Regulated AI Control Plane

The Control Plane for Regulated AI

One endpoint in front of every model — Claude, OpenAI, Gemini, and open-weight models — with routing, caching, cost control, observability, and governance applied before anything reaches a vendor.

Cut your AI spend as usage grows — and prove every call to your examiner. Built first for US credit unions and mid-size banks.

Priced per completed taskHarness-aware routingGLBA-ready auditAny model, one API
Tessra Control PlaneLive
PII RedactionPolicy EnforcementCache CheckProfile RouterAudit Logger
Allow 60%Route 20%Deny 20%
ModelProviderStatusCostLatency
Claude Sonnetprofile · deep-repoAnthropicallow · cached$0.0000 ms
gpt-4o-mini→ lean-fast profile (cheaper / task)OpenAIroute$0.0018312 ms
Gemini Flashprofile · balancedGoogleallow$0.0003187 ms
Llama 3.3profile · lean-fastSelf-hostedallow$0.000891 ms
gpt-4-turbo (EU region)foreign-hosted — blockedOpenAIdeny
$0.71
Cost / Completed Task
100%
Calls Audited
0
PII Leaked
Cost / completed taskby execution profile
lean-fastbest
$0.71
balanced
$1.14
deep-repo
$1.86
EXHIBIT 1 — Tessra Control Plane — Live Call LedgerIllustrative console view
INTERACTIVE — 60-SECOND TEASER

The gate, in your hands

Pick a real prompt scenario recorded from Tessra's live gateway and watch redaction, policy, and audit fire in sequence.

Select a scenario above to replay a real recorded gateway decision.

EXHIBIT 2 — Tessra Gateway — Recorded Response ReplayRecorded from live demo gateway
How it works

Every model call, one control plane.

Agent traffic enters on the left. Tessra gates, routes, and prices it. What leaves is governed, attributed, and ledgered.

Agent traffic
AgentsSentra · LangGraph · custom
Appsinternal tools · copilots
Pipelinesbatch · RAG · evals
IntegrationsOpenAI-compatible /v1
Tessra Control Plane
Policy Gate
system of enforcement
Cost Ledger
system of record
What surfaces
Cost per task
Routing decisions
Policy verdicts
Audit trail
System layers

Three layers. One decision path.

The ledger captures every call. The policy gate reasons over live spend, surfacing overrun, drift, and routing waste.
Active
02
System of Intelligence
Tessra Policy Gate

Reasons over the full task, scoring what a call should cost and where it should run. Surfaces budget drift, misrouted work, and quality regression as they emerge.

Semantic RoutingBudget Guard
High-Fidelity Cost Signals
Foundation
01
System of Record
Tessra Cost Ledger

The foundation. Captures and prices every call into an integrated, task-anchored history — complete, validated, and attributable to the workflow that spent it.

Task StitchingSpend Lineage
Audit-Grade Artifacts
Gate pipeline

One request. Two passes. Five gates.

Request-side gates govern what the call attempts. Ledger-side gates price the result and write the record.

Request pass · policy & routing
Ledger pass · pricing & record
1
Intent
G1
2
Policy
G2
3
Route
G3
4
Meter
G4
5
Ledger
G5
Platform

Six Planes. One Platform.

TESSRA is an acronym — each letter names a plane of the control plane. Together they cover everything a regulated institution needs before any prompt reaches a model vendor.

T

Telemetry

Full observability across every model call — traces, latency distributions, output quality scores, and cost rolled up by org, team, and user.

E

Enforcement

Policy-as-code governance: model allowlists, data-residency rules, prompt-pattern blocks, and human-in-the-loop approval gates — version-controlled like your code.

S

Security

PII redaction inline, before data ever leaves your perimeter. Names, account numbers, SSNs, and configurable custom patterns are masked or tokenised in every request.

S

Spend

Cache-aware routing and cheaper-model defaults keep costs down as usage grows. Spend attribution by org, team, and user gives finance the visibility they need.

R

Routing

One endpoint, cross-provider failover, warm-cache stickiness. Tessra routes on the execution profile (model and harness together), picking the right one per request by policy, cost, and price per completed task.

A

Audit

Tamper-evident, hash-chained record of every call. Designed to map to GLBA and BSA requirements and support examiner review without data preparation.

Enterprise-Ready

Built for Regulated Industries

Every capability is designed around the real compliance demands of financial institutions — so your AI program is defensible, not just deployable.

Redaction Before Egress

Sensitive data — PII, account numbers, SSNs — is masked before it reaches any model vendor. Data never leaves your perimeter in plain form.

