Skip to content
InSearch
How it works
Enterprise search software ChatGPT Enterprise pricing Coveo vs Lucidworks Dust vs GoSearch Dashworks alternatives Glean pricing Glean alternatives Microsoft Copilot alternatives Dropbox Dash pricing Dropbox Dash vs Glean Dust vs Gemini Enterprise Guru pricing Coveo pricing Coveo alternatives Bloomfire alternatives Moveworks alternatives Claude Ask Your Org Claude Enterprise pricing Notion AI pricing Elastic Enterprise Search pricing Perplexity Enterprise pricing Copilot Studio pricing Amazon Kendra pricing Unleash pricing ChatGPT Business pricing Copilot Business pricing Kore.ai pricing Claude Team pricing Dust pricing Grok Business pricing Hebbia pricing Slack AI pricing Gemini Enterprise vs ChatGPT Enterprise ChatGPT Enterprise vs Copilot Amazon Quick Suite pricing Amazon Q pricing Gemini Enterprise pricing Copilot pricing Slack enterprise search Enterprise search use cases Enterprise search tools AI work assistant Knowledge base search AI enterprise search Internal company search engine Internal knowledge search Workplace search Search all company apps AI knowledge assistant Unified search Search Slack & Drive AI assistant for work Knowledge management RAG for enterprise Cited AI answers Confluence search Notion search AI for support agents Sales enablement search Engineering search Enterprise search for remote teams HR knowledge assistant Permission-aware search Secure AI search Onboarding knowledge SharePoint search Intranet search See all →
GoSearch alternatives Dust alternative Guru alternative Amazon Kendra alternative Lucidworks alternative Sinequa alternative Atlassian Rovo alternative Hebbia alternative Onyx alternative Amazon Q Business alternative Gemini Enterprise alternative Google Agentspace alternative ServiceNow Otto alternative Copilot Studio alternative SharePoint agents alternative
Security Pricing Blog Contact Sign in
Procurement manager comparing two printed vendor proposals at a desk

Compare · Amazon Kendra

Amazon Kendra alternative for teams migrating now that Kendra is in maintenance mode

AWS has put Amazon Kendra into Maintenance Mode as of June 30, 2026, and the service stopped accepting new customers on July 30, 2026. Existing indexes keep running, and AWS says it will continue shipping bug fixes and security updates, but there will be no new features. AWS's own guidance is to migrate Kendra applications, and build any new search application, on Amazon Bedrock Managed Knowledge Base.

or see the comparison ↓

One search · cited answers · permission-aware

Answer Console
Your files only
Reading your files…

That request did not get through. Tap Ask InSearch again.

No account needed. Your files are read once to answer, then deleted, and never used to train any model.

That leaves teams with a real fork in the road. Bedrock Managed Knowledge Base is a managed RAG toolkit you build an application on top of: AWS's own migration guide lists 7 native connectors for the managed knowledge base against Kendra's 32, and notes that faceted search, query suggestions, custom synonyms, spell checking, incremental learning and custom document enrichment all need workarounds you implement yourself. If your goal was a search platform to build on, that is a reasonable path. If your goal was employees getting answers, you are being asked to build a product.

Kendra is also not the only AWS search product that closed its doors. Amazon Q Business, the assistant many teams ran on top of Kendra, stopped accepting new customers one day later on July 31, 2026, with AWS pointing those customers to Amazon Quick. If you were running both, you are scoping two migrations with two different destinations, not one.

InSearch is the other fork: a finished workplace search you connect rather than construct. It searches Google Drive, Slack, Notion, Confluence, Gmail, Jira and Salesforce in one query and returns a written answer with inline citations, with item-level permissions enforced at query time and no training on your data. No index capacity to provision, no retrieval pipeline to assemble, no application to write.

Kendra moving to maintenance mode changed the timeline for a lot of teams, as we cover in the Kendra maintenance-mode migration. If you are weighing an AWS-native rebuild, read Bedrock Knowledge Base versus a Kendra rebuild, check Kendra vs OpenSearch cost if you are considering a self-built index, then compare Amazon Q Business. What your current index costs each month, edition by edition, is worked out on Amazon Kendra pricing.

Amazon Kendra is in maintenance mode and closed to new customers from July 30, 2026, with AWS pointing migrations at Bedrock Managed Knowledge Base, a RAG toolkit you build on. InSearch is the finished alternative: connect your apps and get cited, permission-aware answers without building a search application.

Side by side

Amazon Kendra vs InSearch, honestly

A fair look at what each does well. Both are capable tools. Here is where they differ.

