Skip to content
Smriti AI

Capability overview

Amazon Bedrock-based business platforms

Business platforms on AWS that combine foundation models available through Amazon Bedrock with an organisation's knowledge, tools and workflows.
Discuss a Project
Entry type
Capability overview
Business
Enterprise AI Platforms
Project family
Amazon Bedrock-based business platforms
Evidence
No customer or result claims

Context

The problem this work addresses

Choosing a model is only the start. A business platform needs application logic, access to the right data and tools, guardrails suited to the use case and a way to measure whether it is working.

Typical use cases

  • Knowledge assistants grounded in an organisation's documents
  • Workflow automation with model-assisted steps and human checkpoints
  • Agentic applications that call business tools through defined interfaces
  • Selecting and comparing models for a specific task

Typical applications of this kind of system — not a list of delivered projects.

What Smriti engineers

Our contribution

The parts of the system we design, build and evaluate — beyond the platforms and models we build with.

  • Platform architecture

    The layers between the business interface and the selected models.

  • Workflow and agent logic

    Application rules, tool use and the hand-offs between steps.

  • Model selection and evaluation

    Comparing candidate models against the task, not a generic benchmark.

  • Operations

    Deployment, monitoring and iteration once the platform is in use.

System shape

How a system in this family is typically shaped

Layers run from the people who use the system down to the foundations it runs on. Each tag shows who is responsible for that layer.

Technologies we build with

  • AWS
  • Amazon Bedrock

Supporting AWS services, such as Amazon Bedrock Knowledge Bases, Guardrails or AgentCore, are used only where a project requires them.

  1. Business interface

    Applications and workflows people use

    Smriti engineers

  2. Agent or workflow logic

    Orchestration, rules and tool calls

    Smriti engineers

  3. Selected models

    Foundation models available through Amazon Bedrock

    Amazon Bedrock provides

  4. Approved data and tools

    Knowledge sources and business systems

    Integrated with permission

  5. Evaluation and operations

    Measurement, monitoring and improvement

    Smriti engineers
  • Engineered by Smriti
  • Provided by Amazon Bedrock
  • Customer systems and data, integrated with permission
DrawingTypical system shape
TypeReference architecture
PracticeEnterprise AI Platforms

Related

More in Enterprise AI Platforms

  • Capability overview

    Gemini-powered enterprise agents

    Agents that work with an organisation's own knowledge and software, built on Google Cloud with Gemini models, Gemini Enterprise and the Agent Development Kit.

    Technologies: Google Cloud · Gemini models · Gemini Enterprise · Agent Development Kit (ADK)

  • Capability overview

    Smriti voice models and applications

    Voice-enabled systems that combine Smriti's own voice-model development with speech applications and, where relevant, third-party speech services.

    Technologies: Smriti voice models · Cloud Text-to-Speech · Cloud Speech-to-Text

  • Capability overview

    AI harnesses and evaluation systems

    The engineering around a model that makes it dependable: context handling, orchestration, tool integration, retrieval, workflow rules, evaluation and deployment logic.

    Technologies: Model-agnostic · Google Cloud · AWS

All portfolio entriesExplore Enterprise AI Platforms

Enterprise AI Platforms

Discuss an enterprise AI project.

Tell us about the problem, the people involved and the systems it touches.
Discuss a ProjectExplore Enterprise AI