AI control plane

Control the systems that act for you.

PSIFI Lattice gives engineering and security teams a unified control plane for observing, governing and operating production AI agents, models and tools.

Agent Model Tool Policy Action Audit

agentproductionmodelactivepolicyenforcedtraceliveConceptual view
CUSTOMER AGENTPRODUCTIONFINANCE AGENTPRODUCTIONRESEARCH AGENTSTAGINGPRIMARY MODELROUTEDREASONING MODELROUTEDCRM TOOLREADREFUND APIWRITEKNOWLEDGE INDEXREADAPPROVERFINANCE OPSCRMSYSTEM OF RECORDPAYMENTSFINANCIALWAREHOUSEANALYTICSAUDIT LEDGERAPPEND ONLY

PSIFI Lattice — conceptual map of a governed action path. 13 nodes and 14 connections. Customer agent, a agent in production, connects to Primary model. Finance agent, a agent in production, connects to Primary model and Reasoning model. Research agent, a agent in staging, connects to Reasoning model. Primary model, a model in routed, connects to CRM tool and Refund API, through a allow gate and approval gate. Reasoning model, a model in routed, connects to Knowledge index, through a allow gate. CRM tool, a tool in read, connects to CRM. Refund API, a tool in write, connects to Approver. Knowledge index, a data in read, connects to Warehouse. Approver, a human in finance ops, connects to Payments. CRM, a system in system of record, connects to Audit ledger. Payments, a system in financial, connects to Audit ledger. Warehouse, a system in analytics, connects to Audit ledger. Audit ledger, a policy in append only, terminal node.

  • Agent
  • Model
  • Tool
  • Data
  • Human
  • System
  • Policy gate
Fig. 01Governed action path · hover or focus a node to trace its relationships

02The problem

Your AI stack is becoming a system.

Production AI now spans agents, models, tools, data, APIs, policies and human approvals. Each part is owned by a different team and observed by a different tool.

The problem is no longer model intelligence. Once a system can take an action, the operational questions are about control.

  • 01Who can act?Permissions
  • 02What can they access?Scope
  • 03What happened?Traces
  • 04What was blocked?Policy
  • 05What did it cost?Cost
  • 06Who approved it?Audit
Fragmented AI infrastructure consolidating into one control surfaceONE OPERATIONAL CONTROL SURFACEAGENTS?MODELS?TOOLS?DATA?APIS?POLICIES?HUMANS?

On the left, seven parts of an AI stack — agents, models, tools, data, APIs, policies and humans — sit in separate dashed outlines with unconnected edges and open questions. As the section progresses they move together into a single framed lattice in which every part is connected through policy, labelled one operational control surface.

Fig. 02After — one operational control surfaceConceptual

03The PSIFI thesis

Intelligence can generate the action.
Infrastructure must control the action.

PSIFI Lattice sits between AI systems and the systems they act upon. It does not decide what an agent should do. It decides what an agent is permitted to do, records what it did, and holds the consequential actions for a human.

AI systems
agents · models · tools

PSIFI Lattice · control plane

Select a function to see what it does at this layer.

Enterprise systems
crm · erp · payments · data

FIG. 03 — Every action crosses the control plane before it reaches a system of record.

05The product

See the entire AI system.

One map of every agent, the models it calls, the tools it can use, the data it reads and the policies that stand between them. Switch the overlay to change what the same map tells you.

Lattice / Command CenterPRODUCTIONIllustrative data
Live lattice map
CUSTOMER AGENTPROD · LOW RISKRESEARCH AGENTSTAGING · LOW RISKFINANCE AGENTPROD · MEDIUM RISKGENERAL LARGEPROVIDER AREASONING MIDPROVIDER BCRM TOOLREADKNOWLEDGE INDEXVECTOR STORELEDGER DATABASEREADREFUND APIWRITECRMSYSTEM OF RECORDWAREHOUSEANALYTICSAPPROVERFINANCE OPSPAYMENTSFINANCIAL