What matters InSearch Amazon Kendra
Status in 2026 Actively developed and shipping Maintenance Mode since June 30, 2026; closed to new customers from July 30, 2026; no new features
What you get A finished workplace search product, not a service you build on top of A search service you build an application on top of
AWS migration path Not applicable; connect your apps and search AWS recommends migrating to Amazon Bedrock Managed Knowledge Base
Connectors Drive, Slack, Notion, Confluence, Gmail, Jira and Salesforce out of the box Kendra ships 32 native connectors; the Bedrock managed knowledge base ships 7, so other sources need a custom pipeline into S3
Answers Written answer with inline citations to the source docs Kendra returns ranked passages; generating an answer needs an external LLM you wire up
Pricing model Transparent per seat, so cost tracks the people using it Provisioned index capacity: storage units and query unit hours billed from index creation until deletion, plus connector sync
Engineering effort Connect apps, invite the team Provision the index, build ingestion, retrieval, ranking, permissions and the UI
Best suited for Teams that want employees answering questions, not a search stack to maintain Teams with AWS engineers who want to build custom search inside their own AWS account

Comparison reflects general, publicly understood positioning. Capabilities change, so check each product for the latest.

Why teams pick InSearch

One cited, permission-aware search across every app

A product, not a build

Bedrock Managed Knowledge Base hands you a RAG toolkit and a migration guide. InSearch hands your team a working search box on the apps they already use.

Nothing to re-platform

No index to provision, no chunking strategy to pick, no connectors to rebuild in Lambda. You connect the apps and start asking questions.

Cited and permission-aware

Item-level permissions from each source enforced at query time, and every answer traceable to the exact document it came from.

Good questions

Amazon Kendra vs InSearch, answered

Not discontinued, but it is winding down. AWS put Kendra into Maintenance Mode on June 30, 2026, and it stopped accepting new customers on July 30, 2026. Existing customers keep a fully supported service with bug fixes and security updates, but AWS will not build new features for it and recommends migrating to Amazon Bedrock Managed Knowledge Base.
It depends on what you were using Kendra for. If you were building custom search inside AWS, Bedrock Managed Knowledge Base is the path AWS recommends. If you were using Kendra so employees could find answers across company apps, a finished product like InSearch is a better fit: it connects Drive, Slack, Notion, Confluence, Gmail, Jira and Salesforce and returns cited, permission-aware answers with no application to build.
Migrating to Bedrock Managed Knowledge Base means re-ingesting every data source and rewriting your application against new APIs. AWS documents both, and flags that faceted search, query suggestions, custom synonyms, spell checking, incremental learning and custom document enrichment need workarounds. Moving to InSearch skips that work entirely, because you connect the source apps directly instead of rebuilding an index.
No. Kendra stopped accepting new customers on July 30, 2026, so spinning up a first Kendra index is no longer an option. If you already run Kendra, it keeps working and stays supported with bug fixes and security updates, which gives you room to plan a migration rather than rush one.

More comparisons

See how InSearch compares

vs GoSearch

GoSearch alternatives

Cited, permission-aware answers across every app.

 vs Dust

Dust alternative

Search-first, with cited answers out of the box.

 vs Guru

Guru alternative

Live search across every app, not just a curated wiki.

 vs Lucidworks

Lucidworks alternative

Workplace search without a Kubernetes cluster to run.

 vs Sinequa

Sinequa alternative

Built for the modern SaaS stack, not a two-year rollout.

 vs Atlassian Rovo

Atlassian Rovo alternative

For companies that are not only an Atlassian shop.

 vs Hebbia

Hebbia alternative

Company-wide cited search, not finance-desk document diligence.

 vs Onyx

Onyx alternative

The same cited, permission-aware answers, fully managed and no-ops.

 vs Amazon Q Business

Amazon Q Business alternative

Still open to new customers, and permission-aware by default.

 vs Gemini Enterprise

Gemini Enterprise alternative

Cross-app cited answers without a Google Cloud project to run.

 vs Google Agentspace

Google Agentspace alternative

Agentspace became Gemini Enterprise. Here is what that means for buyers.

 vs ServiceNow Otto

ServiceNow Otto alternative

Otto absorbed Now Assist and Moveworks. Here is the focused option.

 vs Microsoft Copilot Studio

Copilot Studio alternative

Build an agent, or just get the answer.

 vs SharePoint agents

SharePoint agents alternative

Twenty sources is a site bot. Company search is a different job.
See every use case

Find any answer at work with InSearch

One search across all your company apps, a clear cited answer, scoped to exactly what each person can see, and never trained on your data.

See pricing

One search across every app · cited answers · permission-aware · never trains on your data