Agentic AI operating system for manufacturing

Connecting intelligence to physical autonomy.

CADENCE is the second brain of the factory. Specialist AI agents sense what is happening across design, production and supply, negotiate solutions with each other, and bring engineers decisions they can trust. It starts today with first-time-right PPAP approval for automotive suppliers.

  • Finds problems on day one Capability gaps are checked before any production run.
  • Agents that negotiate Design, factory and supply agents resolve trade-offs together.
  • Engineers decide Every recommendation is explained and logged.
The CADENCE second brain A central AI OS connected to business context, objectives, decisions, knowledge, workflow and learning. Its arms reach into ERP, MES, APS and IoT systems, and from there to robots, machines, AMRs, sensors and people. Business context Objectives Decisions Knowledge Workflow Learning CADENCE AI OS ERP MES APS IoT Robots Machines AMRs Sensors People
The brain sets intent The arms sense and act People stay in charge
~10 days
Target PPAP cycle, down from 10–14 weeks today
6
Specialist AI agents working as one team
9
PPAP Level 3 documents generated automatically
4
Feasible configurations for every capability gap

The shift

From finding problems in week six to fixing them on day one.

Engineers set tolerances without knowing whether their machines can hold them. The gap shows up after the production run, when the PPAP fails and weeks of documents have to be redone. CADENCE moves the capability check to the moment the drawing is uploaded.

Traditional model

  1. Design
  2. Release
  3. Production run
  4. Measure
  5. Cpk 1.12 · fail
  6. Rework

Linear. Email-driven. Discovered in week six. 10–14 weeks to approval, with £50K–£200K redesign risk per part.

The CADENCE model

  1. Extract
  2. Check
  3. Negotiate
  4. Decide
  5. Document
  6. Learn

Continuous. Agent-driven. Resolved in minutes. Capability is proven before money is spent on production.

The second brain

Built like an octopus: one brain, many intelligent arms.

An octopus keeps most of its neurons in its arms. Each arm senses and acts on its own while the brain sets the goal. CADENCE works the same way: a central AI OS holds business context and objectives, and specialist agents work inside each system and on the shop floor.

01

The brain

CADENCE AI OS

Holds what the business is trying to achieve and everything it has learned, so every agent works toward the same objective.

  • Business context
  • Objectives
  • Decisions
  • Knowledge
  • Workflow
  • Learning
02

The arms

Specialist agents in every system

Each agent understands one domain deeply, reads its own system and acts locally, then reports back to the brain.

  • CAD & PLM
  • ERP
  • MES
  • APS
  • QMS
  • IoT
03

The body

The physical AI ecosystem

Intent from the brain reaches the machines, robots and people who make the part, and what they measure flows back.

  • Robots
  • Machines
  • AMRs
  • Sensors
  • People
  • SaferRisks flagged before parts are cut.
  • Higher qualityTolerances matched to proven capability.
  • More efficientWeeks of email become minutes of agent work.
  • More flexibleOptions re-evaluated the moment constraints change.

Available now · Agentic PPAP

From drawing to submission-ready PPAP, with agents doing the legwork.

The first CADENCE arm is running as a pilot for Tier 1 automotive suppliers. Upload a drawing and the agents check capability, resolve gaps and assemble the PPAP package, with an engineer approving every decision. These are screens from a real run on a NIST test part.

CADENCE file viewer showing an uploaded engineering drawing with GD&T callouts

The agent team

Six specialists. One shared goal.

Each agent behaves like an expert colleague with one job. When a check fails, the orchestrator starts a re-optimisation cascade and the agents work the problem together until they have options worth a human's time.

Orchestrator

Project manager

Runs the workflow, detects capability gaps, starts the cascade and decides when to hand over to a person.

Design Agent

Design engineer

Reads drawings with vision AI, extracts GD&T and proposes tolerances that still preserve the part's function.

Factory Agent

Manufacturing engineer

Predicts Cpk for each feature on each machine and flags anything below the 1.33 threshold.

Supply Chain Agent

Procurement manager

Checks qualified Tier 2 suppliers, certifications and whether a single-source risk is hiding in the plan.

RaiDOT Agent

Compliance auditor

Validates every option against AIAG PPAP, ISO 2768 and OEM-specific requirements, and flags risk.

Digital Thread Agent

Documentation specialist

Generates PFMEA, Control Plan, Process Flow and PSW aligned line by line, and keeps the audit trail.

Inside a re-optimisation cascade

Illustrative exchange from the brake-bracket demo scenario.

