Lessie is an AI agent that helps you find and reach the right people. Instead of filters or keywords, describe your target. Lessie discovers high-quality matches across the web and automates personalized outreach and follow-ups.
We built Lessie around a simple question: Why is finding the right person still so slow?
Whether it's creators, leads, or candidates, the process is always the same — search across platforms, compare profiles, filter manually, then figure out how to reach out.
So we rethought the whole flow. With Lessie, you can just describe who you're looking for — and it handles the rest: finding, evaluating, and even reaching out. Instead of giving you another list, it actually helps you move from search to connection in one go.
What sets us apart is our State-of-the-Art (SOTA) people search quality. In our head-to-head platform comparisons, Lessie consistently outperforms tools like Exa and Juicebox across Relevance, Coverage, and Utility. By reasoning across the entire web, Lessie identifies the most relevant matches that traditional filters miss, delivering a level of precision and depth that defines the new standard for AI-native people search.
If you're doing:
📣 Influencer sourcing
🚀 Outbound / Lead gen
🤝 Hiring or networking
…or really anyone, anywhere you need to reach, would love for you to try Lessie with a real use case and tell us where it breaks.
We've also open-sourced our core Skills — including our modules for finding people, enriching contacts, and deep company research. We want Lessie to be truly extensible, so we encourage you to plug these skills into your own stack. Whether you're building a custom sourcing engine or a specialized research agent, you can leverage our open-source foundation to automate the heavy lifting.
🎁 Try Lessie today withPH Special: Use code PH50 to get 50% OFF! We're here all day — happy to dive into anything.
Report
@colin_yu_123 I’m particularly interested in your open-sourced Skills. As someone focused on AI Agent orchestration, I’d love to know: how modular are these skills? Can they be easily plugged into a local-first stack (like an Ollama-based agent) to handle the 'deep company research' part without hitting your cloud infrastructure? Also, how do you handle the 'Human-in-the-loop' part for the automated outreach to ensure it doesn't feel like spam?
@dora_lin2 Thanks for asking. Our Lessie skill is fairly modular.
We currently support both MCP and CLI, and we package the core people-search/research capabilities as atomic building blocks, so they can slot into different agent setups pretty cleanly. For local-first use: the skill is still backed by Lessie’s online service, so there’s no need to deploy the stack locally. You just need a client that supports skills — such as Claude Code, Cursor, OpenClaw, or Claude.ai web — and it works through Lessie’s auth flow.
For outreach, we’re very careful about the human-in-the-loop piece. We don’t think good outreach should feel like mass spam. The goal is to help users create recipient-specific, context-aware drafts, with human review where it matters, so the experience feels much closer to real communication than sequence blasting.
@victoria_wu Totally agree. That is exactly the direction we believe in, less filtering, more actual outcomes.
Niche profiles are actually one of the most interesting use cases for Lessie, since they usually do not fit cleanly into standard filters. That is where broader cross-source signals become especially helpful.
@victoria_wu Thanks! Less filtering, more actual results, that’s what we built Lessie for.
Report
@colin_yu_123 The evidence part helps. A list is easy. Feeling confident enough to actually message the person is the harder step. What do users edit more often right now, the match or the outreach?
@artem_kosilov Great question. From what we have seen, the match and the outreach usually evolve together, because they are really part of the same workflow.
As people get clearer on who is actually a strong fit, the outreach becomes easier to shape. And once they start drafting outreach, it often helps confirm whether the match and reasoning are strong enough.
That is why the evidence layer matters so much to us.
@artem_kosilov That’s a great way to put it, the confidence to reach out is really the harder part.
So far, we’re seeing users tweak the outreach slightly more than the matches, mainly to adjust tone or add context. But overall, the matching tends to hold up well, especially with clearer intent.
Report
@colin_yu_123 How customizable are the outreach templates for non-US markets? Would love to see it handle cultural nuances better.
The useful part here is the context layer. For finding creators who actually fit a niche, knowing why someone matches is way more valuable than getting 500 loose results.
@busmark_w_nika Great question! We do cover some of the core capabilities you’d expect from tools like RocketReach — including contact data and enrichment.
Where Lessie goes further is helping you identify the right people to reach out to, not just find contacts. We focus on matching “fit” using AI, and also support tailored email generation and more structured outreach management.
On the data side, we aggregate from multiple providers to ensure compliance and accuracy, and validate results across sources. Happy to share more!
Report
@busmark_w_nika This is interesting! I wonder what methods they use to collect such detailed contact info for each person. Any insights?
@busmark_w_nika@sarah_jade1 Great question. We use a combination of compliant and accuracy-focused third party contact data providers, together with our own internally built data sources.
A big part of the work is not just collecting data, but cross-checking signals across sources so the results are more reliable and actionable.
@busmark_w_nika The main difference is that Lessie is besides just “cold emails”, we do more about helping you figure out who’s actually worth reaching out to. It’s designed to handle the matching, prioritization, and even the outreach flow, not just return a single list with outdated data.
Very interesting for those looking out agentic solutions for sales - congrats on launching!