Live lattice map — agents, models, tools, data and the systems they act upon. 13 nodes and 14 connections. Customer agent, a agent in prod · low risk, connects to General large. Research agent, a agent in staging · low risk, connects to Reasoning mid. Finance agent, a agent in prod · medium risk, connects to General large and Reasoning mid. General large, a model in provider a, connects to CRM tool and Knowledge index and Refund API, through a allow gate and allow gate and approval gate. Reasoning mid, a model in provider b, connects to Knowledge index and Ledger database, through a allow gate and redact gate. CRM tool, a tool in read, connects to CRM. Knowledge index, a data in vector store, connects to Warehouse. Ledger database, a data in read, connects to Warehouse. Refund API, a tool in write, connects to Approver. CRM, a system in system of record, terminal node. Warehouse, a system in analytics, terminal node. Approver, a human in finance ops, connects to Payments. Payments, a system in financial, terminal node.

  • Agent
  • Model
  • Tool
  • Data
  • Human
  • System
  • Policy gate

OVERLAY · POLICY — gates shown on every governed edge, with the policy that applies

Runtime activity
  • 09:41:07tool.call · payments.refund.create◐ approval
  • 09:41:06model.call · general-large● allow
  • 09:41:04tool.call · crm.customer.read● allow
  • 09:41:02tool.call · erp.invoice.read● allow
  • 09:40:58tool.call · email.send✕ deny
  • 09:40:55vector.query · knowledge_v3● allow
Policy events
  • 09:41:07P-014 · refund above threshold◐ approval
  • 09:40:58P-031 · outbound email to new domain✕ deny
  • 09:40:55P-021 · pii redaction applied● allow
  • 09:40:31P-014 · refund below threshold● allow
Inspector

No node selected

Select any node in the lattice map to see its identity, environment, permissions and recent activity.

Timeline09:38 — 09:41

Amber ticks mark policy events · scrub to reconstruct the map at that moment

Cost · 7 days₹83,300
+12% vs prior 7d

FIG. 04 — Command Center. All entities, activity and figures on this screen are illustrative.

06Signature demonstration

Watch an agent execute.

An autonomous refund request, from the customer message to the sealed audit event. The policy step is the one that matters: the action is held before it reaches the payment system.

Interactive product simulationNo real transaction occurs
10 steps · not started

Arrow keys move between completed steps · Enter or click selects

Event detailnot started

Nothing has executed yet

Run the simulation to watch a governed action travel the lattice: agent, model, tool, policy, approval, action and audit.

07The five control layers

Five layers. One operating surface.

Observe, govern, approve, optimize and audit are not separate products. They are one path that every governed action travels, in that order.

Reconstruct any action after the fact.

Each governed action leaves an append-only record: the actor, the action, the policy version that applied, the approver if there was one, and the result the target system returned.

Append-only ledgerPolicy versionsApprover identityResult
Audit record

who

finance_approver

what

payments.refund.create

when

2026-01-14 09:41:10.402

why

P-014 v4 · amount above threshold

result

rfd_0d93aa · 402 ms

Policy events
  • 09:41:07P-014 · refund above threshold◐ approval
  • 09:40:58P-031 · outbound email to new domain✕ deny
  • 09:40:55P-021 · pii redaction applied● allow
  • 09:40:31P-014 · refund below threshold● allow

08Product ecosystem

One control plane. Connected layers.

Lattice is the control plane. Relay routes model traffic beneath it and Sentinel enforces policy at the agent boundary above it. Relay and Sentinel are on the roadmap and are not available.

FIG. 05 — Sentinel at the agent boundary, Lattice as the control plane, Relay on the model path.

09Agent inventory

Agents are infrastructure. Manage them like it.

An agent has an owner, an environment, a risk classification, a set of tools it may reach, the models it routes to, the policies attached to it and an operating cost. That makes it an asset, not a script.

