Skip to content
Smriti AI

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.
Discuss a Project
Entry type
Capability overview
Business
Enterprise AI Platforms
Project family
AI harnesses and evaluation systems
Evidence
No customer or result claims

Context

The problem this work addresses

Most of what makes an AI system useful sits outside the model. The harness decides what the model sees, what it may do and how its work is checked.

Typical use cases

  • Making a model-backed feature reliable enough to ship
  • Adding retrieval, tools and rules to an existing application
  • Building evaluation suites that reflect real tasks
  • Comparing models or configurations before a change

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.

  • Context and retrieval

    What information the model receives, from which approved sources.

  • Orchestration and tools

    Multi-step execution, tool calls and error handling.

  • Workflow rules

    Boundaries, approvals and fallbacks defined by the business.

  • Evaluation

    Task-specific test sets and checks run before every significant change.

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

  • Model-agnostic
  • Google Cloud
  • AWS

  1. Application

    The product surface and its users

    Smriti engineers

  2. Harness

    Context, retrieval, tools, rules and evaluation

    Smriti engineers

  3. Model

    Third-party or Smriti-developed, chosen per task

    Chosen per task
  • Engineered by Smriti
  • Provided by the model provider
  • A third-party or Smriti-developed model, chosen per task
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

    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.

    Technologies: AWS · Amazon Bedrock

  • 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

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