Waboom AI
AI Training

AI Training

AI Team TrainingPopular

Hands-on workshops for marketing, sales, operations, and customer service teams.

AI Strategy Workshop

Executive workshops for leadership teams. Identify opportunities. Calculate ROI. Walk out with a roadmap.

Claude Code Workshop

Build apps in hours not months. Ship websites, automations, and tools with AI.

AI Training for Teams

AI Training for Teams

Hands-on workshops for marketing, sales, operations, and customer service teams. Not theory. Real tools. Real tasks. Real outcomes.

2,000+ people trained across NZ

Learn more
AI Automation

AI Automation

AI Agents & AutomationPopular

Your AI workforce: outbound, proposals, knowledge and support agents. Find buyers, write SOWs, answer every call.

AI Retainer Support

Already built with us? Stay on retainer and we keep shipping new agents and features for your business.

Microsoft Copilot Agents

Build custom Copilot agents in Power Automate & Copilot Studio. Automate workflows across your entire Microsoft 365 ecosystem.

Waboom Concierge

Personalised inbound for premium brands. An AI concierge greets every visitor, builds an on-the-spot quote, and books a real conversation.

AI Automation & Integration

AI Automation & Integration

We build faster and more cost effectively than traditional development teams. You tell us the problem. We deliver the solution.

30+ projects live in 24 months

Learn more
AI Voice Agents

AI Voice Agents

AI Voice Agents

24/7 AI-powered phone agents for inbound & outbound calls. Never miss a lead, handle enquiries, book appointments automatically.

AI Receptionist

Pay-as-you-go inbound receptionist. Answers, transfers calls, takes messages inside your VoIP. $1/min with auto top-up.

Voice Agent Pricing

Transparent pricing for AI voice agents. See costs per minute and platform fees.

AI Voice Agent Demo

Talk to Michelle on three voice AI engines side by side. Hear the latency, find the model that fits.

Listen to Our Voices

Preview all 32 AI voice agents across NZ, AU, UK and US. Find the perfect voice for your brand.

Case Studies

Real customer results. Vendor leads, viewings booked, relationships scaled. Every story has the math.

AI Voice Agents

AI Voice Agents

Never miss a lead. AI agents that answer calls 24/7, qualify prospects, and book appointments automatically.

30+ voice agents deployed

Learn more
Case Studies

Case Studies

Melbourne: 5 listings from one 14-year dormant contactPopular

$2.9M of CBD apartments relisted by the same agent who sold them in 2012. AI dialled the dormant number.

Home builder: AU$374.4M in lost sales uncovered

5,200 cold calls into a 70,000-prospect CRM. 234 confirmed lost deals at AU$1.6M each. A very leaky bucket.

Sydney agent: 141 vendor leads in 90 days

9,856 dials, 1,997 conversations, 141 warm-transferred sellers at $32.74 each.

Christchurch developer: 49 viewings in 14 days

931 Meta leads called same-day. 49 viewings booked at $7.12 each.

City Sales Auckland: 100,000+ relationships

How a leading Auckland firm strengthened over 100,000 client relationships with AI.

See all case studies

Browse every Waboom customer case study in one place.

Real numbers from real Waboom customers

Real numbers from real Waboom customers

Vendor leads. Viewings booked. Relationships scaled. Every story has the math.

5,000+ AI-handled conversations

Learn more
Resources

Resources

AI Resources & Guides

Free templates, frameworks, and implementation guides to help you adopt AI effectively in your organisation.

Blog

Expert insights on AI voice agents, automation strategies, and industry best practices from the Waboom team.

Workshop Tutorial Videos

Paid-attendee video library. Cowork 101 and Claude Code 101, on demand with clickable chapter navigation.

AI Resources Hub

AI Resources Hub

Free tools and guides to help you implement AI effectively. From policy templates to ROI calculators.

New resources added monthly

Learn more
Contact

Contact

Contact Us

Get in touch with our team. We'd love to hear about your AI goals.

About Waboom AI

Learn about our mission, team, and why we're passionate about AI adoption in NZ.

Let's Talk AI

Let's Talk AI

Whether you need training, automation, or strategy - we're here to help you adopt AI effectively.

Response within 24 hours

Learn more
09 885 9695 (NZ)+61 485 027 479 (AU)
Back to BlogExplainers

Extended Thinking vs Web Search vs Research: which Claude mode to hit and when

Leonardo Garcia-Curtis13/05/2026
TL;DR

Claude has three modes you can toggle that change how it works on a problem. Extended Thinking lets Claude spend longer on a single hard reasoning task before responding. Web Search lets Claude pull live information from the internet to ground its answer. Research is a multi-step mode where Claude searches, reads, cross-references, and synthesises a long answer from many sources. The rule of thumb: thinking is for deliberation, search is for facts, research is for reports. Most people only ever hit Send and miss the leverage. The button you pick changes the answer.

