Product Thumbnail

Lightfield

AI-native CRM that builds itself and does work for you

Sales
Artificial Intelligence
CRM

Lightfield reads your emails, meetings, and calls to build your CRM automatically. No manual data entry — ever. Connect your inbox, upload a spreadsheet or CSV from your old CRM, and everything is recreated in less than five minutes. Ask it anything in plain English: who needs follow-up, what objections keep coming up, how has our ICP shifted — answered from your actual conversations. Then put it to work to draft follow-ups, create board decks, build proposals, and more.

Top comment

Hey Product Hunt — I'm Keith, co-founder of Lightfield. Before this, I led Instagram Direct from zero to 500M users and helped build Stories and camera AR. I then co-founded Tome, which launched as #1 on Product Hunt and grew to 20M users.

Of all the products I've worked on, Lightfield has the deepest engagement I've ever seen. It’s an AI-native CRM that builds and updates itself from your real conversations — emails, calls, and meetings. No fields to define. No manual data entry, ever.

Connect your inbox, upload data from a spreadsheet or your old CRM, and you're up and running in five minutes.

One of our early users connected her inbox, typed one prompt — "go through my emails and fill in my opportunities" — and came back to a fully populated pipeline. Stages, contacts, deal context. All built from conversations she'd already had.

Most AI CRMs stop there. Lightfield goes further — it stores every interaction as continuous context, not disconnected records, so the AI sees the full story of every relationship. Then it writes and runs code against that complete memory.

Ask it anything:

  • "What objections keep coming up across all my calls?" — pattern-matched across every conversation you've ever had

  • "How has our ICP shifted in the last 3 months?" — answered from real deal data, not gut feel

Then put it to work:

  • "Draft a re-engagement email for each of my cold prospects" — written with full knowledge of your history together

  • "Build a board-ready pipeline report" — from what's actually happening inside deal

We built this for founders doing their own sales, from our own experience. That's where every company's customer knowledge begins — with the founding team and their first conversations. Lightfield makes sure none of it gets lost. Not when you hire your first rep. Not when you build out a team. Every conversation compounds.

As a thank-you to the Product Hunt community — we're offering 3 months free for anyone who signs up with code PH3. We ask for credit card up front at sign-up to keep bot traffic out, so don’t forget to use the code to get free access.

Try it at https://lightfield.app


Our entire team is on standby to help you get set up. Drop a comment with your first question for the agent — I'll reply to every one.

Huge thanks to @chrismessina for hunting us. We're honored to have the #1 Product Hunter behind our launch.

Comment highlights

Excellent product, been using it for a few months now and it's helped us keep up with the messy sales cycles of early stage life

This app really going to help freelancers alot, like now you don't need to be taken note or even record the chat to remember all that we talked about.

Really interesting idea: a CRM that builds itself from real conversations instead of manual data entry feels like a huge shift for sales teams. Congrats on the launch! How do you ensure the system correctly interprets context from emails and calls without introducing errors into the pipeline? 🚀

Been able to see this team grind it out up close over the past year. Feels like the next gen of CRMs are coming and Lightfield is going to pave the way. Also code execution in Lightfield is crazy good for custom reports after calls

The schema-less approach is really smart — most CRMs force you into rigid data models that don't match how relationships actually evolve. I'm curious about two things:

  1. How does Lightfield handle the "cold start" problem? When you first connect it, does it immediately start surfacing useful insights from existing email/Slack history, or does it need a few weeks of fresh interactions to become valuable?

  2. For solo founders or small teams who wear multiple hats (sales, support, partnerships), does the AI differentiate between these relationship types automatically, or do you need to manually categorize them?

I run a content automation tool and the hardest part of building AI features is making them feel genuinely useful from day one, not just after months of training data. Would love to hear how you tackled that.

ny plans to open source any parts? love the landing page design, really great work.

Proven team, but CRM has a long history of well-funded AI-native challengers hitting the Salesforce/HubSpot wall. The real moat question: does accumulated conversation context create meaningful switching costs, or can a customer export and move on in a day?

Awesome Job Team !!!

This is super exciting. an AI-native CRM that builds itself from conversations” is such a clear framing, and the continuous context model feels like the missing piece between inbox, notes, and pipeline. The examples around objections and ICP drift are exactly the questions founders actually ask but rarely have clean answers for.


Curious how you’re handling the line between insight and action: do most teams stay in the “ask anything” layer, or are you seeing people lean heavily on Lightfield to actually run sequences (re‑engagement, follow-ups, etc.) end-to-end already?

@keith_peiris congratulations on your launch, and your success with your past projects!
Curious how large the context window is? I'm thinking that drawing on such a large bank of client information could lead to important points being compressed and faulty assumptions and inaccuracies being made!

Love the design and approach; proven team.

I appreciate Lightfield's proactivity as well — once I connected my contacts and calendar, it started offering value on Day 1 with meeting pre-caps and client dossiers.

Amazing product, I’ve absolutely loved following the journey! QQ: As a frequent CRM user, one challenge I’ve seen is that even when data is available, teams don’t always trust it or use it for forecasting. How are you seeing Lightfield impact forecast accuracy and confidence across teams?

Interesting concept. Turning conversations directly into a living CRM without manual data entry sounds like a big step forward. How does Lightfield handle incomplete or ambiguous information when building the pipeline from conversations?

Lightfield is one of the best products we’ve used—especially valuable for transitioning from founder-led sales to scalable growth. Congratulations to the team for the PH launch. If anyone is thinking to migrate from Hubspot or other CRM, please go for it. Lightfield will make sure that you will not miss those CRMs.