# SEAM - Semantic Engine for Agent Mediation

> SEAM is a governance layer for AI agents built by Measurelab. It sits between AI agents and the data sources they query, ensuring every answer is consistent, auditable, and governed — regardless of which system the data lives in.

## The Problem

AI agents can now query live systems directly — CRMs, billing platforms, databases, documents. The friction that made the data warehouse necessary as an access layer has collapsed. When different agents query different systems with different definitions, the same question produces different answers with no audit trail.

## What SEAM Does

SEAM acts as an intelligent proxy between AI agents and data sources. It:

- Resolves natural language questions against governed metric definitions before any query executes
- Maintains a single source of truth for what business terms mean (metrics, entities, business logic)
- Provides complete audit trails for every agent interaction
- Works with structured and unstructured data sources (databases, APIs, documents, Slack, email)
- Requires no data movement or replatforming — governs data wherever it already lives
- Uses version-controlled YAML definitions that are reviewed, tested, and owned like code

## Architecture

SEAM consists of:

- **Definition files (YAML)**: Version-controlled schemas defining tools, metrics, and access policies
- **Compiler/validator**: Validates definitions against schemas before deployment
- **Context resolver**: Maps agent intent to the correct governed definition
- **Agent middleware**: Plugs into existing agent stacks via the Model Context Protocol (MCP) and other interfaces
- **Audit logger**: Full execution trace of every prompt, call, and result

## Key Concepts

- **Metric definitions**: What terms like "revenue", "active customer", and "churn rate" mean in a specific business context, with team-specific variants
- **Source hierarchy**: Rules for which system takes precedence when systems disagree
- **Entity resolution**: How records in one system map to records in another
- **Business logic**: Fiscal year boundaries, attribution models, segmentation rules
- **Temporal context**: Version history of definitions, so the right definition applies to the right time period

## Partner Programme

SEAM is in active development. Organisations can join the partner programme at three levels:

- **Early access**: Hands-on deployment with direct engineering support
- **Co-development**: Joint governance schema development with custom connectors
- **Design partner**: Deep integration with preferential pricing at general availability

## Contact

- Email: hello@measurelab.co.uk
- Website: https://measurelab.ai
- Parent company: https://www.measurelab.co.uk

## Links

- [Home — The Situation](https://measurelab.ai/)
- [Product — Why, What, How](https://measurelab.ai/seam/)
- [Manifesto — Siloed Data, Central Intelligence](https://measurelab.ai/seam/manifesto/)
- [Partner Programme](https://measurelab.ai/seam/#partner)