Lattice / AI InventoryPRODUCTIONIllustrative data
6 of 6 agents
Agent inventory. Select a row to open the full agent record.
AgentStatusOwnerRiskLast executionCost · 30d
Invoice Resolution Agent
agt_invoice_resolution
● PRODUCTIONFinance AutomationMEDIUM2 min ago₹18,240
Customer Resolution Agent
agt_customer_resolution
● PRODUCTIONSupport AutomationHIGH14 s ago₹42,900
Research Agent
agt_market_research
◐ STAGINGKnowledge PlatformLOW6 min ago₹7,120
Release Notes Agent
agt_release_notes
○ DEVELOPMENTDeveloper ExperienceLOW3 h ago₹410
Ticket Triage Agent
agt_ticket_triage
● PRODUCTIONSupport AutomationLOW38 s ago₹11,650
Vendor Onboarding Agent
agt_vendor_onboarding
◐ STAGINGProcurement OpsMEDIUM22 min ago₹2,980

Swipe → for more columns

Agent recordPRODUCTION

Invoice Resolution Agent

agt_invoice_resolution

owner
Finance Automation
environment
production
risk
MEDIUM
last execution
2 min ago
runs · 24h
1,204
cost · 30d
₹18,240

Tool permissions

  • erp.invoice.read● ALLOW
  • billing.api.write◐ APPROVAL

Models

  • general-largerouted

Attached policies

  • Finance Refund PolicyACTIVE
  • PII redactionACTIVE

10Policy engine

Write the boundary once. Enforce it everywhere.

A policy is a condition and an action. Because it is evaluated at the boundary rather than inside the prompt, it applies whatever the model decided to do.

Move the test amount below ₹50,000 to watch the decision change.

Lattice / PoliciesPRODUCTIONIllustrative data
Policies4
Policy P-014 · v4ACTIVEProduction

Prevent autonomous refunds above ₹50,000

When

transaction.type=refund

AND

transaction.amount>50000

Then

require_human_approval

Scope

Finance Agents · Production

Evaluation preview

₹82,400
{
  "transaction": {
    "type": "refund",
    "amount": 82400
  }
}

Decision

◐ approval required

matched P-014 · amount above ₹50,000

Designed
Version history
  • v4threshold raised to ₹50,00011 Jan
  • v3scope narrowed to finance agents04 Jan
  • v2action changed to require_human_approval28 Dec
  • v1created in observe-only mode21 Dec

11Approval center

Keep a human on the decisions that matter.

The held action arrives with the trace, the context and the exact call attached — enough to decide without opening four other systems. Approve or reject below; both write an audit event.

Lattice / ApprovalsPRODUCTIONIllustrative data
Queue · high-value actions3 pending
Pending decision · apr_5512AWAITING HUMAN

Refund request

Customer Resolution Agent

₹82,400

policy
P-014 · high-value financial action
risk
HIGH
waiting
2 min
approver role
finance_approver
sla
30 min · 12 min remaining

Pending action

POST /v1/refunds
{
  "order": "ORD-40218",
  "amount": 82400,
  "currency": "INR",
  "reason": "damaged_on_arrival"
}

Context

Order ORD-40218 · delivered 11 Jan · two prior support contacts · no previous refunds on this account.

Agent reasoning summary

Customer reported damage on arrival with photographic evidence attached to the ticket. Refund matches the order total.
Demonstration data · no transaction occurs
Audit events appended by this queue

No decision recorded in this session yet.

12Cost intelligence

Know what every agent costs to run.

Spend attributed to the agent, the model and the tool that produced it, with event markers for the changes that moved the line. All figures on this screen are illustrative.

Lattice / CostPRODUCTIONIllustrative data
AI spend · 30d: ₹83,300 · Executions · 30d: 412,908 · Cost per execution: ₹0.20 · Forecast · next 30d: ₹96,400
AI spendevent markers show what changed
₹0k₹54k₹108kFORECASTrouting v2P-014 enabledday 1day 35
Show values as a table
Illustrative daily AI spend
DaySpend (₹ thousands)
122
225
324
428
531
630
734
833
938
1041
1139
1244
1348
1446
1552
1650
1755
1858
1954
2061
2159
2264
2368
2466
2571
2674
2772
2878
2981
3084
Execution volume

Executions per day, thousands · illustrative

Cost by agent
Customer Resolution Agent₹42,900
Invoice Resolution Agent₹18,240
Ticket Triage Agent₹11,650
Research Agent₹7,120
Vendor Onboarding Agent₹2,980
Release Notes Agent₹410
Model spend

general-large₹54,300

reasoning-mid₹21,880

embedding-small₹7,120

Small multiples rather than a stacked area, so each model is readable on its own scale.

