer over a wall. Kai Resolve investigates. It reads the conversation, ticket history, connected tools, APIs, source context, and approved data sources. It determines what is actually happening. A billing problem can become a safe action. A product gap can become evidence. A confirmed bug can become implementation work. Kai Code is where the category becomes real. It takes confirmed bugs and approved specs into plan mode, build mode, checks, and pull requests. The customer report does not die as a ticket. It becomes code. Not someday. Not after someone manually reconstructs context. It moves from signal to shipped work. Kai PM turns customer demand into roadmap decisions. It reads feature requests, votes, surveys, support themes, revenue impact, and competitive context. When a feature is approved, the spec moves to Kai Code. When it ships, Kai PM writes the release notes and notifies the customers who asked for it. Kai Custom Agents extend the same idea into the workflows every company has but no SaaS vendor fully understands. The boring glue work, the internal checks, the recurring operational tasks, the handoffs that should have been automated years ago. This is the shift: from AI that helps you operate software to AI that operates software for you. Humans are still in command. But command changes. It is no longer typing every instruction, chasing every ticket, and manually moving work across tools. Command means defining the goal, reviewing the important decisions, setting guardrails, and letting the system carry the loop from customer signal to customer outcome. Self-Driving Development is not a prettier IDE. It is not a chatbot on top of your backlog. It is a system of specialist agents that understand support, investigation, product, code, release, and customer communication as one continuous loop. That loop is the company. The faster it runs, the faster customers trust you. The cleaner it runs, the more your team can focus on the parts of the business only they can do: strategy, taste, relationships, judgment, and invention. The next generation of software companies will not win because they have more tools. They will win because the tools disappear into outcomes. Customers will report less, wait less, repeat less, and wonder less. Teams will spend less time coordinating the work around the work, and more time building the business they actually set out to build. This is what we mean when we say Self-Driving Development. You set the destination. Kai ships it.`} signaturePreset="founder" signatureCaption="Lukas Böhler, CEO of Gleap" />