Extended Thinking vs Web Search vs Research: which Claude mode to hit and when

7 min read  ·  Modes explainer  ·  Last updated 14 May 2026

Part of Learn Claude Code: The Complete Operator's Guide. For the operator's overview of Skills, Connectors, Cowork, and Artifacts, start there.

Open Claude. There are three buttons you probably walk past every day.

They are Extended Thinking, Web Search, and Research.

Three different jobs. The wrong button gets you the wrong answer. The right one cuts a 30-minute task to 30 seconds.

This post is the plain-English guide to when to hit each.

The 10-second rule of thumb

  • Extended Thinking = deliberation. Hard reasoning. Logic puzzles. Multi-constraint problems. Coding architecture decisions.
  • Web Search = live facts. Pricing, news, current events, anything that changed since Claude's training cutoff.
  • Research = a report. Multi-source synthesis on a topic. Reading lots of pages and giving you back the distilled version.
  • Thinking is for deliberation, search is for facts, research is for reports. That is the whole map you need.

    The Web search toggle in Claude settings, controlling whether Claude can search the internet

    Extended Thinking: when Claude should slow down

    By default Claude responds quickly. Extended Thinking tells it: spend more time on this before answering.

    You toggle Extended Thinking when the problem has three or more hard constraints, multiple steps, or more than one plausible answer. You want the considered version, not the fast one.

    Three good Extended Thinking prompts

    • "Design the data model for a CRM that handles companies, contacts, deals, and a many-to-many relationship between contacts and deals. Consider scale to 1M records and reporting performance."
    • "Here is our pricing structure. Find the holes that would let a customer game us. Explain the worst three and how to close them."
    • "We need to choose between Postgres and DynamoDB for this workload (describe workload). Walk me through the decision step by step, including the failure mode of each."
    • For chat prompts and quick answers, do not bother. Extended Thinking is for the deep ones.

      Web Search: when Claude needs the internet

      Claude was trained on data with a cutoff. Anything after the cutoff is invisible to it unless you toggle on Web Search.

      You toggle Web Search when the answer depends on what happened recently, like today's stock price, this week's news, or the current pricing of a competitor.

      Three good Web Search prompts

      • "What is HubSpot's current Starter plan pricing as of this week? Cite the source."
      • "What was Anthropic's most recent product launch? Summarise in three bullets."
      • "Find me the three most-cited articles about voice AI written in the last 30 days."
      • Ask Claude something current without Web Search on, and it will either guess from training data or tell you it does not know. Toggle it on. Source citations come back automatically.

        Research: when you want a report, not an answer

        Research is the longest-running mode. Claude searches, opens multiple sources, reads each, cross-references, and produces a structured synthesis. It is the closest thing in Claude to a junior analyst writing a brief.

        You toggle Research when you want a 1-2 page document with multiple sources cited, not a one-paragraph chat reply.

        Three good Research prompts

        • "Research the current state of AI voice agents for property management. Cover the top 5 vendors, their pricing models, their typical use cases, and where the market is headed. 1-2 pages."
        • "Build me a competitive landscape brief for accounting practice software in New Zealand. Include Xero, MYOB, and any new entrants in 2025. Note pricing, target market, and any recent funding."
        • "What is the latest research on time-to-first-token latency for production voice agents? Summarise the three most useful sources and what they actually measured."
        • Research is slow, with five to ten minutes being normal, but you get back a structured document with citations. Treat it like a draft from a junior, not a finished product.

          A comparison table

          Mode When Output shape Time
          Extended ThinkingMulti-constraint problems, design decisionsA considered reasoning answer30-90 seconds
          Web SearchYou need live informationAn answer grounded in cited current sources10-30 seconds
          ResearchYou want a report from multiple sourcesA structured 1-2 page document with citations5-10 minutes

          A common mistake: combining them when you should not

          People sometimes toggle on all three at once thinking they get the best of all worlds.

          You do not. You get a slower answer that lands no better.

          Pick the one that fits the job. Need facts AND deliberation? Do Web Search first to pull the facts. Then a follow-up message with Extended Thinking to chew on what you found.

          Pairing modes with skills

          We run you through these three modes side-by-side at our Claude Code workshop. Most operators only ever hit one of these three buttons before training; afterwards, picking the right one becomes automatic.

          The step that compounds: a skill that knows when to recommend which mode.

          We have a skill called research-brief that always runs in Research mode and outputs in our brief format. When we ask for "a competitor brief on X", the skill triggers, switches modes, and runs.

