Rohan Chaubey

Shadow 2.0 - The work your meetings create, done before they end

by
Every online call creates a to-do list. Shadow clears it live. It understands your conversation, tracks what needs to happen, and executes tasks in real time. PDF creation, slide generation, CRM updates, follow-ups, and scheduling before the call ends. Our goal is to have no post-call work. Just stay focused while Shadow handles everything in the background. Starting with core workflows and expanding to everything your calls create.

Add a comment

Replies

Best
Karan Soni

Can Shadow schedule follow ups and send docs on its own, or is there still a human layer present?

Priyansh Agrawal

@soni_karan Shadow understands the meeting context and is helpful enough to takeover much of your workload generated from everyday meetings, alongside, it is careful enough to not execute sensitive tasks, and wait for your approval.

Think metrics brought for you instantly during call,
Mails drafted for you during call,
Calendar events scheduled for you during the call
Notion pages published for you during the call.

Mayank Gupta

@soni_karan here’s still a human layer by design.


Shadow can detect the follow-up, prepare the doc/email, or set up the calendar invite in real time - but the user reviews and approves before anything gets sent or scheduled.


We don’t want AI silently acting on your behalf. We want it to remove the busywork while keeping you in control.


Curious - would you be comfortable with auto-send for low-risk follow-ups, or should approval always stay mandatory?

Shubham Gupta

@soni_karan It does both and goes beyond. Shadow creates Notion docs, drafts emails, books follow-ups, all while you're still on the call. Next up: BI tools, Jira, CRMs. The goal is simple: Give people their time back.

Hersh Singh

Hello Product Hunt 👋

I'm Hersh, founding member at Shadow leading GTM. Wanted to share what we've learned building this.

The pattern:

Over the last six months, I've spoken with hundreds of founders, freelancers, consultants, recruiters, and operators. Different roles, different industries. They all said some version of the same thing.

"The actual call isn't what's killing me. It's everything that comes after."

The follow-up email. The invoice. The doc share. The CRM update. The Notion recap. The next-step Slack message.

A 30-minute call creates 90 minutes of work.

Why this matters now:

We've spent a decade adding tools to capture more of what happens in our calls. Notetakers record it. Notion stores it. Slack notifies the team. Every one of those tools makes you do more after the call ends. Not less.

We started Shadow with one question. What if the work just got done while the call was still happening?

What we built:

Shadow runs on your call, understands what's being asked for, and executes the work in real time.

Someone asks for the doc. The link is in their inbox before they finish the question. Someone asks for the latest numbers. The data is on screen mid-conversation. Someone asks for a follow-up. It's scheduled before you hang up.

By the time you say goodbye, the to-do list is already done.

Who it's for:

Anyone whose day is shaped by meetings. Founders, freelancers, consultants, recruiters, ops leaders, sales teams. If you finish your day with a stack of admin that came from your calls, Shadow is for you.

A question:

If you could automate one thing that happens after every call this week, what would it be? Genuinely curious. The answers might shape what we ship next.


Hersh
Founding GTM

shadowlabs.ai

Mayank Gupta

@hersh_singh Hersh has been closest to the people we’re building this for, and this pattern kept coming up again and again: the call is not the hard part, the work after the call is.

That’s why we’re building Shadow as a real-time layer that doesn’t just capture context, but helps complete the work while the context is still fresh.

Raghav

Can it also help create user stories in productboard automatically? I go over lot of customer calls. I want AI to take my notes and put it in my tools

Mayank Gupta

@raghav39 this is exactly the kind of workflow we want Shadow to handle.

Today, Shadow can capture the notes/action items during the call and turn them into docs, follow-ups, or tasks. Productboard isn’t live yet, but converting customer calls into structured user stories inside product tools is very much on the roadmap.

Curious - would you want it to create raw notes in Productboard first, or directly create polished user stories with problem, context, and acceptance criteria?

Shubham Gupta
@raghav39 eventually yes. We will connect to all the enterprise tools used today to help users get relieved from the busy work
Curious Kitty
For people already using Otter/Fireflies/Granola-style tools, what’s the most common “breaking point” that makes them switch—what specific post-call workflow finally becomes painful enough that a notetaker stops being enough?
Mayank Gupta

@curiouskitty The breaking point we keep hearing is: the summary is useful, but it still leaves the user with another to-do list.

For people using Otter/Fireflies/Granola-style tools, the pain usually starts when the same post-call workflows repeat every day:

  • writing the follow-up email

  • creating the recap/doc/proposal

  • scheduling the next meeting

  • updating CRM/tasks

  • sharing the right collateral

That’s where a notetaker stops being enough. Shadow is trying to move from “here’s what happened” to “here’s the work, already prepared for approval.”

For sales/consulting-heavy users, the biggest switch trigger seems to be follow-ups + proposal/docs + CRM/task updates after every call.

Nuseir Yassin

I have a feature suggestion. What if you could actually record the meeting and then take out the best parts of the meeting and turn it into social media content + schedule that content? I think that would be cool because a lot of consulting calls are essentially you sharing knowledge.

