# LLM assistants that survive real operating constraints.

> Most AI demos die in production. We owned the failure modes, memory, handoff, cost, tenant isolation, and shipped assistants that keep answering when conditions get hard.

Industry and market: AI Systems · Production
Year: 2025
Canonical page: https://www.7unit.tech/work/ai-assistants

## Situation

Buyers were not asking for another chatbot demo. They needed assistants that would hold under real traffic: WhatsApp inquiry volume, multi-tenant cost pressure, and human escalation when the model is uncertain. Most LLM integrations fail the same way, they work in a demo and break in production.

## Stakes

When an assistant fails at message 40, drops context on handoff, or burns budget without attribution, the business does not get a 'model problem', it gets silent leads, angry customers, and an AI line item nobody can explain. Production failure is a revenue and trust failure.

## What 7Unit owned

7Unit owned architecture and delivery of production assistant systems across client contexts, including WhatsApp inquiry agents, designed around session memory, human handoff with conversation context, per-tenant cost attribution, and graceful degradation when the model layer fails.

## What 7Unit did not own

We do not claim a single named public client for this pattern page. The outcomes below describe production constraints we engineered for, not a single public scoreboard. We own the system constraints; the client owns domain policy and human staffing for escalations.

## What we built

LLM-powered assistant systems designed around the constraints that kill most implementations. Applied across WhatsApp inquiry agents, document intelligence pipelines, and coordination agents, same production discipline, different surfaces.

## Risks and how they were reduced

- **Context window exhaustion mid-conversation** — Session-scoped memory with selective compression, intent and key facts preserved without blowing token budgets.
- **Handoff that forces customers to repeat themselves** — Human escalation carries full conversation context, last model reasoning state, and a suggested next action.
- **Unattributable AI cost across tenants** — Every LLM call instrumented with tenant_id and conversation_id, cost anomalies visible before they become a surprise bill.
- **Hard failure when the model API is down** — Graceful degradation: queue/retry for async work, immediate human handoff for live conversations.

## Architecture decisions

### Session memory without token blowout

Naive implementations keep full history in context for every call. We implement session-scoped memory with selective compression.

Rationale: A session that fails at message 40 because the context window is full is not a production system.

Trade-off: Slightly more complex memory architecture in exchange for conversations that do not fail at scale.

### Human handoff with full context transfer

When confidence drops, the system hands off with full context, the human does not start from scratch.

Rationale: A handoff that drops context is a restart, not an escalation.

Trade-off: More complex handoff state management in exchange for seamless human escalation.

### Cost attribution per tenant per conversation

Every LLM call carries tenant_id and conversation_id. Monthly cost reports per tenant are first-class.

Rationale: Without attribution, one high-volume tenant can make the system unprofitable without any single call looking wrong.

Trade-off: Instrumentation overhead in exchange for full cost visibility per tenant.

### Graceful degradation

When the LLM API fails, async work queues and retries; live conversations escalate to humans immediately.

Rationale: An AI system that fails hard when the model API is unavailable is not production-grade.

Trade-off: More complex fallback logic in exchange for operational continuity under failure.

## Outcomes

- **Designed-in — Failure modes.** Memory, handoff, cost, and degradation treated as product requirements, not post-demo patches.
- **Per-tenant — Cost attributed.** Token spend tracked per conversation and tenant, so AI cost is an operated line, not a mystery.
- **Context — Human handoff.** Escalation carries the thread and suggested next action, not a cold restart for the customer.

## Stack

- Claude API
- FastAPI
- PostgreSQL
- WhatsApp Business API
- Redis

## Who this is for

If your AI assistant works in a demo but you cannot explain cost, handoff, or what happens when the model fails, you do not have a production system yet. That is the problem we take ownership of.

Product and engineering leaders shipping customer-facing or multi-tenant LLM assistants who need production constraints designed in from day one.

## Contact

Email: hello@7unit.tech
Book a call: https://www.7unit.tech/contact
Send a project brief: https://www.7unit.tech/rfq