ForecastDesigned

Next 30 days

₹96,400

Projected from the current 30-day trend and the execution volume of the last seven days. Shown as a dashed continuation on the spend chart.

  • basis30d linear trend
  • confidenceillustrative only
  • driversvolume · model mix

13How it works

From first connection to full control.

Four stages on one path. Telemetry flows in from the boundary, policy is evaluated at the boundary, and operators work from what the boundary recorded.

The four stages of putting Lattice in front of an agentSDKGATEWAYMCPOTLPPOLICYCONNECT01OBSERVE02CONTROL03OPERATE04ENTERPRISE SYSTEMS

A single horizontal path. On the left, four ingest surfaces — SDK, gateway, MCP and OTLP — feed stage one, Connect. The path continues through stage two, Observe, then crosses a policy gate at stage three, Control, and ends at stage four, Operate, before reaching enterprise systems.

Fig. 06One path · four stages · policy evaluated before the action leaves the boundary

14Developer experience

Built for the teams shipping AI.

One call does the work that matters: ask whether this action may proceed, and honour the answer. Everything else — traces, cost attribution, the audit record — follows from it.

  • Python SDKInstrument agents and wrap tool calls.Designed
  • TypeScript SDKNode and edge runtimes, same event model.Designed
  • REST APIAgents, policies, approvals, traces, audit.Designed
  • OpenTelemetrySend existing spans over OTLP.Designed
  • MCP connectivityGovern tools exposed over Model Context Protocol.Designed
  • API keysScoped keys per environment.Designed
  • WebhooksApproval requests and policy events.Designed
fromfromimport psifi import Latticelattice = Lattice(api_key=osos.environ["PSIFI_API_KEY"])# Register the agent once, at startup.agent = lattice.agent(    id="invoice-resolution",    environment="production",    owner="finance-automation",)# Wrap the consequential call. Lattice evaluates policy# before the request reaches the payment system.withwith agent.run(trace="tr_8f21c4") asas run:    decision = run.guard(        tool="payments.refund.create",        payload={"order": order_id, "amount": 82_400},    )    ifif decision.requires_approval:        run.wait_for_approval(decision.approval_id)    ifif decision.allowed:        payments.refunds.create(order=order_id, amount=82_400)
DesignedDesigned integration model · the interface is illustrative and subject to change

FIG. 08 — Guarding a consequential call. The policy decision is returned before the request reaches the payment system.

15Architecture

A control plane, drawn honestly.

Seven layers, from the operator in a browser to the system of record an agent can change. The interesting one is layer six: the boundary where an action is intercepted.

Holds the agent registry, evaluates policy, routes approvals and appends audit records.

In: evaluation and registration requests. Out: decisions, approval requests, audit events.

FIG. 07 — Designed architecture. Select a layer for its responsibility, inputs and outputs.

Reference architecture
Designed
Reference architecture — not a statement of current deployment. Service names are an illustrative mapping, not a partnership or a completed integration.
Reference architecture layers and their illustrative cloud mapping
LayerDesign choiceComponentWhy
FrontendStatic build behind a CDNCDNConsole assets cached at the edge
APIContainer infrastructureContainersHorizontally scaled, stateless request handling
DataPostgreSQLPostgreSQLRegistry, policies, approvals, audit ledger
EventsQueue / streamingQueueTelemetry ingest decoupled from query
TelemetryObject storage + searchObject store + searchSpan payloads with configurable retention
CacheRedisRedisPolicy compilation and hot lookups
SecretsSecrets managementSecrets managerProvider credentials and API keys
AIModel providers / cloud AIModel providersReached through the gateway, never stored
MonitoringOpenTelemetry / cloud monitoringOpenTelemetryThe control plane is itself observable

Swipe → for the full table

16Security

Control is part of the architecture.

Identity decides who the actor is. Policy decides whether the action may happen. The audit record makes both reconstructable. None of that is a setting applied afterwards.

