Signal IQ

The AI-native sales agent that turns Nimble's live web search into pipeline. Define your ICP, get scored accounts, real buying signals, and personalized outreach in under a minute for under 5 cents.

Comment

What is Signal IQ

Signal IQ is an agentic AI sales intelligence platform. A sales rep describes their ideal customer in natural language, and an AI agent autonomously finds matching companies from the live web, enriches them with contacts and buying signals, and generates personalized outreach - all in under a minute.

It is powered by Nimble's live web data infrastructure for sourcing and signal detection, and Claude AI for reasoning, scoring, and writing. Every step is traced and observable. Nothing sends without human approval.

The Problem

B2B sales reps spend 70% of their time on work that isn't selling. Researching companies, finding the right contact, writing a personalized email, updating the CRM - all of it manual, all of it slow, all of it based on stale data from static databases that were last updated months ago.

The result: reps reach out to companies that just got acquired, contact people who left six months ago, and send generic emails that reference signals that are no longer relevant. Pipeline suffers. Quota suffers.

The root cause isn't effort - it's data. Sales teams don't have access to live web intelligence at the moment they need it.

The Insight

Nimble gives you the live web. Every company's LinkedIn page, every funding announcement, every executive hire, every job posting - all of it accessible in real time via structured APIs.

The question is: what's the right architecture to turn that live web data into revenue?

Signal IQ is our answer - surfacing the intelligence that's already on the web so sales reps know exactly which companies to call, why, and what to say.

How It Works

A sales rep defines their Ideal Customer Profile (ICP) - the type of company they want to sell to - and the agent does the rest:

  1. Finds matching companies from the live web - Nimble's Search API searches for LinkedIn company pages matching the ICP criteria in real time (see Nimble module in the repo: backbone/app/integrations/connectors/nimble.py)
  2. Parses firmographic data from LinkedIn search snippets - employee count, headquarters, industry, description
  3. Detects buying signals - funding rounds, executive hires, market expansions - via 4 parallel Nimble Search API queries per company
  4. Scores each account against the ICP - Claude assigns a fit score based on industry, size, geography, and signals
  5. Generates personalized outreach anchored to real Nimble signals - Claude writes each email using the actual buying signal as the hook
  6. Queues everything for human approval - Claude's drafts wait for a human decision before anything sends

The entire pipeline runs in under a minute for about 5 cents.

The Architecture

Signal IQ is built as a 9-node state machine. Each node has a single responsibility, reads from the shared state, calls its tools, and writes results back. The pipeline is fully observable - every Nimble API call, every LLM call, every token logged with inputs, outputs, reasoning, and latency.

ICP definition
    ↓
[Claude] Translate ICP → search parameters
    ↓
[Nimble Search API] Find LinkedIn company URLs + parse firmographics from snippets
    ↓
[Nimble Search API] Contact enrichment — LinkedIn profile search per account
    ↓
[Nimble Search API] 4 parallel signal queries per company
    ↓
[Claude] Score each account for ICP fit
    ↓
[Claude] Generate value hypothesis per top account
    ↓
[Claude] Write personalized outreach anchored to real signals
    ↓
Human-in-the-Loop checkpoint → approve or reject each draft

Why the Search API - Not Agents, Extract, or SERP

Before settling on the Search API as the foundation, we systematically evaluated every Nimble API to find the best fit for a GTM sales application.

Web Search Agents — we evaluated both Nimble's official agent gallery and all 702 community-maintained agents. The official gallery covers e-commerce, search engines, and social media — none applicable to B2B company research. Among the community agents, we inspected the most promising candidates across news, finance, and jobs verticals. No pre-built agent exists for generic company profiles, firmographic data, or buying signals that works across any user-defined ICP — the closest options (LinkedIn job boards, Glassdoor, SEC EDGAR) either require a known URL or a company-specific identifier such as a CIK number, neither of which a sales rep has when prospecting a new market.

