IskayPet Connects SharePoint to a Managed Knowledge Base: Validate Permissions Before Answers
Four languages and three countries can share retrieval, but permissions, citations, and cost still need evidence
Key takeaways
AWS published IskayPet’s corporate knowledge assistant case study on October 22, 2026. The system connects Amazon Bedrock Managed Knowledge Bases to existing SharePoint repositories and answers cited questions across retail operations, veterinary care, onboarding, and procurement in four languages and three countries. This article turns the case into a practical acceptance plan for knowledge owners. It checks source scope, inherited permissions, hybrid retrieval, duplicate and fragment removal, citation quality, feedback, and token cost before expansion. It also separates the customer’s reported production results from what another organization should expect. A managed retrieval stack reduces infrastructure work, but it does not remove content ownership, access reviews, evaluation datasets, or human verification of important answers.
By ENHE AI · 2026-10-25 · AI-assisted drafting and editorial checks.
Direct answer: Managed RAG still needs content governance
A managed knowledge base reduces vector-store and ingestion operations, but content owners still define scope, permissions, refresh cadence, citations, and refusal criteria.
Architecture confirmed by the case
The IskayPet assistant answers questions across three countries and four languages while reusing SharePoint. Each assistant targets specific sites or libraries so countries and business domains do not share an uncontrolled retrieval scope.
Six minimal acceptance checks
Prepare ten known-answer questions, five unanswerable questions, and two accounts without access. Check sync scope, hybrid retrieval, duplicate-fragment removal, clickable citations, refusal behavior, and feedback capture. Record injected passages and tokens per answer.
Permission and cost impact
The knowledge base enforces source-system permissions at retrieval time and returns only passages the user could already read. The case retrieves 25 passages and injects up to 15 after cleanup, showing how retrieval depth affects both quality and input-token cost.
Frequently asked questions
Must SharePoint content be migrated?
The case uses a native connector without a large migration, but formats and synchronization still need validation.
Does multilingual support guarantee equal accuracy?
No. Every language needs a separate evaluation set with known answers.
Why this matters
Long-term enterprise knowledge value comes from consistent permissions, verifiable citations, and continuous evaluation, not a single demonstration.
Related tools and reading
These pages support the same task, workflow, or risk boundary.
Conclusion
Start with one document domain, one language pair, and a reviewable question set; expand only after permissions, citations, refusal behavior, and cost all pass.
What this means for everyday users
The knowledge base enforces source-system permissions at retrieval time and returns only passages the user could already read. The case retrieves 25 passages and injects up to 15 after cleanup, showing how retrieval depth affects both quality and input-token cost.
Related tutorials
[[zh]][[/zh]][[en]]Review a public website[[/en]]
SearchScope SEO/GEO
[[zh]][[/zh]][[en]]Access and usage guide[[/en]]
AI Prompt Management System | 418 Bilingual Prompts for Writing, SEO and AI Creation
High-Frequency AI Prompts for Work, Learning, and Teaching guide
High-Frequency AI Prompts for Work, Learning, and Teaching
Related reading
AWS Adds Query-Aware Compression to Reduce Bedrock RAG Context Cost
Review the official scope, availability, ordinary-user task, permissions, cost, review, and rollback checks for AWS Adds Query-Aware Compression to Reduce Bedrock RAG Context Cost.
AWS AgentCore Adds Cross-Account Knowledge Base Connections
AWS AgentCore Adds Cross-Account Knowledge Base Connections. The official source dated August 2026 describes a concrete product, research, or governance change rather than a universal guarantee. This article separates what is available now from preview or planned access, then translates the change into one ordinary-user task: enabling an AI agent to securely retrieve from a knowledge base in another account while verifying least-privilege access. Before using it, readers should verify account eligibility, workspace permissions, data boundaries, model or service cost, human review, audit logs, and rollback. A small reversible pilot with explicit acceptance checks is safer than copying a headline result or assuming that a new integration can publish, merge, or make decisions without approval. The source set is linked so teams can recheck availability and scope when the product changes.
Google Cloud Storage Intelligence brings proactive governance to fast-growing AI data
Google Cloud announced general availability for Storage Intelligence advisor and expanded Cloud Storage batch operations on September 25. Google says AI training and inference pipelines create data quickly and change access patterns often, so problems may surface only after they appear on a bill. The advisor analyzes inventory and access behavior to produce actionable recommendations, while batch operations can apply remediations across large object sets. Teams should not turn every recommendation directly into an automated command. Confirm the affected objects, regions, retention policies, compliance obligations, and estimated cost, test on a limited scope, and retain audit evidence for misclassification, access disruption, and rollback.
When Should an AI Agent Use a Local Small Model or the Cloud? A Hybrid Routing Checklist
AWS published an Adaptive Agentic Intelligence Framework guide using Strands Agents on October 21, 2026. The reference routes routine status checks and local vision work to small models through Ollama, while complex analysis goes to Amazon Bedrock. This durable guide helps teams decide when an AI agent should stay local and when it should use a cloud model. It classifies tasks, marks data that may leave the device, establishes local and cloud quality baselines, defines timeouts and fallbacks, applies one safety policy across both paths, and measures actual routing before estimating cost. The example can run on an 8 GB Raspberry Pi, but that hardware detail is not evidence that every workload belongs on a small local model.
Bayer Shares Production Lessons From 22 Specialist Agents: HTTP Success Is Not Task Success
AWS published Bayer Crop Science’s Agentic Decision Engine case study on October 23, 2026. The production system runs 22 specialist agents over governed analytics workflows, models, logs, and visualization tools. This article turns the architecture into five reusable acceptance checks for enterprise agent teams: persist the state needed to resume work, define identity and authorization at every boundary, scope each agent’s tool catalog, distinguish transport success from task success, and release to a gated group before broader access. It also explains why Bayer’s adoption and resolution figures are evidence about one implementation, not promises for another organization. The focus is operational proof, least privilege, rollback, and observable outcomes rather than prompt polish.
GitHub Copilot Metrics Add OpenCode and Other Clients: Requests Are Not Prompts
GitHub added totals_by_client to the Copilot usage metrics API on October 23, 2026. Enterprise and organization reports can now show model traffic from OpenCode, Claude Code, Codex, Zed, Copilot CLI, GitHub apps, cloud agents, code review, VS Code, JetBrains, and other clients. This article helps administrators build reliable one-day and 28-day reports without confusing model calls with user prompts. It explains request, session, token, model, and selection-mode fields; separates client traffic from agent-app jobs; and adds checks for unknown identifiers, empty arrays, permissions, and coverage. The result is a governance trend report, not an exact invoice or individual productivity score.