Interview prompt
As the FDE (Forward Deployed Engineer), you are asked to build an Enterprise Chatbot Platform that 40,000 employees will use. What is really pushing the project is that 6,400 of those staff already paste company data into consumer AI tools.
Clarify the customer problem
- Should we call a commercial API, host models ourselves, or mix the two by data class?
- Do we launch with plain chat, or with grounding on day one? If grounding, against which systems?
- How long do we keep conversations, and who is allowed to read someone else's history?
- May any employee publish an assistant, or does each one go through review?
- Why can't the company just buy a vendor's enterprise tier?
Users and workflows
| User | Workflow | Current pain | AI assist opportunity | Human approval needed? |
|---|---|---|---|---|
| Employee | ||||
| Security / legal / compliance | ||||
| Department admin | ||||
| Platform operator |
Requirements
Functional
Non-functional
- Latency target
- Availability target
- Cost budget
- Security/privacy constraints
- Audit/compliance requirement
Data and integration map
| Data source | Format | Owner | Freshness | Permission model | Risk |
|---|---|---|---|---|---|
Proposed architecture
Start from a rendered diagram and shape it to fit this case. Cover each part below:
- Session and identity
- Context assembler
- Retrieval ACLs
- Policy and DLP
- Model router
- Audit
Evaluation plan
| Metric | Good threshold | Bad threshold | Test dataset | Owner |
|---|---|---|---|---|
| Consumer-AI egress | Down 80% / 2 quarters | Not falling, or climbing | Baseline from proxy logs | Security |
| Weekly active / eligible | >= 50% | Below 25% | Telemetry from the product | Product |
| Permission violations | 0 | Anything above zero | Contract tests plus audit | Governance |
| Audit completeness | 100% | Below 100% | Turns logged against turns served | Compliance |
Failure modes
- An assistant with too wide a scope hands out access its users lack
- An ACL (access control list) stays cached after access has been revoked
- An uploaded document carries a prompt injection
- The system prompt gets cut short and nobody notices
- A scripted account runs out of control and drains the budget
- The audit pipeline is down, so turns go unlogged
Rollout plan
- Take a baseline of egress from the proxy logs.
- Launch plain chat behind SSO (single sign-on), with audit on.
- Ground answers in one corpus.
- Block progress unless permission violations stay at zero.
- Allow attachments, each one scanned.
- Let people publish assistants after review.
Weak vs strong answer
Weak: "I'd stand up a React frontend, hook it to a vector DB, and route model calls through an LLM (large language model) gateway."
Strong: "I'd fix identity when the session starts and check it again on every turn. Nothing reaches the context window unless policy lets it through and the audit log records it. Retrieval checks the live ACL for each chunk. An assistant can only see what both it and the current viewer may see. Every layer fails closed."
Candidate scorecard
Final 2-minute spoken answer
Rehearse this out loud before you look at it. Summarising the whole design in two minutes is its own skill, and it is usually the last thing you are asked for.