Web Search Agents

Web Search Agents turn complex web research tasks into repeatable API calls. Describe the task in plain language — the agent plans the work, searches and extracts across the live web, reasons over what it finds, and returns a cited answer or a structured dataset. Generic search tools treat every use case the same. A Web Search Agent is an expert you shape: it learns your domain, remembers what worked, and improves with every run — while staying fully controllable and auditable.

Try it in the Playground

Run a research task in the browser — no code, no setup

Quickstart

Zero to a cited answer in three API calls

Input and output

One request in:

{ "input": "Compare the pricing and positioning of Datadog and Grafana Cloud." }

One deliverable out:

Datadog anchors the premium end of the market, with Pro pricing
from $15 per host per month [1]. Grafana Cloud undercuts it with
a free tier and usage-based pricing [2], positioning itself for
teams that want to start small...

[1] datadoghq.com/pricing — "Pro: starting at $15 per host, per month"
[2] grafana.com/pricing — "Start for free, pay as you go"

Each [n] marker resolves to a machine-readable claim with source URLs, verbatim excerpts, and a confidence grade. See Trust. Run it yourself — in the Playground or from code:

from nimble_python import Nimble

nimble = Nimble(api_key="YOUR-API-KEY")

run = nimble.agents.run(
    input="Compare the pricing and positioning of Datadog and Grafana Cloud."
)

import Nimble from "@nimble-way/nimble-js";

const nimble = new Nimble({ apiKey: process.env.NIMBLE_API_KEY });

const run = await nimble.agents.run({
  input: "Compare the pricing and positioning of Datadog and Grafana Cloud.",
});

client := nimble.NewClient(option.WithAPIKey("YOUR-API-KEY"))

run, err := client.Agents.Run(ctx, nimble.AgentRunParams{
    Input: "Compare the pricing and positioning of Datadog and Grafana Cloud.",
})

nimble agents run \
  --input "Compare the pricing and positioning of Datadog and Grafana Cloud."

curl -X POST 'https://sdk.nimbleway.com/v2/agents/runs' \
  --header 'Authorization: Bearer <YOUR-API-KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
    "input": "Compare the pricing and positioning of Datadog and Grafana Cloud."
  }'

Runs are asynchronous — poll for the result or stream progress events. The Quickstart walks through the full loop.

What you can build

Every agent works in one of three modes, set by its use_case:

Research

Answer hard questions. Competitive intelligence, due diligence, market and sentiment analysis — cited briefs on demand.

Enrichment

Complete your data. Send CRM rows or product records with gaps, get them back filled — every added value cited.

Dataset Building

Discover from scratch. One prompt in, a structured dataset out — every cell with its own evidence.

Mode	You send	You get back
Research	”How is Acme positioned against its competitors?”	A cited analyst brief
Enrichment	500 CRM rows with missing funding data + a schema	The same 500 rows, gaps filled and cited
Dataset Building	”Find all spas and salons in New York City” + a schema	Fresh rows discovered from the live web

Build the agent your workflow needs: a Company Research Agent that maintains living company profiles, a Consumer Sentiment Agent that reads reviews and forums, a Lead Enrichment Agent that completes your pipeline — or start from a pre-built template.

Start from a template

Templates ship with goals, source guidance, a skill briefing, and output schemas already tuned. Create your own copy with one call and customize from there:

agent = nimble.agents.create(template="due-diligence")

const agent = await nimble.agents.create({ template: "due-diligence" });

agent, err := client.Agents.New(ctx, nimble.AgentNewParams{
    Template: param.NewOpt("due-diligence"),
})

nimble agents create --template due-diligence

curl -X POST 'https://sdk.nimbleway.com/v2/agents' \
  --header 'Authorization: Bearer <YOUR-API-KEY>' \
  --header 'Content-Type: application/json' \
  --data '{"template": "due-diligence"}'

Mode	Templates
Research	`competitive-intelligence` · `due-diligence` · `brand-intelligence` · `company-profile` · `price-comparison` · `real-estate-research`
Enrichment	`lead-enrichment` · `financial-intelligence` · `ecommerce-intelligence`
Dataset Building	`business-discovery` · `company-discovery` · `gtm-lead-discovery` · `open-positions-search` · `social-media-monitor`

List them with GET /v2/agents/templates — each returns its full configuration, suggested prompts, and an example result.