01

Identity

 

02

Policy

‖ evaluate

03

Agent

 

04

Tool

‖ permission

05

Action

 

06

Audit

‖ record

  • 01EncryptionTransport encryption in flight and encryption at rest for stored telemetry and records.Designed
  • 02Tenant isolationWorkspace-scoped data paths, with logical isolation as the default and private deployment as an option.Designed
  • 03RBACRoles for engineers, approvers, auditors and administrators, scoped per environment.Designed
  • 04SSOEnterprise identity through SAML or OIDC, with group-to-role mapping.Designed
  • 05Audit logsAppend-only records for agent actions, policy changes and approval decisions.Designed
  • 06Secrets managementProvider credentials and API keys held in a secrets manager, never in telemetry.Designed
  • 07Data redactionField and pattern redaction applied before payloads are stored or sent to a model.Designed
  • 08Retention controlsPer-workspace retention windows for traces, payloads and audit records.Designed
Request security overview

No certification is claimed on this site. Security documentation is available on request.

17Use cases

Where control matters.

Five operations where an AI action has a consequence. Each row shows the path an action takes and the capability that holds it.

See solutions by team

18Integrations

Connects to the systems you already run.

Categories rather than logos. Nothing here is presented as a completed integration unless it is marked available — and at this stage, none are.

Models

Model providers reached through the gateway.

  • Hosted model providersDesigned
  • Cloud AI servicesDesigned
  • Self-hosted inferenceRoadmap
  • Embedding providersDesigned

Infrastructure

Where the control plane runs.

  • AWSDesigned
  • AzureDesigned
  • GCPDesigned
  • Private deploymentRoadmap

Business systems

Systems an agent can change.

  • CRMDesigned
  • ERPDesigned
  • Support deskDesigned
  • CommunicationRoadmap

Developer systems

Engineering surfaces.

  • Git providersDesigned
  • REST APIsDesigned
  • DatabasesDesigned
  • CI pipelinesRoadmap

AI infrastructure

The agent runtime itself.

  • MCP serversDesigned
  • Vector storesDesigned
  • Inference endpointsDesigned
  • OpenTelemetryDesigned
Full integration ecosystem

Available · connected today · Designed · interface defined · Roadmap · planned, not built

19Pricing

Priced on what you operate.

The meter is the governed action, not the seat. Published prices are not available yet; the drivers and the tier boundaries are.

Pricing available on request.

Pricing tiers and the drivers that differ between them
DriverDeveloperFor experimentation.TeamFor production teams.BusinessFor organisations requiring governance.EnterpriseFor private deployment and advanced controls.
Monitored AI eventsThe primary meter: governed actions and captured spans.Included allowanceScales with volumeScales with volumeCustom
EnvironmentsDevelopment, staging and production separation.13UnlimitedUnlimited
Telemetry retentionHow long traces and payloads are queryable.ShortStandardExtendedCustom
UsersConsole seats, including approvers and auditors.1TeamOrganisationOrganisation
Policy engineConditions, actions and scopes.BasicFullFullFull
Approval workflowsQueues, thresholds and routing.—IncludedIncludedIncluded
SSO and RBACEnterprise identity and role scoping.——IncludedIncluded
Advanced controlsRedaction rules, retention policy, export.——IncludedIncluded
Private deploymentControl plane in your own cloud account.———Included
SupportResponse commitments.CommunityStandardPriorityDedicated
 Request accessTalk to salesTalk to salesTalk to sales

Swipe → to compare tiers

Talk to salesRequest access

20FAQ

Questions engineers ask.

Where a capability is designed rather than built, the answer says so.

Product

Lattice is a control plane for production AI. It sits between your AI agents and the systems they act upon, and it gives engineering and security teams one place to see what agents did, define what they are allowed to do, approve the consequential actions and reconstruct any of it afterwards.

It is infrastructure rather than an application: it does not generate the action, it governs it.

Integration

Control

Data and deployment

Commercial

Put a control layer around your AI systems.

Connect your agents, understand their behaviour, define their boundaries and operate AI systems with a clear audit trail.