Reduce escalations to senior engineers
Tier-1 resolves more, engineering gets interrupted less.
Tier-1 escalates anything technical because they cannot find or interpret the relevant docs, and your engineers lose hours a week to interrupt-driven support. Escalations that turn out to be documented behavior are especially demoralizing on both sides.
With Kelu indexing your technical docs, runbooks, and GitHub repos, tier-1 agents ask the internal Ask assistant and get engineer-quality answers with citations. Escalation-worthy gaps show up in knowledge gap analytics, so you can document the top escalation drivers and shrink the queue at the source.
How it works
- 01
Index technical docs, runbooks, and GitHub repos alongside your help center.
- 02
Give tier-1 agents the internal Ask assistant in the dashboard or Slack.
- 03
Agents get engineer-quality, cited answers instead of escalating on uncertainty.
- 04
Knowledge gap analytics surface the topics that still drive escalations, so you document them.
What you get
- Let tier-1 resolve technical questions that used to be automatic escalations.
- Protect engineering focus time from interrupt-driven support.
- Turn escalation patterns into a prioritized documentation backlog.
- Cite runbooks and repos in answers so agents can verify before responding.
Features that make it work
Got questions?
Frequently asked questions
Can the assistant really answer from code repositories?
Yes. GitHub sources index READMEs, docs folders, and other configured paths with code-block-aware normalization, so answers can include and cite technical content from your repos — alongside issues, pull requests and discussions as their own source types.
How do I stop tier-1 from seeing knowledge they should not?
Per-knowledge-base chat permissions control which knowledge bases each member can query, and document-level visibility (public vs. restricted) governs what is retrievable. Restricted docs are available to workspace members through the internal assistant, not the public widget.
How does this reduce escalations over time, not just per ticket?
Gap analytics cluster the questions the AI could not answer, ranked by frequency. Documenting the top clusters removes the root cause of recurring escalations rather than just absorbing them.
How long does setup take?
Most teams are live the same day. You connect a source — a docs URL, GitHub repo, Notion workspace, or a file upload — and Kelu crawls, normalizes, chunks, and embeds the content automatically. The website widget is a single script tag, and the Slack bot installs in a few clicks. There is no model to fine-tune and no infrastructure to run.
Are answers backed by citations?
Yes. Every answer from your docs includes a structured citations list with the URL, title, and excerpt of each source used, and the answer text cites sources inline. Users can click through to verify any claim against the original document — which is what makes the answers trustworthy enough for support, sales, and internal use.
Is my content used to train AI models?
No. Your indexed content, embeddings, and conversations are isolated to your workspace and are only used to answer your own questions. Content is never shared across customers, and data is encrypted at rest and in transit. Enterprise plans add OIDC/SAML SSO, a widget without Kelu branding, and a custom SLA.
Which knowledge sources can I connect?
24 source types: websites, GitHub (docs files, source code, issues, pull requests, discussions), Notion, Confluence, Google Drive, OneDrive, Zendesk (Help Center and solved tickets), Jira, Jira Service Management, Linear, Salesforce Knowledge articles, Salesforce Cases, Discourse, Stack Overflow for Teams, YouTube, OpenAPI specs, S3, curated Q&A, and direct file uploads (PDF, DOCX, XLSX, CSV, Markdown, TXT, HTML). Sources sync on a schedule, and GitHub sources can re-index automatically via webhook on every push.
What happens when the AI is not confident in an answer?
Answers are grounded in your sources. When they do not cover a question, Kelu returns a transparent, configurable fallback — typically pointing users to your support channel — instead of guessing. Those unanswered questions are logged in knowledge gap analytics so you can close the gap in your docs.
Related use cases
Deflect repetitive support tickets
Answer common questions before they become tickets.
Learn moreFix slow first response times
Give customers an accurate answer in seconds, not hours.
Learn moreDeflect tickets at the support form
Answer the question before it becomes a ticket.
Learn moreReady to reduce escalations to senior engineers?
Connect your knowledge sources and see cited AI answers in minutes — free, no credit card required.
Free to start · No credit card required