Technology
Enterprise multimodal AI on AWS
Transparent by design: architects see how inputs route, how agents orchestrate, and where human oversight and compliance controls plug in.
Input processing
- Text: NLU, intent routing, safety classifiers, and structured tool calls.
- Image: Bedrock Claude Vision, optional Amazon Textract for scans, custom rubrics for grading assists.
- Draw: Client-side canvas to PNG; treated as a first-class bitmap for vision—ideal for scratch work without a camera.
- Voice: Sonic speech-to-text, streaming partials, accent-aware adaptation.
- Video: Motion-aware sampling, key-frame extraction, synchronized transcript alignment.
Orchestration & inference
AgentCore coordinates tools, memory, and policy guardrails across specialized agents. Each request is routed to the appropriate inference profile—multi-step reasoning, multimodal analysis, or low-latency lookup—balancing accuracy, latency, and cost under your deployment policies.
Memory & retrieval
Within each platform, embeddings power semantic recall across modalities; retention windows meet your policy. AgentCore Memory keeps session state synchronized inside that product—typing, speaking, or uploading in the same workspace.
Outputs
Multi-format responses combine formatted text, lightweight overlays on student uploads, Polly-class speech, and optional downloadable practice sets.
Data privacy & security
- TLS everywhere; optional customer-managed keys for storage.
- SOC 2 Type II on the roadmap—display badges only when audits complete.
- Media handling: ephemeral processing by default, encrypted at rest when retention enabled.
- Audit logs, configurable retention, and enterprise access controls on dedicated deployments.
Industry-specific compliance details are documented on each live product site—for Education, see Interactive Learning security & trust.
Performance & scale
Global AWS regions, autoscaling inference, and edge caching for static assets. Target SLOs mirror classroom realities—see homepage deep dive for modality latency budgets.
Accessibility engineering
Components ship with logical focus order, ARIA for live regions, captions for synthesized speech, and high-contrast tokens. Pair with your institution’s AT evaluations before production rollout.