Why it’s different

Generic web search has no idea what your agent is trying to accomplish. A Web Search Agent does — because it’s stateful, self-improving, and configurable to perfection:

An expert, not a generic index. The agent learns your use case through its skill, goals, and sources — what dimensions matter, what jargon means, which sources to trust, and what a good result looks like.
Self-improving. Memory captures what worked — sources, retrieval paths, domain patterns — and feeds every future run. Storage keeps collected data and outputs so runs build on each other instead of starting from zero. Recurring tasks get faster, more accurate, and up to 50% cheaper.
Trustworthy. Every run returns a trust report: per-claim citations with verbatim excerpts, graded confidence, and the full list of sources consulted — auditable end to end.
Full web access. Agents run on Nimble’s web tools — Search, Extract with JS rendering and stealth mode, Extract Templates, and Crawl — reaching data that generic tools can’t.

A completed Web Search Agent run showing a cited competitive-intelligence report — A completed research run: the answer, its execution metadata, and a confidence-graded citation on every claim.

How it works

You send a task

Plain language, like briefing an analyst. Optionally add a JSON Schema to get structured data back.

The agent plans

It breaks the task into checkable goals and search steps, informed by its skill and everything in memory.

It searches and extracts

The agent works across dozens to hundreds of pages, cross-checking conflicting sources and ranking them by authority.

You get the deliverable

A prose answer or JSON matching your schema — plus the trust report grading the evidence behind every claim.

Configure it to perfection

agents.run works with zero configuration. For repeat work, create a persistent agent and tune every dimension:

Field	What it does
`skill`	A briefing that makes the agent think like your analyst — what dimensions matter, what jargon means
`goals`	Checkable objectives the agent works through on every run
`sources`	Allow-lists, block-lists, and hints like “official pricing pages over third-party summaries”
`effort`	A dial from `low` (quick sweep) to `x-high` (exhaustive). See Efforts
`output_schema`	A JSON Schema — answers arrive as data, every value cited
`use_case`	`research`, `enrichment`, or `dataset_building`

Runs at any scale

Stream a single run’s progress as server-sent events, chain follow-up runs with previous_interaction_id, or hand the agent to Jobs to run on a schedule across thousands of inputs with managed delivery.

Building AI agents? Web Search Agents are available as tools on the Nimble MCP server — call them from Claude, Cursor, or any MCP client in production.

Zero Data Retention

Web Search Agents support Zero Data Retention (ZDR) on enterprise plans. With ZDR enabled, your prompts, input data, and outputs are retained only within the window defined in your contract — and are never used for training or shared with any other customer. Retention is set per data type, including whether the agent keeps memory and storage across runs. Contact Nimble to enable ZDR for your account.

Next steps

Playground

Run your first task in the browser

Quickstart

The full create → wait → result loop in code

Use Cases

Research, Enrichment, and Dataset Building in depth

API Reference

Every endpoint, field, and response

Getting Started

Web Tools

Extract Templates

Jobs

Guides

SDKs

Admin

Proxy

Web Search Agents

Try it in the Playground

Quickstart

Input and output

What you can build

Research

Enrichment

Dataset Building

Start from a template

Why it’s different

How it works

Configure it to perfection

Runs at any scale

Zero Data Retention

Next steps

Playground

Quickstart

Use Cases

API Reference

Try it in the Playground

Quickstart

​Input and output

​What you can build

Research

Enrichment

Dataset Building

​Start from a template

​Why it’s different

​How it works

​Configure it to perfection

​Runs at any scale

​Zero Data Retention

​Next steps

Playground

Quickstart

Use Cases

API Reference

Input and output

What you can build

Start from a template

Why it’s different

How it works

Configure it to perfection

Runs at any scale

Zero Data Retention

Next steps