Will this handle bidirectional sync (with existing CRM) ? Specifically, if a lead is updated in our CRM (say, they are marked "Do Not Contact"), does Lessie's AI agent detect the changes to adjust its own outreach logic?
We already respect key CRM signals like “Do Not Contact” to avoid conflicts. Full real-time bidirectional sync is something we’re actively working on. Which CRM are you using?
@gayatri_sachdeva Love this question, this is exactly the kind of workflow we’re thinking about. Today, Lessie can already pick up important signals (like contact restrictions) to prevent unwanted outreach. And deeper CRM sync is something we’re building toward.
Report
Interesting that you mention multi-agent architecture on the site. Does each agent handle a different source like LinkedIn vs Twitter, or is it more about splitting up the research steps?
@ermakovich_sergey It’s mainly about splitting the research into specialized steps (intent, sourcing, verification, ranking), with some agents optimized for specific sources — so a mix of both
Report
Maker
@ermakovich_sergey Good question, it’s more about splitting up the research steps than just assigning one agent per platform.
Report
Just tested it with a real search, looked up Nintendo Switch influencers and the results were actually relevant, not just a generic list of gaming accounts.
That's already better than most tools I've tried, curious how it handles more niche searches though, would 'indie iOS app makers who talk about productivity' surface real micro-influencers, or does it work better with broader categories?
@misbah_abdel Love that example — appreciate you trying it out!
It actually tends to perform even better on niche queries like that. The more specific (even a bit fuzzy) the intent, the more the agent can surface relevant micro-influencers beyond generic lists.Would be curious what you find if you test that one!
Report
Maker
@misbah_abdel thanks for testing, from what I’ve seen, it actually gets pretty interesting with niche searches. Stuff like “indie iOS app makers who talk about productivity” usually brings up smaller builders and micro-creators instead of just big generic accounts.
For me the best part of this category is prioritization. A ranked list of creators with reasons makes the influencer discovery workflow much easier than a raw directory dump.
Totally agree — prioritization makes all the difference. We focus on ranking creators by real relevance, with clear reasons behind each result — so it’s not just a list, but something you can act on.
Lessie AI
👋 Meet Lessie
Hi Product Hunt! I'm Colin, founder of Lessie.
We built Lessie around a simple question: Why is finding the right person still so slow?
Whether it's creators, leads, or candidates, the process is always the same — search across platforms, compare profiles, filter manually, then figure out how to reach out.
So we rethought the whole flow. With Lessie, you can just describe who you're looking for — and it handles the rest: finding, evaluating, and even reaching out. Instead of giving you another list, it actually helps you move from search to connection in one go.
What sets us apart is our State-of-the-Art (SOTA) people search quality. In our head-to-head platform comparisons, Lessie consistently outperforms tools like Exa and Juicebox across Relevance, Coverage, and Utility. By reasoning across the entire web, Lessie identifies the most relevant matches that traditional filters miss, delivering a level of precision and depth that defines the new standard for AI-native people search.
If you're doing:
📣 Influencer sourcing
🚀 Outbound / Lead gen
🤝 Hiring or networking
…or really anyone, anywhere you need to reach, would love for you to try Lessie with a real use case and tell us where it breaks.
We've also open-sourced our core Skills — including our modules for finding people, enriching contacts, and deep company research. We want Lessie to be truly extensible, so we encourage you to plug these skills into your own stack. Whether you're building a custom sourcing engine or a specialized research agent, you can leverage our open-source foundation to automate the heavy lifting.
🎁 Try Lessie today with PH Special: Use code PH50 to get 50% OFF! We're here all day — happy to dive into anything.
@colin_yu_123 I’m particularly interested in your open-sourced Skills. As someone focused on AI Agent orchestration, I’d love to know: how modular are these skills? Can they be easily plugged into a local-first stack (like an Ollama-based agent) to handle the 'deep company research' part without hitting your cloud infrastructure? Also, how do you handle the 'Human-in-the-loop' part for the automated outreach to ensure it doesn't feel like spam?
Lessie AI
@dora_lin2 Thanks for asking. Our Lessie skill is fairly modular.
We currently support both MCP and CLI, and we package the core people-search/research capabilities as atomic building blocks, so they can slot into different agent setups pretty cleanly. For local-first use: the skill is still backed by Lessie’s online service, so there’s no need to deploy the stack locally. You just need a client that supports skills — such as Claude Code, Cursor, OpenClaw, or Claude.ai web — and it works through Lessie’s auth flow.
For outreach, we’re very careful about the human-in-the-loop piece. We don’t think good outreach should feel like mass spam. The goal is to help users create recipient-specific, context-aware drafts, with human review where it matters, so the experience feels much closer to real communication than sequence blasting.
Happycapy
@colin_yu_123 Super interesting take on “people search → connection” instead of just another list.
Feels like this is where things should go — less filtering, more actual outcomes. Curious how it performs on really niche profiles 👀
Lessie AI
@victoria_wu Totally agree. That is exactly the direction we believe in, less filtering, more actual outcomes.
Niche profiles are actually one of the most interesting use cases for Lessie, since they usually do not fit cleanly into standard filters. That is where broader cross-source signals become especially helpful.