          That is the operating-stack idea again. Skills 101 covers the foundation.

          What to do next

          Tomorrow morning, the first prompt you write: pause for two seconds. Pick the right mode for the job. Hit it.

          Do that for a week. You will notice the difference in your answers.

          Anthropic's official comparison guide for these modes is at support.claude.com.

          Frequently asked questions

          What is the difference between Extended Thinking, Web Search, and Research in Claude?

          Thinking is for deliberation, search is for facts, research is for reports. That is the whole map.

          Extended Thinking tells Claude to slow down on a hard problem. Web Search pulls live information from the internet. Research opens five or more sources and hands back a structured document.

          When should I use Extended Thinking?

          Turn it on when the problem has three or more hard constraints, four or five steps, or more than one plausible answer. Data model design, pricing-hole analysis, and architecture decisions all qualify.

          For quick answers and everyday chat prompts, leave it off. You will just wait longer for the same reply.

          Should I turn on all three modes at once?

          No. People do this expecting the best of all worlds and get a slower answer that lands no better.

          If you need facts and deliberation, split it. Run Web Search first to pull the facts. Then send a follow-up with Extended Thinking to chew on what came back.

          How long does each Claude mode take?

          Web Search returns in roughly 10 to 30 seconds. Extended Thinking takes 30 to 90 seconds. Research runs 5 to 10 minutes.

          Research is slow because it is opening and cross-referencing multiple sources. Treat the output like a draft from a junior analyst, not a finished document.

          Does Claude cite its sources when Web Search is on?

          Yes, citations come back automatically. Ask Claude something current with search switched off and it will either guess from training data or tell you it does not know.

          Self-paced

          Six short modules on Claude Skills. Build a skill that picks the right mode automatically for the work you do.

          Start Claude Skills 101 →

          Hands-on with us

          Live workshop walks through real prompts on each mode. You leave with a feel for when to hit which button.

          See the workshop →

          We run hands-on AI training for teams across NZ and Australia.

          LG

          Leonardo Garcia-Curtis

          Founder & CEO at Waboom AI. Building voice AI agents that convert.

          Want your team to actually use these tools?

          Waboom AI runs hands-on AI training and Claude workshops for teams across New Zealand and Australia.

          Explore AI Team Training

          Related Pages

          AI Team Training

          Hands-on AI training for NZ and Australian teams.

          Claude Team Training

          Get your whole team productive with Claude.

          Related Articles

          What is a Claude Skill? The Plain-English Guide (2026)

          What is a Claude Skill? The Plain-English Guide (2026)

          Conversational AI Answers the Phone When Your Team Cannot. Here Is How It Actually Works.

          Conversational AI Answers the Phone When Your Team Cannot. Here Is How It Actually Works.

          The AI Voice Agent That Calls Before Customers Complain

          The AI Voice Agent That Calls Before Customers Complain

          Waboom AI

          Empowering New Zealand and Australian businesses with AI voice agents and automation that deliver real, measurable value.

          info@waboom.ai+64 9 885 9695 (NZ)+61 485 027 479 (AU)
          Level 8, 139 Quay Street
          Auckland CBD, New Zealand

          Voice Agents

          • AI Voice Agents
          • AI Receptionist NZ
          • AI Receptionist Australia
          • AI Phone Answering
          • AI Virtual Receptionist
          • AI Receptionist Pay As You Go
          • Waboom Concierge
          • Medical Answering Service
          • Answering Service Australia
          • AI Sales Agent
          • Voice Agent Pricing
          • Listen to Voices
          • Real Estate Guide

          By Industry

          • Real Estate
          • Mortgage Brokers
          • Insurance Brokers
          • Property Managers
          • Medical Clinics
          • Dentists
          • Vets
          • Childcare + ECE
          • Car Dealerships
          • Construction + Builders
          • Electricians
          • Plumbers
          • HVAC
          • Accountants
          • Law Firms
          • All industries and regions

          Workshops

          • All Workshops
          • AI Team Training
          • AI Strategy Workshop
          • AI Champion Workshop
          • Claude Team Training
          • Claude Code Workshop
          • Lovable Workshop
          • Free AI Workshop

          Automation

          • AI Automation
          • Microsoft Copilot Agents
          • Integrations

          Company

          • About Us
          • Contact
          • Partners
          • Pipedrive Partner
          • Resources
          • Blog
          • AI Agency NZ
          • AI Agency Australia

          Powered by leading AI technologies

          VAPIOpenAIZapierMakeStripe

          © 2026 Waboom.ai. All rights reserved.

          PrivacyTermsSecurity