A shared assistant spans countries and business functions
Iberian pet-care group IskayPet has built a corporate knowledge assistant on Amazon Bedrock Managed Knowledge Bases. Employees can ask questions covering retail operations, veterinary care, people and onboarding, and procurement across three countries and four languages. The project aims to reduce the time spent searching documents while avoiding a custom retrieval infrastructure.
The source material already lived in SharePoint, so the team used the native connector rather than migrating documents into another authoring system. Advanced indexing prepares content for retrieval, and a foundation model generates answers from selected passages. The application is instructed to cite its sources and say when the retrieved material does not contain an answer.
Managed retrieval keeps SharePoint as the source
Users receive the answer and the underlying documents, then can mark the result with positive or negative feedback. Those signals feed an evaluation set rather than being treated as an automatic truth label. A thumbs-down may reflect stale source content, weak retrieval, ambiguous wording or model behaviour, so investigation should preserve the query, retrieved passages and policy context.
IskayPet used Kiro with Claude Haiku 4.5 on Amazon Bedrock to develop the store-facing interface, design the AWS architecture and provision knowledge bases, data sources, IAM roles and the application layer. The case shows agentic development being used for both code and infrastructure, which increases the importance of review, reproducible deployments and least-privilege role testing.
Feedback and citations support ongoing evaluation
Multilingual retrieval creates evaluation demands beyond translation fluency. Product names, veterinary terminology and local employment or procurement rules may differ by country. Teams need language-specific questions and expected evidence, along with checks that the assistant does not retrieve a policy from the wrong jurisdiction merely because its wording is semantically similar.
Managed knowledge bases reduce operational work, but information governance remains with the organisation. SharePoint permissions, document freshness, connector synchronisation and deletion handling determine what the assistant can expose. The strongest measure of success is not answer volume; it is whether staff reach the correct, current source faster and know when the system lacks enough evidence.
What teams should validate before production
For implementation, teams should record the exact model, software, dataset, connector and policy versions behind every result. Representative evaluation must include normal work, boundary cases, deliberate misuse and component failure, with outcomes separated by user role, data sensitivity and consequence. A strong average should never hide a serious failure in a critical path. Changes should pass the same regression set before promotion, and operators need a documented fallback that preserves evidence rather than silently broadening access or lowering quality.
Procurement and planning should account for the human work required to review exceptions, maintain controls and investigate incidents. Published performance or efficiency claims are useful starting points, but production confidence comes from evidence collected in the organisation’s own environment. A named owner, measurable acceptance threshold, cost model and tested shutdown path turn a promising release into a service that can be governed over time. Where decisions affect safety, rights, money or regulated records, accountable professional review remains essential.
Security and operational evidence
Security review should map every identity, credential, network destination, stored artefact and administrative access path involved in the workflow. Logs need enough context to reconstruct who initiated an action, which evidence was consulted, what the system proposed and what ultimately executed. Sensitive prompts and traces should not be retained merely because they are useful for debugging. Retention, redaction and access must follow the underlying data classification, with a practical process for correcting or removing material when policy or law requires it.
Operational monitoring should measure quality and service behaviour together. Latency, throughput and availability matter, but so do unsupported claims, missed constraints, unsafe tool calls and the rate at which people overturn recommendations. Teams should rehearse dependency outages and partial failures before unattended operation. If a model, connector or external service becomes unavailable, the workflow should fail predictably, preserve its state and tell the user what remains unfinished. Clear degradation is safer than an agent improvising around a missing control.
Transparency should scale with adoption
Organisations should explain the scope and limitations of the deployed capability to the people affected by it. Users need to know when automation is involved, how to challenge an outcome and where a human can intervene. That transparency improves feedback and prevents a pilot result from being interpreted as blanket approval for broader autonomy. Expansion should follow demonstrated evidence, not novelty or pressure to match a competitor announcement. The durable advantage comes from dependable integration, careful measurement and learning that survives the next model or product update.
Finally, teams should schedule a review after real usage rather than treating launch as the end of governance. The review should compare expected benefits with observed quality, cost, incidents and user behaviour, then retire workflows that do not justify their complexity. A service that works well can expand through the same evidence-based process. A service that fails should be narrowed or stopped without losing the records needed to understand why. This feedback loop is what turns experimentation into accountable operational capability.