Show HN: AI that researches your B2B prospects like a human

Show HN: AI that researches your B2B prospects like a human(intellisell.ai)

3 points by troyethaniel 281 days ago | 5 comments

My co-founder and I work in B2B sales. We’ve seen how genuine prospect research and personalized outreach can win deals — but also how exhausting it is to manually research and track every prospect.

We tried CRMs and popular sales intelligence tools, but they felt like static directories — good for contacts, not for real insights or engagement. GPTs were great at generating content, but to get a usable Customer 360° strategy, we had to constantly engineer prompts and feed it fresh data about both the customer and us.

So we built intellisell.ai — an AI-first sales research assistant that: a) Aggregates information from multiple public sources, and b) Uses AI to deduce and distill it into insights and strategies that align with your solution.

The User Experience: - You complete your profile (your solution, ICP, UVP) once. - You then provide the company URLs you want to track - We aggregate company information from multiple sources across web, news, social media, etc - We then feed this context and structured prompts to build a comprehensive account profile. - You can then Ask any questions - e.g "What are the top 3 priorities for their CTO based on recent interviews?" or "Draft me an email referencing their latest product launch." Auto-Generate a comprehensive account plan and Engagement Strategy - matching your solution and ICP. Track updates & buying signals - See a weekly summarised view of the latest updates with insight and buying signals, sentiment, and tags.

We're trying to build something more dynamic than a CRM and more strategic than a simple data firehose. Instead of just giving you data, it helps connect the dots.

Is this a problem you or your sales teams have faced? We would love to hear your feedback.

troyethaniel 281 days ago |

Thanks for checking this out — happy to answer any technical or product questions.

A bit more context on how we built it:

The Technical Solution The Architecture has 4 major components

1. Data Extraction Engine (DXE): We aggregate information from multiple sources across web, news, social media, etc. using a combination of scraping and APIs. 2. Data Inference Engine (DIE): We use a combination of methods + prompts and context engineering to get LLM to "deduce" context from indirect and unstructured sources. e.g "a company's Tech Stack can be inferred from job postings" 3. Update Tracking Engine (UTE): Essentially a combination of DXE and DIE to track updates across web, news and social media and use LLM to filter and summarize raw data into insights, tags and sentiment analysis 4. Personalized Conversation Engine (PCE): We ask for a users company, solution (product/services), Unique Value Proposition, ICP and Competitors - so responses to any user question are relevant and in context to the solution user offers.

The hardest problems:

Signal vs. noise — Many updates from public sources aren’t actionable. We had to train heuristics + LLM filters to prioritize events like funding rounds, leadership changes, product launches, and regulatory filings over irrelevant press.

Context merging — Linking a single prospect’s identity across fragmented sources (different domains, naming variations, subsidiaries) without false positives was tricky — we built a lightweight entity resolution system for this.

Inference — Instead of just surfacing raw events, we needed the AI to connect the dots (e.g., “They just hired a new CFO from a competitor — may signal strategic shift”). This required multiple chained LLM calls and domain-specific prompt templates.

Speed — Research and plan generation had to happen in seconds, so we implemented caching and pre-fetching strategies for monitored accounts.

What we’re curious about from HN folks:

- Better ways to extract information from unstructured data sources - Ideas for reducing LLM token usage without losing context quality - Feedback on UX for chat-based research vs. dashboard-style layouts

Happy to dive into any of these or share more if people are interested.

adityamoghe 281 days ago |

This sounds really powerful for lead generation. I'm curious, how does the AI handle finding contact information for specific people within a company, like decision-makers?

troyethaniel 281 days ago | |

Thanks Aditya, while intellisell can be used for lead generation like other Sales Intelligence tools, we believe our focus is on lead qualification and research. As for finding contact information - we do rely on API from our data partners for publicly available information on people's roles. The AI then analyzes who could be potential decision makers based on user's product or solution.. e.g A HR SaaS indicated that a Head of HR would be a decision maker. It then summarizes the Names, Titles, Roles, Departments, Background and Experience, Key Motivations, Potential Objections and creates a tailored Engagement strategy.

Hope this helps

jonclair 281 days ago |

Is the “deduction” part all prompt-engineered GPT-4/Claude/etc., or have you fine-tuned a custom model specifically for B2B sales intelligence?

troyethaniel 281 days ago | |

Right now, it’s a blend: structured pre-processing + context engineering + proprietary prompt frameworks on top of Gemini + Web Search, with fallback to OpenAI and Claude for certain synthesis tasks. Over time, we may shift more of that into a vertically-trained model to improve speed, privacy, and cost.