Websearch

Websearch tool

Enable your AI agent to retrieve real-time information from the internet during execution — accessing up-to-date external data instead of relying solely on pre-trained knowledge.

Agent Tool Real-Time Search Structured Output Full Observability

What is the Web Search tool?

The Web Search tool is an agent tool that enables an AI agent to retrieve real-time information from the internet during execution. Agents can access current external data such as news, market trends, company information, and technical updates instead of relying solely on pre-trained knowledge.

The tool performs the search, retrieves relevant results, and the LLM processes them to extract useful information. The output is returned as a ToolMessage, and the agent continues execution using the retrieved data.

Key capabilities

Real-time retrieval

News, market trends, company profiles, and technical updates

Structured output

Source links, citations, and extracted content

Full observability

All activity visible in logs — query, sources, results

Prerequisites

What you'll need before using the Web Search tool.

Required

LLM connection

At least one LLM provider connection available in your Konnectify account

Required

Supported model

OpenAI GPT-4o or Anthropic Claude 3 and above selected for the agent

Required

Existing agent

An existing agent or the ability to create a new one in AI Agents

Configuration

When adding the Web Search tool to an agent, three fields must be configured. Each one shapes how the agent identifies, invokes, and uses the tool during execution.

Field

Description

Instructions

Required

Specifies how the tool should be used. Provide the agent with detailed operational guidance — prioritizing recent sources, requiring citations, or structuring the output in a specific format. Well-written instructions directly improve the quality and consistency of output.

Tool name

Identifier

A custom identifier used by the agent to invoke the tool. This is the name the agent will reference internally when deciding to use web search.

Description

Trigger logic

Defines when the agent should use the Web Search tool. A clear, specific description helps guide the agent's decision-making — the better the description, the more reliably the agent invokes the tool at the right moment.

Note

All three fields are required. The Instructions field in particular has the most direct impact on output quality — always provide clear, specific guidance on how the tool should behave.

When to use

Use the Web Search tool when your agent needs dynamic or external data that goes beyond its pre-trained knowledge.

Good fits

Researching company profiles, founders, or funding data

Fetching the latest news on a topic

Identifying competitors, trends, and industry insights

Enriching internal records with external data

Looking up documentation, versions, or technical updates

Not the right tool

Static or already known information the model has in training

Private or restricted content not accessible by web search

Data requiring authenticated access to internal systems

Step-by-step guide

Open the AI Agents section Setup

Navigate to the AI Agents section and open an existing agent or create a new one.

Go to Configured Tools Setup

Inside the agent, navigate to the Configured Tools section.

Add Web Search Add tool

Click Add a new tool and select Web Search from the tool list.

Configure the tool Configure

Write Instructions — specify how the tool should behave: prioritizing recent sources, always including citations, or structuring output in a specific format

Enter a Tool Name — a clear identifier the agent will use to invoke the tool

Write a Description — define when the agent should use web search

Tip

All three fields are required. The Instructions field directly controls how the agent uses the tool — invest time writing clear, detailed instructions for the best results.

Update the agent's instructions Instructions

Update the agent's main instructions to include guidance on when to use the Web Search tool. This reinforces the tool's purpose at the agent level.

Select a supported language model Model

Choose a compatible model for the agent — OpenAI GPT-4o or Anthropic Claude 3 and above.

Save and activate the agent Activate

Save the configuration and set the agent status to Active to make it live.

Test and verify Final step

Test the agent with queries that require real-time or external information

Verify the results and review the activity logs to confirm the tool was invoked correctly

Activity logs

The activity logs provide full visibility into every Web Search tool execution. Each log entry includes:

Search query

The exact query the agent used to search the web

Sources referenced

The list of web sources the tool retrieved results from

Extracted content

The relevant information pulled from search results

Tool output

The full ToolMessage returned to the agent for further processing

Example use cases

Common scenarios where the Web Search tool adds real value inside an AI Agent workflow.

Company research

Founders · Headquarters · Products · Funding

Research

Retrieve company details such as founders, headquarters, products, funding rounds, and key competitors. Ideal for sales intelligence, due diligence, and market mapping.

News retrieval

Latest updates · Topic monitoring · Current events

News

Fetch the latest news and updates on any specific topic. Useful for monitoring brand mentions, industry shifts, regulatory changes, or competitor activity.

Market analysis

Competitors · Trends · Industry insights

Analysis

Identify competitors, trends, and industry insights from the web. Supports strategic planning, positioning, and competitive benchmarking.

Data enrichment

External data · Internal record enhancement

Enrichment

Enhance internal data records with external information from the web — such as adding missing company details, contact data, or product information to a CRM entry.

Technical lookup

Documentation · Versions · Technology updates

Technical

Retrieve documentation, version numbers, changelogs, or updates for libraries, APIs, and technologies. Keeps agents up to date with the latest releases.

Example instruction

A ready-to-use instruction you can paste into the Instructions field when configuring the Web Search tool for a Company Research use case. Adapt it for your own needs.

Company Research — Example Instructions Field

You are a professional market research analyst.

I will provide you with a company name. Your task is to perform a web search and generate a structured, accurate, and concise company profile.

Instructions:

1. Search the web for the given company.

2. Extract only verified and relevant information.

3. Present the output in a clean, structured format.

Include the following details:

- Company Name

- Founders (with names)

- Year Founded

- Headquarters (Location)

- Industry / Sector

- Company Size (employees or range)

- About the Company

- Products / Services

- Target Customers / Market

- Funding / Valuation (if available)

- Key Competitors (if available)

- Website

Rules:

- Use the most recent and reliable sources.

- Keep the response concise but informative.

- Do NOT hallucinate or assume missing data — mention "Not publicly available" if needed.

- Prefer bullet points over long paragraphs.

Input:

Company Name: [ENTER COMPANY NAME]

Things to know

Best practices and limitations to keep in mind when using the Web Search tool.

Best practices

Clearly define when the tool should be used in the Description and agent instructions

Write detailed Instructions — this field is required and has the most direct impact on output quality

Use the tool for dynamic and external data requirements only — avoid static or already-known information

Review activity logs after testing to confirm the agent is invoking the tool at the right moment

Limitations

Limitation

Detail

Result accuracy

Depends on the capabilities of the selected large language model

Private or restricted content

Cannot be accessed — the tool only retrieves publicly available web content

Model selection matters

The quality and accuracy of web search results are directly influenced by the model processing them. Always use a supported model — GPT-4o or Claude 3 and above — for the best results.

Get started

Ready to build smarter agents?

Add Web Search to your agent and give it access to real-time, source-backed information.

Get started free