ClearPoint Logic

One spine. One trust fabric. Three ways in.

ClearPoint Logic is built in layers. Nexus helps teams adopt proven skills. Studio turns new ideas into real agents. Meridian governs the workforce record. Under all three, Anchor signs the proof and Agent Core runs the work.

Get early access

How the platform is layered.

The same architecture diagram our engineers walk customers through on day one.

01ProductsNexus, Studio, and Meridian open in waves
  • Soon
    NexusAdopt
    Certified catalog of ClearPoint-built AI skills.
  • Soon
    StudioBuild
    Build engine for production-ready agents.
  • Soon
    MeridianGovern
    System of record for the AI workforce.
02Trust fabricIdentity, policy, and signed evidence
Anchor
Trust fabric
Cert. Standard
Open spec
AI BOM
Per-artifact
Agent Passport
Identity
Signed Evidence
Per-run
03Agent runtimeWhere ClearPoint hosts or mediates execution
Agent Core
Agent runtime
Runtime path
ADK Go
Runtime path
Microsoft Agent Framework
Runtime path
A2A
Runtime path
MCP tools
04Agent estateAgents teams adopt, build, or bring
Agent estate
Governed sources
  • Google Gemini Enterprise
  • Microsoft Agent 365
  • A2A-compatible agents
  • Studio-built agents
  • Custom / BYOA
The agent estate tier shows governed sources.
Layer 02 · Anchor

The trust fabric.

Anchor is the layer everything in the platform is signed against. It ties people, agents, models, prompts, tools, datasets, and runs together into a single signed record that is auditable end to end and exportable to your evidence system.

The standard itself is open through Open Anchor, so anyone can read it, validate against it, and verify a claim independently. Anchor Pro, the trust fabric inside Meridian, is how ClearPoint implements and enforces it.

Public contract

Open Anchor

Published schemas, artifact envelopes, validator behavior, public status fields, and conformance tests. Anyone can validate compatibility without seeing private evidence.

Meridian trust fabric

Anchor Pro

ClearPoint-issued certification, policy enforcement, evidence retention, revocation workflows, and audit operations. Customers get proof and export without the internal control logic.

Open Anchor standard
An open, public spec for what "governed" means at the artifact level, with a CLI validator and conformance suite anyone can run. Every claim points to it.
AI Bill of Materials
A signed manifest per agent: every model, prompt, tool, dataset, dependency, and version.
Agent Passport
A vendor-neutral identity record. The same passport works on Microsoft, Google, custom, BYOA.
Signed Evidence
Every run produces a signed trace: inputs, decisions, approvals, outputs, retained per policy.
Explore the Open Anchor standard
AgentPassportAI BOMModelToolRunOperatorDataset
CoreIdentitySpecificationEvidence
Agent sources
Gemini Enterprise
Agent 365
A2A
Studio-built
Agent Core runtime
Lifecycle
deploy · canary · rollback
Approvals
role · dual · reversible
Audit
signed traces · streaming
Memory layer
Cloud SQL · pgvector · tenant-partitioned
Kill switches
agent · tool · tenant
Anchored to Anchoridentity · evidence
Layer 03 · Agent Core

Where agents run.

Agent Core is the runtime control layer for agents ClearPoint hosts or mediates. It connects Google Gemini Enterprise, Microsoft Agent 365, A2A-compatible agents, and Studio-built packages to the same identity, lifecycle, approvals, evidence, and memory path. ADK Go and Microsoft Agent Framework are supported implementation paths where we are in the execution lane.

  • Cross-estate runtime control
    Connect Google Gemini Enterprise agents, Microsoft Agent 365 agents, A2A-compatible agents, and Studio-built packages to the same lifecycle and telemetry.
  • Lifecycle management
    Versioning, blue/green, canary, rollback. Promotion is a policy decision, not a deploy.
  • Approval routing
    Human-in-the-loop checkpoints with role-based routing, dual control, and reversible actions.
  • Audit pipeline
    Every tool call, prompt, and decision streams as a signed trace, retained per policy.
  • Memory layer
    Cloud SQL with pgvector, tenant-partitioned. Per-agent retention and PII redaction at ingest.
  • Kill switches
    Per-agent, per-tool, and per-tenant pause or revoke, enforced in Agent Core where ClearPoint sits in the path.
Layer 04 · Agent estate

The agents your teams actually run.