Model Governance

Allow only approved models and endpoints. Block unapproved or foreign-hosted models on sensitive data. Policy rules are auditable and version-controlled.

Tamper-Evident Audit Log

Hash-chained logs designed to map to GLBA and BSA requirements, and to support examiner review without custom data preparation.

Flexible Deployment

SaaS, private VPC, or fully on-premises / air-gapped inside your boundary. All three modes share the same compliance feature set.

Cost Control

Cache-aware routing and cheaper-model defaults reduce spend as usage scales. Attribution by team and user gives finance visibility without extra tooling.

Any Model

Claude, OpenAI, Gemini, and open-weight or self-hosted models — all accessible through one OpenAI-compatible API. No SDK changes required.

Enterprise Access

SSO and role-based access control so the right people see the right data — and auditors can verify who authorized what.

Built For

Regulated Industries First

Tessra is built first for US financial institutions and designed to extend to any industry where model governance and auditability are non-negotiable.

US Credit Unions & Mid-Size Banks

A natural companion to Adalma's Cernio (financial crime) and Cura (compliance management). Tessra gives your AI program the control plane that NCUA and FDIC examiners expect to find.

GLBA-ready auditBSA mappingExaminer-ready export

Healthcare Organizations

The same engine with a HIPAA compliance pack — PHI redaction, access controls, and audit trails designed for covered entities and business associates deploying AI at scale.

PHI redactionHIPAA-mapped auditBAA-ready deployment

Advanced Manufacturing & Defense

Export-controlled data demands the strictest perimeter controls. Tessra's on-premises and air-gapped modes support environments where data cannot leave the facility.

Air-gapped deploymentExport-control awareOn-prem model support
Cost Reduction

Spend Less as You Scale

Cache-aware routing, cheaper-model defaults, and budget attribution let you grow AI usage without a proportional cost increase. Tessra applies these automatically on every request — no manual tuning required.

External reference: Coinbase has publicly reported significant AI-spend cuts using this same routing-and-caching approach — their result, not a Tessra-produced number.

Cache-aware routing
Cheaper-model defaults
Spend by org / team
Budget alerts
The next unit of AI cost

Priced Per Completed Task, Not Per Token

The industry just proved it. The same model run through a leaner harness can cost far less at equal quality, because the harness controls context, retrieval, tools, and the test-and-repair loop. Price per token is the wrong number. Tessra routes on price per completed task, and records every choice in the audit ledger.

Execution Profiles

The real unit of an agent run is model, harness, context strategy, tools, and reasoning tier together. Tessra makes that a first-class, declarable profile in your compliance pack, and routes to it per request.

Cost Per Completed Task

Total spend across a task, including retries and failed attempts, divided by the work it actually finished. A cheaper token can be a more expensive result. Tessra reports the number finance actually cares about.

Examiner-Ready by Design

Every execution-profile decision is hash-chained, so an examiner can see which harness served a request, why it was chosen, and what it cost per finished task. No other gateway logs the profile.

Industry proof point

The harness is the runtime

In a public benchmark on a multi-million-line codebase, the same model run through a leaner harness finished tasks at more than two times lower cost, at comparable quality. And a model that is cheaper per token can cost more per completed task, because it burns more tokens to get there. That delta is execution architecture, not model intelligence.

External reference: Databricks coding-agent benchmark, 2026. Their published result, not a Tessra-produced number.

Model routing
Harness-aware
Eval-driven
Completed work / $
Deployment

Fits Your Security Boundary

Pick the deployment that matches your institution's data-residency and risk posture. All three modes share the same compliance capabilities.

Fastest time to value

Managed SaaS

Single-tenant, US-hosted. Tessra manages infrastructure, updates, and uptime SLA. Suitable for institutions comfortable with third-party SaaS.

  • Single-tenant US instance
  • Tessra-managed uptime SLA
  • Fastest time to value
Your cloud boundary

Private VPC

Deployed inside your AWS, Azure, or GCP environment. Data never leaves your cloud account. You control the perimeter.

  • Inside your cloud account
  • Your VPC, your network controls
  • Data never leaves your boundary
Maximum isolation

On-Premises / Air-Gapped

Fully on-premises or air-gapped. Supports self-hosted open-weight models so nothing leaves your facility — suited for defense and highest-sensitivity environments.

  • Zero external network calls
  • Self-hosted model support
  • Air-gapped compatible
FAQ

Common Questions About Tessra

Tessra — regulated-AI control plane

One endpoint, every model — every call accounted for.

Talk to us about putting Tessra in front of your AI stack — and giving your examiners the audit trail they need from day one.

Talk to our team

Tell us a little about your team and we'll set up a walkthrough.