Prev Next

AI / Claude Models Basics Interview Questions

What is multi-turn conversation handling in Claude and how do you implement it?

Claude's Messages API is stateless — each API call is independent and Claude has no memory of previous calls unless you include the conversation history explicitly. Multi-turn conversation is implemented by appending each exchange to the messages array.

# Building a multi-turn conversation manually
messages = []

# Turn 1
messages.append({"role": "user", "content": "What is the capital of France?"})
response = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=256,
    messages=messages
)
assistant_reply = response.content[0].text
messages.append({"role": "assistant", "content": assistant_reply})

# Turn 2 — Claude now has context of the previous exchange
messages.append({"role": "user", "content": "What is its population?"})
response2 = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=256,
    messages=messages  # full history included
)
print(response2.content[0].text)
# Claude knows "its" refers to Paris from the previous turn

# Important: as conversation grows, context window fills up
# Common strategies when context limit approaches:
# 1. Summarise older turns and replace them with the summary
# 2. Use prompt caching on stable early context
# 3. Truncate oldest messages (may lose important context)

Key implementation notes:

  • Messages must alternate: user → assistant → user → assistant (etc.)
  • You cannot have two consecutive user or assistant messages
  • The entire conversation history is sent on every request — this grows your token count over time
  • Prompt caching can significantly reduce costs for long conversations with stable early context
Why must you include the full conversation history in every Claude API call for multi-turn conversation?
What is the required message order in a Claude multi-turn conversation?

Invest now in Acorns!!! 🚀 Join Acorns and get your $5 bonus!

Invest now in Acorns!!! 🚀
Join Acorns and get your $5 bonus!

Earn passively and while sleeping

Acorns is a micro-investing app that automatically invests your "spare change" from daily purchases into diversified, expert-built portfolios of ETFs. It is designed for beginners, allowing you to start investing with as little as $5. The service automates saving and investing. Disclosure: I may receive a referral bonus.

Invest now!!! Get Free equity stock (US, UK only)!

Use Robinhood app to invest in stocks. It is safe and secure. Use the Referral link to claim your free stock when you sign up!.

The Robinhood app makes it easy to trade stocks, crypto and more.


Webull! Receive free stock by signing up using the link: Webull signup.

More Related questions...

What is Claude and who makes it? What are the current Claude model families and what is each one optimised for? What are the API model IDs for the current Claude models? What is a context window and what are the context window sizes for current Claude models? What are the pricing tiers for current Claude models and how is pricing calculated? What input and output modalities do current Claude models support? What is extended thinking and how does it differ from adaptive thinking in Claude? What platforms and cloud providers is Claude available on? What is the knowledge cutoff for current Claude models? What is the Claude model lifecycle — what do 'Active', 'Legacy', and 'Deprecated' mean? What is Claude Fable 5 and what makes it different from Claude Opus 4.8? What is Claude Mythos 5 and how does it differ from Claude Fable 5? What is Claude Haiku 4.5 and what are its key characteristics? What is prompt caching and how does it reduce costs when using Claude? What is the Messages Batches API and when should you use it? What is tool use (function calling) in Claude and which models support it? What is computer use in Claude and which models support it? What are the different claude.ai plans and what does each include? What is the effort parameter in Claude and which models support it? What is streaming in Claude API responses and how do you use it? What is the system prompt in Claude and how does it affect model behaviour? What is zero data retention (ZDR) and which Claude models support it? What is Claude's approach to safety and what are Constitutional AI principles? What is the difference between an operator and a user in Claude's design? What is Claude's context window and how are tokens counted? What are Claude's rate limits and how are they structured? What is Claude's approach to harmful content — what will and won't it do? What is Claude's max_tokens parameter and how does it relate to the context window? What is the temperature parameter in Claude and how does it affect responses? What are Claude's multimodal capabilities — how does it process images and documents? What are the claude.ai plans and what models does each tier include access to? What is multi-turn conversation handling in Claude and how do you implement it? What are the different stop_reason values in Claude API responses? What is Claude's approach to honesty and what does it mean for Claude to be non-deceptive? What is Claude Code and how does it differ from using Claude directly via the API? What are the Anthropic SDKs and what languages are officially supported? What is Anthropic's policy on model deprecation and how should developers prepare? What are the key differences between Claude 4 and earlier Claude 3 generation models?
Show more question and Answers...

RenovateBot Interview Questions

Comments & Discussions