Lessie AI
@victoria_wu Thanks! Less filtering, more actual results, that’s what we built Lessie for.
@colin_yu_123 The evidence part helps. A list is easy. Feeling confident enough to actually message the person is the harder step. What do users edit more often right now, the match or the outreach?
Lessie AI
@artem_kosilov Great question. From what we have seen, the match and the outreach usually evolve together, because they are really part of the same workflow.
As people get clearer on who is actually a strong fit, the outreach becomes easier to shape. And once they start drafting outreach, it often helps confirm whether the match and reasoning are strong enough.
That is why the evidence layer matters so much to us.
Lessie AI
@artem_kosilov That’s a great way to put it, the confidence to reach out is really the harder part.
So far, we’re seeing users tweak the outreach slightly more than the matches, mainly to adjust tone or add context. But overall, the matching tends to hold up well, especially with clearer intent.
@colin_yu_123 How customizable are the outreach templates for non-US markets? Would love to see it handle cultural nuances better.
Typeless
The useful part here is the context layer. For finding creators who actually fit a niche, knowing why someone matches is way more valuable than getting 500 loose results.
Lessie AI
@yuki1028 Totally. We're trying to make the 'why this creator' part obvious, not just return a long list.
Lessie AI
@yuki1028 Yeah, the evidence Lessie provides means to help users to make a decision, I'm happy to see you find it useful!
minimalist phone: creating folders
Is it something like RocketReach? How the data (+ contact information) for each person are collected?
Lessie AI
@busmark_w_nika Great question! We do cover some of the core capabilities you’d expect from tools like RocketReach — including contact data and enrichment.
Where Lessie goes further is helping you identify the right people to reach out to, not just find contacts. We focus on matching “fit” using AI, and also support tailored email generation and more structured outreach management.
On the data side, we aggregate from multiple providers to ensure compliance and accuracy, and validate results across sources. Happy to share more!
@busmark_w_nika This is interesting! I wonder what methods they use to collect such detailed contact info for each person. Any insights?
Lessie AI
@busmark_w_nika @sarah_jade1 Great question. We use a combination of compliant and accuracy-focused third party contact data providers, together with our own internally built data sources.
A big part of the work is not just collecting data, but cross-checking signals across sources so the results are more reliable and actionable.
Lessie AI
@busmark_w_nika The main difference is that Lessie is besides just “cold emails”, we do more about helping you figure out who’s actually worth reaching out to. It’s designed to handle the matching, prioritization, and even the outreach flow, not just return a single list with outdated data.
DronaHQ
Very interesting for those looking out agentic solutions for sales - congrats on launching!
Will this handle bidirectional sync (with existing CRM) ? Specifically, if a lead is updated in our CRM (say, they are marked "Do Not Contact"), does Lessie's AI agent detect the changes to adjust its own outreach logic?
Lessie AI
@gayatri_sachdeva Great question — and thanks!
We already respect key CRM signals like “Do Not Contact” to avoid conflicts. Full real-time bidirectional sync is something we’re actively working on. Which CRM are you using?
DronaHQ
@libin_yao using a custom CRM we've built in-house on DronaHQ platform
Lessie AI
@gayatri_sachdeva Love this question, this is exactly the kind of workflow we’re thinking about. Today, Lessie can already pick up important signals (like contact restrictions) to prevent unwanted outreach. And deeper CRM sync is something we’re building toward.
Interesting that you mention multi-agent architecture on the site. Does each agent handle a different source like LinkedIn vs Twitter, or is it more about splitting up the research steps?
Lessie AI
@ermakovich_sergey It’s mainly about splitting the research into specialized steps (intent, sourcing, verification, ranking), with some agents optimized for specific sources — so a mix of both
@ermakovich_sergey Good question, it’s more about splitting up the research steps than just assigning one agent per platform.
Just tested it with a real search, looked up Nintendo Switch influencers and the results were actually relevant, not just a generic list of gaming accounts.
That's already better than most tools I've tried, curious how it handles more niche searches though, would 'indie iOS app makers who talk about productivity' surface real micro-influencers, or does it work better with broader categories?
Lessie AI
@misbah_abdel Love that example — appreciate you trying it out!
It actually tends to perform even better on niche queries like that. The more specific (even a bit fuzzy) the intent, the more the agent can surface relevant micro-influencers beyond generic lists.Would be curious what you find if you test that one!
@misbah_abdel thanks for testing, from what I’ve seen, it actually gets pretty interesting with niche searches. Stuff like “indie iOS app makers who talk about productivity” usually brings up smaller builders and micro-creators instead of just big generic accounts.
Agnes AI
For me the best part of this category is prioritization. A ranked list of creators with reasons makes the influencer discovery workflow much easier than a raw directory dump.
Lessie AI
Totally agree — prioritization makes all the difference. We focus on ranking creators by real relevance, with clear reasons behind each result — so it’s not just a list, but something you can act on.
Lessie AI
@cruise_chen Yes, exactly. Prioritization is a huge part of the value here, not just search volume.