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
Thinking is for deliberation, search is for facts, research is for reports. That is the whole map you need.
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
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
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 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 Thinking | Multi-constraint problems, design decisions | A considered reasoning answer | 30-90 seconds |
| Web Search | You need live information | An answer grounded in cited current sources | 10-30 seconds |
| Research | You want a report from multiple sources | A structured 1-2 page document with citations | 5-10 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.
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 →Leonardo Garcia-Curtis
Founder & CEO at Waboom AI. Building voice AI agents that convert.
Ready to Build Your AI Voice Agent?
Let's discuss how Waboom AI can help automate your customer conversations.
Book a Free Demo