  1. DesignI need ±0.05 mm on hole position for M10 bolt clearance.
  2. FactoryCNC Mill #3 reaches Cpk 1.12 at ±0.05 mm. That is below 1.33.
  3. DesignAt ±0.08 mm the bolt still has 10.84 mm clearance. Function is preserved.
  4. FactoryAt ±0.08 mm, Cpk rises to 1.67.
  5. SupplyFive qualified Tier 2 suppliers can support ±0.08 mm.
  6. RaiDOTISO 2768-m and OEM requirements still satisfied.
  7. OrchestratorConsensus reached. Presenting four options to the design engineer.

Who it is for

One workspace for everyone who signs off a part.

CADENCE gives each role in the PPAP chain its own view of the same project, so design, manufacturing and quality work from one source of truth instead of three spreadsheets.

Tier 1 suppliers

Get parts approved first time.

Built for the teams at automotive suppliers who prepare PPAP submissions for OEMs, and for any manufacturer whose tolerances have to be proven before production.

Design engineer dashboard listing a PPAP project at stage 7 of 9 with learning progress metrics

Design engineers

Set tolerances you can make.

See capability while you design, and choose from options rather than discovering failures.

Manufacturing engineers

Your machine data, put to work.

Validate machine choices and feed production results back so predictions improve.

Quality engineers & managers

Review, don't rewrite.

Aligned documents, a completion checklist and a full audit trail before you sign.

Technical capabilities

Serious engineering under the hood.

CADENCE is a multi-agent system on Google Cloud, built to slot into an existing engineering stack and to grow one integration at a time.

Multi-agent orchestration

Agents built on Google's Agent Development Kit call each other as tools, sharing session state and long-term memory.

Vision GD&T extraction

Reads PDF drawings and extracts datums, feature control frames and dimensions using multi-model vision (Gemini, Claude, GPT), with chat-based correction.

Capability engine

Cpk prediction from a four-level knowledge hierarchy: industry baseline, machine capability, similar features and exact historical matches.

Re-optimisation cascade

Triggers automatically below Cpk 1.33 and returns four ranked configurations: balanced, high reliability, cost-optimised and multi-supplier.

PPAP document generation

Ballooned drawing, DFMEA, PFMEA, Process Flow, Control Plan, customer requirements and PSW, exported to Excel and PDF and bundled as one package.

Explainable AI

Every recommendation can be questioned. Answers come in layers: the rule applied, the reasoning, the evidence and the counterfactual.

Live audit trail

Agent actions, tool calls and human decisions stream to the interface in real time and are stored with who, what, when and why.

Learns from the floor

Engineer overrides and real production results feed back into the knowledge base, so each factory's predictions improve over time.

Secure by design

JWT authentication, role-based access for design, manufacturing and quality, tenant-aware data, and files held in private cloud storage.

  • Google ADK
  • Gemini 2.5
  • Claude
  • GPT
  • FastAPI
  • PostgreSQL
  • Next.js
  • Cloud Run
  • Vertex AI
  • Cloud Storage

The CADENCE evolution

From one process to the whole factory.

CADENCE grows one arm at a time. Each arm proves its value on a real process before the next one connects, so the second brain is built on evidence, not slides.

  1. 01

    Agentic PPAP

    Design-to-manufacturing capability checks, agent negotiation and generated PPAP packages.

    Available now · pilot
  2. 02

    Connected enterprise

    Agents inside ERP, MES and APS bring orders, routings and schedules into every decision.

    Coming next
  3. 03

    Live factory signals

    IoT and CMM data stream real capability, so predictions are checked against the floor continuously.

    Coming next
  4. 04

    Physical AI ecosystem

    Robots, machines and AMRs receive intent from the AI OS and act on it, with people in charge.

    Vision

Responsible AI

AI recommends. Engineers decide.

Safety-critical parts need accountable people. CADENCE shows its reasoning, records every step and never signs anything on your behalf.

Human authority

Engineers choose between options and can override any feature with their own constraint and reason.

Human in the loop

Explained, not asserted

Ask why and get the rule, the reasoning and what would have changed the answer.

Explainable

Traceable end to end

When an auditor asks why a tolerance changed, the answer is one click away.

Audit-ready

Standards aware

The RaiDOT assurance agent checks options against AIAG PPAP, ISO 2768 and OEM requirements.

Assured

Start here

Start with one part.

Bring a drawing and the machines you plan to run it on. We will show you where the capability gaps are and how CADENCE closes them.

  1. 1

    Tell us about your partA drawing and the machines or suppliers you plan to use.

  2. 2

    See CADENCE work on it, liveExtraction, capability checks and the agents negotiating options.

  3. 3

    Decide on a pilotFor manufacturers, one part number. For partners, one integration.

Book a demo

I am interested in

We only use these details to arrange your demo.