Skip to Content

Agentic AI & Multi-Agent Systems — Interview Q&A

Agentic AI is the 2026 differentiator. Knowing how to call an LLM is no longer enough; interviewers want to know whether you understand the system around the model when you add planning, tools, memory, and supervision.

Many candidates spend months learning models. Very few spend time understanding everything around the model.


Q1 — What’s the difference between an LLM and an AI Agent?

What? An LLM is a text generator. An AI Agent is a goal-driven system that uses an LLM as its reasoning layer, plans tasks, calls external tools/APIs, has memory, executes workflows, and makes decisions.

Why? Because interviewers test whether you understand the actuators (tools) and sensors (retrieval/memory) around the LLM.

How? The contrast:

CapabilityLLMAI Agent
Generative text✓ (via LLM)
Plans tasks
Calls APIs / tools
Has memory (short / long)
Executes workflows
Multi-step autonomy

3 Scenarios

Scenario 1 — “Recommend a mortgage” (pure LLM use case) Ask GPT about mortgages; it gives generic copy. No checks are run on the user’s bank balance, no mortgage calculator is consulted, no email is sent. That’s an LLM.

Scenario 2 — “Help me apply for a mortgage” (Agent use) The Agent confirms identity, fetches accounts, calculates eligibility, asks the user to upload payslips, runs an LLM-based eligibility explanation, drafts an email, sends it. That’s an Agent.

Scenario 3 — “Reply to this customer complaint, escalate if needed” (Multi-Agent) Agent 1 = Triage; Agent 2 = Compliance; Agent 3 = Response; Supervisor = decides escalation. That’s a Multi-Agent system.


Q2 — What is MCP (Model Context Protocol) and why does it matter?

What? MCP is an open protocol that standardises how AI models communicate with external tools, resources, and services. It defines a JSON-RPC-based contract so any client can connect to any compliant tool without writing custom integration glue.

Why? Because without MCP, every Agent team reinvents tool-calling adapters. With MCP, a tool built once is reusable across Claude, GPT, Gemini, any compliant model.

How? MCP has three layers:

  1. Server: the tool/data source. Provides a list of capabilities it exposes.
  2. Client: the agent. Discovers server capabilities and calls them.
  3. Host: the runtime that connects client + server.

3 Scenarios

Scenario 1 — Tool reuse across vendors Company A builds a CRM_lookup MCP server. Claude Desktop, GPT-5 agent, LangGraph agent, and a custom app can all plug into it without rewriting. Before MCP: each frontend wrote a bespoke Python wrapper.

Scenario 2 — Compliance tooling A bank needs every tool call audited. MCP server logs every request in a tamper-evident ledger; the agent calls the tool, the call gets logged automatically. Before MCP: the agent code had to do its own logging.

Scenario 3 — Resource freshness Doc-stores need reindexing every X minutes. An MCP resources endpoint can advertise “this cache expired, fetch again.” The agent sees the resource and refreshes. Before MCP: every agent manually polled the cache.


Q3 — What kinds of memory do AI agents use?

What? Memory is how an agent personalises, retains, and improves over conversations.

Why? Because stateless LLMs forget everything between requests; memory is what makes an agent feel intelligent.

How? Four types:

  1. Short-term: current conversation only. Cleared after the session.
  2. Semantic: facts & concepts the user has stated (e.g., “user prefers £-denominated bonds”).
  3. Episodic: past events (“last week the user asked about overdrafts”).
  4. Long-term / Persistent: user preferences, identity, history.

3 Scenarios

Scenario 1 — Customer-support agent Short-term: this conversation. Semantic: “user has a £12k savings account.” Episodic: “last year the user opened a credit card; rejected, needs help re-applying.” Long-term: name, address, customer ID. All four types are essential for an FCA-grade banking agent.

Scenario 2 — Trading-assistant agent Episodic memory is critical: “you sold AAPL on Feb 3, lost 8%.” Without episodic the agent cannot reference past actions. Without long-term the agent cannot apply user’s risk profile.

Scenario 3 — Coding agent (general-purpose) Short-term: current session. Semantic: “user prefers Python with FastAPI.” Episodic: 30-day history of past projects. Long-term: account-level preferences (Emoji in comments: yes).


Q4 — How would you test an AI Agent?

What? Agent testing is multi-dimensional: functional, retrieval, security, tool, memory, cost, hallucination, multi-turn, end-to-end, prompt-injection, latency, performance, regression.

Why? Because agents fail in non-obvious ways. They can pass functional tests and still produce garbage in production.

How? Run a test harness that covers:

3 Scenarios

Scenario 1 — Looping bug Agent is asked to fetch last 5 transactions but loops 47 times trying. Test: cap the iteration count; assert tool_calls_count <= 5 per agent run. Result: catches the bug before deploy.

Scenario 2 — Cross-conversation memory bleed Agent A’s “user_name=John” leaks into Agent B’s invocation. Test: isolation spec — run two agents in parallel, assert neither reads the other’s user_name. Result: catches the shared-class-attribute bug.

Scenario 3 — Tool failure propagation Agent calls a credit-check API that returns 500. Agent retries 3 times then hallucinates a fake credit score. Test: mock the API to 500; assert agent returns “I cannot check credit score right now” rather than inventing one. Result: catches the hallucinatory-recovery failure mode.


Q5 — How do you design multi-agent supervision?

What? A pattern where one orchestrating agent decides which sub-agent handles each task. The supervisor routes by intent, by capability, or by load.

Why? Because specialised agents are better than one mega-agent at any non-trivial workload, but you need a coordinator to dispatch.

How? Three patterns:

  1. Supervisor-as-router: a stateless function decides which specialist agent receives the input.
  2. Supervisor-as-planner: a planner agent breaks the task into subtasks; a worker pool executes them.
  3. Peer-to-peer: agents talk directly via shared message bus.

3 Scenarios

Scenario 1 — Customer-support multi-agent Supervisor routes to AccountAgent for balance questions, ProductAgent for sales, GeneralAgent for FAQs. Each agent specialises; supervisor is the dispatcher. The supervisor itself is just a classifier.

Scenario 2 — Research multi-agent Planner agent breaks “research X” into subtasks; each researcher agent returns a sub-report; synthesis agent merges them. Plan → execute → merge.

Scenario 3 — Trading multi-agent Risk agent, Execution agent, Compliance agent, all coordinate. Supervisor: “You can’t execute that trade without risk approval.” Peer-to-peer: Risk signals Execution to stop.

Advertisement