NIRA · Neev Intelligent Resolution Agent

Faster resolutions.
Fewer escalations.
Lower support costs.

Organizations can elevate their support capabilities without expanding headcount. NIRA automates the manual effort of ticket routing and historical research, empowering engineering teams to resolve issues faster. This translates to a significant reduction in required handling hours and a more agile, cost-effective operation.

< 7 sec

p50 classification latency

15–20

tickets per day, per engagement

4

independently swappable architecture tiers

Incident · P3Triage · on creation

Supplier invoice stuck on validation hold after bank account update

Scope gate
In scopeOracle Fusion Application Pack
Classification
Payables · Invoice validationConfidence above threshold
Resolver
Named resolver from the registryA person, never just a group
Resolution hints
Drawn from similar resolved ticketsVector similarity over curated resolutions

Active mode · approval required

Illustrative interface

How NIRA works

Three touchpoints across the ticket lifecycle

NIRA acts at the three moments where intelligence changes the outcome of a ticket: when it arrives, while it is being worked, and when it closes.

01

When the ticket is created

Triage

Smart intake and classification. The ticket is checked against installed Application Packs, classified at module level and routed to a named resolver.

02

Any point during resolution

Refresh

Analyst-triggered re-analysis. As the picture changes, the consultant can ask NIRA to re-evaluate the ticket and its resolution hints on demand.

03

On closure

KB Synthesis

Automated knowledge-article generation. A structured KB article is created from the resolved ticket and embedded, ready to inform the next similar ticket.

Between touchpoints: no ambient monitoring, no interruption.

Business impact

Business impact

  • 7 resources (Incidents/SR)
  • 105 tickets per month
  • Steady-state engagement

+54%

productivity per hour worked (0.84 → 1.29 weighted points/hour)

136.8 hrs

saved per month; 1,641.6 hours annualized

15–20%

modelled savings per year

Operational efficiency

Without0.84
With NIRA1.29

Weighted points per hour worked

First-time resolution (FTR)
~65% → ~85%
Escalation rate
~25% → ~10%
CSAT
4.2 → 4.55

Time

Without303.5
With NIRA197.0

Ticket-handling hours per month

Non-ticket hours/month (documentation + RCA)
14.0 → 7.0
Total hours saved/month
136.8
Annualized hours saved
1,641.6

Platform flow

How a ticket moves through NIRA

Six stages, from the moment a ticket is created in your ITSM tool to the knowledge article it leaves behind.

Stage 1

Ticket created

The ITSM connector normalizes the ticket to a canonical ticket model.

Stage 2

Scope gate

Is the ticket in scope for an installed Application Pack? Out-of-scope tickets pass through untouched.

Stage 3

Classification engine

Embedding, hybrid similarity search and an LLM call under Prompt Containment.

Stage 4

Resolver assignment

Classification plus the resolver registry produces a named person, never just a group.

Stage 5

Widget feedback

The consultant agrees or corrects, and can refresh the analysis on demand.

Stage 6

KB synthesis

On closure, a structured KB article is generated and embedded.

Stateless evaluation

Every event is assessed independently. An append-only ACTION_LOG provides audit, not control flow — so the log records what happened without steering what happens next.

Architecture

A four-tier, platform-agnostic architecture

Intelligence is built once. Application knowledge, ITSM plumbing and engagement settings each sit in their own tier, so any one can change without rebuilding the others.

Tier 1

Core Engine

Platform-agnostic intelligence, built once: classification, embeddings, retrieval and prompt logic.

Tier 2

Application Packs

Domain intelligence for each enterprise application.

  • Oracle Fusion
  • Oracle EBS
  • Salesforce
  • ServiceNow
  • Workday

Tier 3

Infrastructure Adapters

Swappable plumbing to ITSM and integration platforms.

  • Jira
  • ServiceNow
  • Remedy
  • OIC
  • Workato
  • MuleSoft
  • Boomi

Tier 4

Client Configuration

Per-engagement settings: scope mapping, resolver registry and field mappings.

Why it matters

What NIRA does that ITSM-native AI cannot

Capability ITSM-native AI NIRA
Application-specific classification None Deep, module-level (Oracle, EBS, Salesforce)
Resolution knowledge retrieval Basic KB search Vector similarity with curated resolutions
Cross-engagement intelligence None (single tenant) Compounding across the Neev portfolio
Multi-ITSM normalization Own platform only Platform-agnostic canonical model

NIRA’s data-isolation rules apply throughout: every client deployment is fully isolated, and cross-client sharing is not permitted unless separately contracted, fully anonymized and reviewed by both clients.

Security architecture

Three pillars that keep your data, Neev’s IP and the LLM itself under control

NIRA’s security model rests on three pillars: data isolation and zero exfiltration; protection of IP, encryption and credentials; and operational safety controls on the LLM itself.

1. Data isolation

Client data never leaves client infrastructure

All tickets, embeddings, prompts and LLM responses stay inside the client boundary. Inference only — no client data is ever used to train a base LLM.

No cross-client pooling

Every client deployment is fully isolated. Neev’s own core-engine IP is architected to contain zero client data.

External LLM use is the one flagged exception

If an external LLM or embedding endpoint is used, that transit point requires TLS 1.3 and a documented review of the provider’s data policy.

Cross-client sharing requires explicit governance

Not permitted unless separately contracted, fully anonymized and reviewed by both clients.

2. IP, encryption & credentials

Encryption at rest

Pack JSON, prompt templates and keyword dictionaries use native encryption (Oracle TDE / auto-encryption). Application-level encryption (DBMS_CRYPTO) protects AGENT_CONFIG.

Compiled, obfuscated code

The curation pipeline and scoring algorithms ship compiled (Cython/PyInstaller); function and variable names are obfuscated in deployed packages.

Managed-app deployment

Widget platform shells deploy as managed apps (for example, Jira Forge) and are not decompilable by the client.

Vaulted credentials

All credentials live in OCI Vault, AWS Secrets Manager or Azure Key Vault, referenced via the orchestration credential store. Never hardcoded; rotated per client policy.

API authentication

Header-based API key for same-network calls; OAuth 2.0 Client Credentials for cross-network access.

Contractual protection

Non-exclusive, revocable license with a non-reverse-engineering clause. IP obligations survive termination.

3. LLM safety controls

Full audit trail

ACTION_LOG records every action, timestamped. CLASSIFICATION_LOG records who, what, when, why and how — including the CEIL patterns used.

Kill switch

Immediate halt on automated actions if misclassification risk emerges.

Confidence gating

P1/P2 tickets are never auto-assigned without ≥95% confidence.

Governed Autonomy

Automation earns trust. It isn’t assumed.

NIRA moves through three operating modes. Authority widens only as accuracy is proven.

01

Shadow

The agent classifies. Humans execute every action.

Who acts
Your team, on every ticket
Trust established
0% — starting point

02

Active

Recommends and assigns. Human approval required.

Who acts
NIRA proposes, a human approves
Trust established
Proven accuracy

03

Auto

Executes directly, within confidence thresholds.

Who acts
NIRA, inside defined thresholds
Trust established
Full trust

No hidden state

Stateless evaluation throughout: each event is judged independently, so no hidden state can quietly widen the agent’s authority.