Extract API — we tested client.extract() on LinkedIn company pages. It returned structured Organization entities for well-known companies but failed silently for smaller or lesser-known companies — the exact firms most likely to appear in a niche ICP. Coverage was inconsistent and latency was higher than search.

SERP API with google_news — we ran the same signal queries through both client.search() and client.serp.run(search_engine="google_news", parse=True). SERP returned Google News redirect URLs (news.google.com/read/...) instead of direct article URLs, and for some queries returned only an Organization entity with no news results at all. client.search() returned direct source URLs from BusinessWire, FinTech Futures, and company newsrooms — immediately usable as signal sources.

The conclusion is clear: client.search() is the ideal API for building a GTM sales application — powerful enough to source companies, enrich contacts, and detect buying signals across any industry and any signal type, all from a single unified interface. The breadth and real-time quality of Nimble's Search API is precisely what makes a user-defined ICP possible at all.

Why Nimble is Central - Not Peripheral

Nimble is the foundation of Signal IQ - not an add-on. Remove it and the platform doesn't work.

Account sourcing is impossible without it. There is no static database of "Series B fintech companies with 200-500 employees that just raised a funding round." That data only exists on the live web. Nimble's Search API finds LinkedIn company pages matching the ICP in real time - companies that fit the criteria today, not six months ago when some database was last refreshed.

Contact enrichment is impossible without it. Nimble's Search API finds decision-maker contacts via LinkedIn profile search - names, titles, LinkedIn URLs. No separate people database needed. No stale contact lists.

Signal detection is impossible without it. The platform runs 4 parallel Search API queries per company - funding news, hiring activity, executive changes, market expansions. These are real web results from the last few weeks, not inferred from company descriptions. An outreach email that opens with "I saw you just raised your Series B" only works if you actually know they just raised their Series B. Nimble makes that possible.

In a live run against a Series B Fintech Scaleup ICP:

  • Nimble found 10 matching companies from LinkedIn
  • Nimble extracted 35 decision-maker contacts via profile search
  • Nimble detected 78 buying signals from live web searches
  • Claude wrote 5 personalized outreach emails, queued for human approval

Every one of those numbers is zero without Nimble.

The Human-in-the-Loop Design

Signal IQ never sends anything automatically. Every outreach draft requires explicit human approval before it goes anywhere. This is intentional - not a limitation.

Nimble provides the live intelligence. Claude does the reasoning. But a human makes the final call on every email. This is the right model for outbound sales: high automation, high quality, human accountability.

The Business Case for Nimble

Every sales rep using Signal IQ is a Nimble API consumer. Every ICP run triggers:

  • 1 Search API call for account sourcing (finds up to 20 LinkedIn URLs, parses top 10)
  • 8 concurrent Search API calls for contact enrichment (one per account)
  • 32 concurrent Search API calls for signal detection (4 queries × 8 accounts)

A sales team of 10 reps, each running 2 prospect sweeps per week, generates ~820 Search API calls per week - just for one team. Scale that to the thousands of B2B sales teams that need this capability and the usage compounds fast.

Signal IQ is designed to make Nimble's live web data the default infrastructure for B2B prospecting. The more reps use it, the more valuable the live data becomes, and the more indispensable Nimble's infrastructure is to the sales workflow.

Key Strengths

  • Full observability. Every step traced. Every Nimble call logged with inputs and outputs. Every token counted. A sales manager can see exactly what the agent did and why.
  • Production architecture. Multi-tenant PostgreSQL with Row-Level Security. Celery async workers. JWT authentication. Not a demo - a v1 product.
  • ICP-driven, not keyword-driven. The AI translates a natural language customer description into structured search parameters. A rep doesn't need to know LinkedIn's industry taxonomy. They just describe their ideal customer.

Try It

URL:      https://signaliq.williamcheung.buzz/login
Email:    demo@acme.com
Password: Signal!Q2026

Two ICPs are pre-loaded: Enterprise SaaS (Series B+) and Series B Fintech Scaleup. Select one, click Run Agent, and watch the pipeline execute live against Nimble's APIs. Results in under a minute.

Built With

Share this project:

Updates