This layer is the governed estate: agents adopted from Google Gemini Enterprise and Microsoft Agent 365, A2A-compatible agents, Studio-built packages, and custom agents your teams bring. ClearPoint does not need them all to run on one framework before it can give them identity, policy, evidence, and lifecycle.

When an agent is hosted or mediated by ClearPoint, ADK Go and Microsoft Agent Framework are supported implementation paths. When it lives in a vendor estate, Anchor carries the passport, AI BOM, policy envelope, and signed evidence trail without pretending we own the vendor runtime.

  • Gemini Enterprise
  • Agent 365
  • A2A-ready
  • custom / BYOA
  • Studio-built
agent-estate.json
{
  "estate": "acme-ai-workforce",
  "sources": [
    { "origin": "Google Gemini Enterprise", "status": "governed" },
    { "origin": "Microsoft Agent 365", "status": "governed" },
    { "origin": "A2A-compatible agent", "status": "passport-issued" },
    { "origin": "Studio-built package", "status": "certified" }
  ],
  "passport": "cpl:passport:8f2a91c4",
  "models": ["gemini", "claude", "openai"],
  "ai_bom": "sha256:a4f2...",
  "policy": "envelope://acme/agent-estate",
  "evidence": "envelope://acme/workforce/current",
  "signature": "anchor:sig:rsa256:c7d1..."
}
Build
Sources · registered
Deploy
Anchor · governed
Cross-ecosystem by design

One workforce record. Wherever your agents run.

Agents arrive from three places: your vendors’ clouds, your own builds, and ClearPoint itself. Vendor governance tools only ever see their own ecosystem. Meridian sits above all three and gives every agent one passport, one policy envelope, and one evidence layer, so the workforce record is complete no matter where an agent runs.

  • Vendor-hosted
    Microsoft · Google

    Agents that run inside a vendor’s own cloud and runtime. Meridian governs them through each vendor’s native control surface.

  • Customer-hosted
    Custom / BYOA

    Agents you build and run in your own environment. Bring your own agent; it gets the same passport, policy envelope, and evidence trail.

  • ClearPoint-hosted
    Resident agents

    Agents ClearPoint builds and runs for you, governed under the same single record as everything else.

On the roadmap: AWS · Salesforce · ServiceNow · SAP. Meridian also routes to leading models like Anthropic, OpenAI, and Gemini. Those are governed in the request path, never depicted as standalone estates.

One passport · one policy envelope · one evidence layer

The foundation we build on.

ClearPoint builds on Google Cloud and routes Gemini, Claude, and OpenAI across Meridian, Studio, and Nexus. Model choice follows workload, tenant policy, and evidence needs, not a single primary model. Meridian itself stays neutral: it governs Microsoft, Google, and the custom agents your teams bring or build under one record.

  • Google Cloud
    Cloud · runtime · model

    ClearPoint is GCP-native at the control-plane layer. Gemini is one of the model families routed across Meridian, Studio, and Nexus; ADK Go remains a supported implementation path where ClearPoint hosts or mediates execution.

    • GCP-native control plane
    • Gemini model family
    • ADK Go implementation path
    • Cloud SQL + pgvector memory
  • Anthropic
    Reasoning · agent SDK · policy

    Claude is one of the reasoning model families we use for selected workflows, not the platform-wide default. Anthropic integrations support review-heavy, safety-sensitive, and agent SDK paths where they fit policy and evidence requirements.

    • Claude for selected reasoning
    • Anthropic Agent SDK support
    • Policy-routed model use
    • Shared AI BOM and evidence path
  • OpenAI
    Generation · tools · model

    OpenAI models are part of the same routed model layer across Meridian, Studio, and Nexus. They sit behind the same tenant policy, telemetry, AI BOM, and evidence controls as Gemini and Claude.

    • OpenAI model family
    • Tool-use and generation workflows
    • Tenant policy routing
    • Shared telemetry controls

Want to go deeper?

Register interest for a technical walkthrough of the platform layers and the rollout path that fits your environment.

Get early access