Talk to the engineer, not a sales rep +1-501-420-2439
|
m.g.jillani@jillanisoftech.com
AI by business model

Who your customer is changes what the AI has to survive

A copilot for fifty enterprise accounts and a support system for two million consumers use overlapping technology and almost nothing else. Volume, latency budget, tolerance for a wrong answer and who carries the liability all differ, and each one pulls the architecture in a different direction.

4Business models served
8Industry verticals
27+Enterprise clients
22+Production systems
Four Shapes

The same technology, four completely different problems

Who your customer is decides what the AI has to survive. Query volume, tolerance for a wrong answer, latency budget, who carries the liability. These four shapes cover almost every engagement we take.

B2B and enterprise software

Low query volume, high stakes per query. A wrong answer reaches a named account and lands in a QBR. The work is accuracy, permissions and per-tenant isolation, not scale.

What we build: internal and customer-facing copilots, revenue intelligence layers, multi-tenant LLM features inside your existing product, usage metering that makes margin visible per customer.

Multi-tenancyRBACUsage meteringSOC 2 ready

Consumer brands and B2C

Enormous volume, thin margin per interaction, and a public failure mode. Cost per request and latency matter more than benchmark scores, and brand safety is a hard requirement rather than a preference.

What we build: autonomous support across channels, real-time personalisation and recommendations, demand forecasting, content operations, sentiment-based escalation to humans.

Sub-100msCost per requestBrand safetyModel routing

Marketplaces and platforms

Two-sided, with strangers transacting. The AI problems are matching, trust and abuse, and they are adversarial: someone is actively trying to defeat the system, which is a different engineering problem from serving cooperative users.

What we build: matching and ranking, listing quality and enrichment, fraud and trust-and-safety classifiers, dispute triage, seller and buyer support agents, moderation queues with human review.

RankingFraud detectionModerationHuman review

Internal operations

No external customer at all. The measure is hours removed and errors avoided, and the hardest constraint is usually the data: undocumented legacy systems, inconsistent schemas and processes that live in somebody's head.

What we build: knowledge search over institutional documents, document processing, compliance and audit automation, engineering and delivery copilots, agents that move work between systems.

Knowledge searchDocument AIAudit trailsIntegrations
Design Consequences

What changes in the architecture, model by model

This table is the short version of a conversation we have on almost every scoping call.

ModelDominant constraintWhat it forcesProof
B2B and enterpriseA wrong answer reaches a named accountCitation grounding, refusal behaviour, tenant isolation, per-customer audit trailKnowledge search
Consumer and B2CVolume and cost per interactionSmall-model routing, aggressive caching, sub-100ms paths, sentiment escalationSupport platform
MarketplacesAdversarial usersClassical ML classifiers, drift monitoring, human review queues, rapid retrainingML systems
Internal operationsMessy, undocumented dataLonger discovery, layout-aware parsing, integration work, change managementDevOps platform

Marketplaces are where we most often say no to generative AI

Fraud scoring, listing quality and abuse detection are adversarial classification problems on structured features. A gradient boosted model retrains in minutes when attackers adapt, explains its decision to a compliance team and costs a fraction of an LLM call per event. We reach for a language model on the parts that need language, and not on the parts that do not.

Evidence

Every number on this site is traceable to a system

We have a standing rule: no figure appears in a proposal, a deck or on this website unless it came out of a deployed system with a client attached. Each one below carries the engagement it was measured in.

91%

Citation accuracy on legal queries, with zero hallucinated citations after DPO alignment

measured · legal-ai · prod
61%

Support queries resolved without human escalation across seven channels

measured · support-platform · prod
$340K

Qualified pipeline generated in the first six months by the autonomous revenue layer

measured · revenue-platform · prod
84%

Accuracy classifying regulatory compliance gaps across eight jurisdictions

measured · regtech · prod
38%

Reduction in debugging and incident resolution time inside an existing DevOps toolchain

measured · devops-platform · prod
100%

Data residency inside the client VPC on the private deployment, with no external API calls

measured · private-llm · prod

Not sure which of these you are?

Most companies are two of them at once. Bring the workflow and the customer, and we will tell you which constraint dominates and what that means for the build.

Chat on WhatsApp