Tatvam
tatvam - essence, the underlying principle of a thing
The whole failure-mode workflow in one control room, auditable end to end.
Tatvam is an AI-assisted DFMEA platform built for medical device and regulated product risk analysis. It brings the full failure-mode workflow into one control room: a product hierarchy tree, a working table for scoring risk, AI-generated failure-mode suggestions an engineer accepts or refines, a risk register comparing initial against residual RPN, and end-to-end traceability from requirements through functions and failure modes to tests. A traditionally spreadsheet-heavy compliance process becomes fast, structured, and auditable.
Workflow
Problem
DFMEA lives in spreadsheets, so risk scoring is inconsistent, failure modes are missed, and requirements-to-test traceability has to be reconstructed before every audit.
Outcome
A structured, auditable digital risk workflow from product hierarchy through failure modes, scoring, and verification test coverage.
01
Model the product
The hierarchy of systems, subsystems, and components is captured as the spine of the analysis.
02
Discover failure modes
Candidate modes are suggested from design context; the engineer stays the decision-maker.
03
Score the risk
Severity, Occurrence, and Detection are applied consistently, producing comparable RPN across the programme.
04
Trace to verification
Every requirement resolves to the failure modes it guards and the tests that verify them.
Modules
Product Hierarchy
The system, subsystem, and component tree that risk analysis hangs from.
DFMEA Working Table
Severity, Occurrence, Detection, and RPN scored consistently across the team.
AI Failure-Mode Discovery
Candidate failure modes suggested from design context for an engineer to accept, refine, or reject.
Requirements Traceability
Requirements to functions to failure modes to verification tests, held as one chain.
Representative use cases
Medical Device Design Risk Analysis & ISO 14971 Compliance
A medical device company developing an automated wearable insulin infusion pump and continuous glucose monitoring (CGM) system seeking FDA 510(k) clearance and CE mark certification.
AI Assisted Failure Mode Discovery & Prevention Across Subsystems
A precision surgical robotics manufacturer developing a multi arm laparoscopic robotic surgery console with haptic feedback and stereoscopic visualization.
Thermal and Electrical Hazard Prioritization & Residual Risk Mitigation
An electro medical device manufacturer producing a high frequency electrosurgical generator and radiofrequency tissue ablation workstation.
End to End Requirements to Design Verification Test Traceability
A neurotechnology enterprise developing an implantable neurostimulator and wireless patient controller for chronic pain management.
Engineering Change Order Impact Analysis on DFMEA Risk Baselines
A commercial hemodialysis machine manufacturer managing a field fleet of 25,000 clinic dialysis consoles, implementing an engineering change to replace an obsolete blood flow sensor.
Audit Ready Digital Risk Documentation & Regulatory Submission Readiness
A multinational orthopedic implant and surgical instrumentation manufacturer facing an unannounced EU MDR notified body quality system audit.
Evidence
What Wayam can show for this entry
Curated solution design with an owner and a review date. No performance or production claim.
Allowed claims at this tier: Possible workflow, typical stack, prerequisites.
- Evidence tier
- T4 · Reference pattern
- Integration status
- Typical enterprise system
- Metric status
- Scenario only
- Evidence owner
- Not yet attached
- Validated
- Not yet attached
- Valid until
- —
- Content version
- 2026.09
Pending evidence attachment
This entry represents an enterprise architectural reference pattern. Customer benchmarks, run replays, and metric verifications are established during technical discovery.
Limitations
- Headline metrics are representative until a customer result is attached.
Representative metrics · Reference · scenario only
Initial vs residual
RPN compared in a sortable risk register
Audit-ready
traceability from requirement to test
These describe the intended outcome of the design. They are not measured customer results until a validated case is attached above.
Architecture & controls
Composed across the operating loop
Ingest
Connect the systems of record and read the signals the work already produces.
Covered by the platform
Reason
Ground context, score options against policy and the stated goal, draft the next step.
3 agent roles
Act
Execute an approved step in the system of record and keep the evidence.
5 agent roles
Govern
Set policy, gate consequential actions on a named approver, and audit what ran.
2 agent roles
Pack Architecture & Agent Composition Graph
10 Composed Agents- AGT-0345
Quality Inspection Reporting Agent
Quality
- AGT-0348
Scrap and Rework Analysis Agent
Quality
- AGT-0349
First-Pass Yield Improvement Agent
Quality
- AGT-0324
Risk Register Maintenance Agent
Risk and Compliance
- AGT-0781
Visual Asset Inspection Agent
Vision
- AGT-0428
Maintenance Work Order Optimization Agent
Asset Management
- AGT-0383
Defect Root Cause Analysis Agent
Quality
- AGT-0366
Engineering Change Order Agent
R and D
Control gates
- A named approver on every consequential write-back
- Evidence and audit trail kept with every run
- Policy and compliance checks on retrieved context
Capability atoms
- document-intelligence
- risk-scoring
- generative-design
- evidence-audit-trail
- policy-compliance
- human-approval
Typical enterprise systems
Typical stack for solution design; compatibility is validated during discovery.
- Siemens MES MCP
- SAP S/4HANA
- PI System
- Cognex VisionPro
- ServiceNow GRC
- Workiva
- Snowflake
- NVIDIA Jetson
Designed for
healthcare, manufacturing, automotive
Business case
Model a Tatvam scenario with your own baseline
Three scenarios from the numbers you enter. Capacity released is time; it becomes a saving only when roles or costs are actually removed or avoided.
| Scenario | Improvement | Capacity released | Cashable savings | Net annual | Payback |
|---|---|---|---|---|---|
| Conservative | 9% | — | — | — | — |
| Expected | 18% | — | — | — | — |
| Upside | 24% | — | — | — | — |
Enter an annual volume and a baseline cost to see figures.
Illustrative planning scenario, not a guarantee. Results depend on process baseline, adoption, data quality, integration scope, controls, and deployment costs.
Pilot this
From solution design to a bounded pilot
Step 1 · 3–4 weeks
Discovery Sprint
Validate the workflow, data, controls, baseline and business case before anything is built.
Gate: Blueprint and pilot plan signed by the business owner, technical owner and Wayam.
Step 2 · 6–10 weeks
Bounded Pilot
Prove quality and value on agreed data against agreed acceptance tests.
Gate: Acceptance thresholds met on the evaluation set; go/no-go decision recorded.
Agrani · evidence pending5 Agrani candidates in this solution: Maintenance Work Order Optimization Agent, Defect Root Cause Analysis Agent, Engineering Change Order Agent, Test Plan Generation Agent, Requirements Decomposition AgentPairs well with