Mayank Gupta

Hey @nuseir_yassin1 , I have been watching your videos from so many years, & I totally love them, just didn't expect at all that you would comment here.

But yes, that’s a really good suggestion, and I agree - a lot of meetings, have useful insights that usually just disappear after the call.

We’re starting with completing action items during the meeting itself, but turning key moments into reusable content is definitely an interesting direction.

Curious - do you think the real value is in creating content from meetings, or in helping people notice the “content-worthy” moments they would normally miss?

Bengeekly

How does this deal with the language switching mid-conversations if we speak multiple languages in the same conversation?

Mayank Gupta

@bengeekly Shadow is built to handle mixed-language conversations by following the actual conversation context, not forcing everything into one language.

So if a call switches between English, Hindi, Spanish, etc., the transcript and action context can still be understood, and the final output can be created in the language that makes sense for the task - for example, an English follow-up email even if parts of the call were in another language.

Curious - when a call switches languages, what matters more to you: accurate transcript in the original language, or clean outputs in one language?

Priyansh Agrawal

@bengeekly try seeing it in action, even we get surprised how smoothly the transcript switches language.

Peter Claridge

Congrats on the launch, folks! Just looking at it from a marketing angle, I think many people would be looking at Shadow AI and thinking: yet another AI notetaking tool.

What would be useful is knowing what makes Shadow AI different? What is the compelling use case that Granola, Fathom, Otter, Fireflies, Loom, and so many others don't provide?


Zoom notes and Gemini notes include action items in their summaries after the email.

A good start is a comparison matrix for people already using these existing notetaking tools on what Shadow AI can do that these other tools cannot.

Mayank Gupta

@peterclaridge this is a very fair point - and probably the biggest thing we need to make clearer.

We don’t think of Shadow as a notetaker. Notetakers capture the meeting, summarize it, and give you action items after.

Shadow is built for what happens during the call: turning those action items into actual work while the context is still live - follow-up emails, docs, scheduling, and eventually CRM/task/tool updates - with the user reviewing and approving before anything goes out.

So the difference we’re betting on is: meetings shouldn’t end with a better to-do list. They should end with the work already done.

Also, +1 on the comparison matrix. That’s a great idea, especially for people already using tools like Granola/Fathom/Otter/Fireflies.

Curious from your marketing lens - which workflow would make this difference most obvious first: follow-up emails, docs, scheduling, or CRM/task updates?

Peter Claridge

@mayank_gupta40 I'm not really sure. Here's a to do list that was generated from a team marketing meeting we had last year, which parts could automated?

  • LN will look over the saved email campaigns and start sending out LinkedIn connection requests to people in the companies starting this weekend.

  • PC will ask ChatGPT to come up with three-point formulas for different personas, such as L&D trainers, executive assistants, and B2B SaaS marketers doing webinars, and turn that into a 30-minute interactive demo presentation featuring Stream Alive heavily, also incorporating AI buzzwords.

  • RR will connect with JV to set up email forwarding and shift notification domain settings, aiming to stop Intercom by tomorrow morning.

  • DL will figure out the next video to work on and send it by tonight.

  • PC will check if the tidy cal link that has been sent so far is working and take another screenshot to show both mugs in the email.

  • The group will communicate to people signing up for events that they will receive a recording if the timing is not convenient and provide a link to past recordings.

  • DL will ask PR to get more thumbnails for the Luma events listing if needed.

  • TL will mention to JV that he needs to sit with RR soon regarding the domain settings.

  • The group will define a clear procedure for who will reply to customer service messages and how to avoid duplication of effort, also checking if Feature Base has a mobile app.

  • PC will talk about Feature Base and its full pricing page in the newsletter, also discussing any talkable moments from the week.

  • PC will put an event on LinkedIn.

  • LN will post the video on LinkedIn today from his profile, while DL will repost it from the Stream Alive page on Monday, along with optimizing text and hashtags for each platform.

  • TL and PC will coordinate on the number of people with monthly plans.

Mayank Gupta

@peterclaridge this is a great example.

Most of these can be automated at least to the “ready for approval” stage. For example:

  • Draft the LinkedIn outreach copy + target list

  • Create the demo/presentation outline from the discussion

  • Draft emails/messages to JV, PR, event signups, etc.

  • Create tasks with owners and deadlines

  • Schedule the RR/JV follow-up

  • Create the SOP/procedure doc for customer service replies

  • Draft the newsletter section and LinkedIn post

  • Push tasks into tools like Linear/Jira/Notion/CRM once connected

A few things like changing domain settings or actually sending LinkedIn requests should probably stay approval-based or be handled through integrations.

So the way we see it: Shadow shouldn’t just say “here’s the to-do list.” It should convert each item into the next best action - draft, task, doc, calendar event, or tool update — and let the user approve.

Peter Claridge

@mayank_gupta40 @shubham16180 You should put a variation of those meeting notes on your website and say "this is what traditional meeting apps tell you" and then show what shadow ai can automate with the output as well.

Shubham Gupta

@peterclaridge Totally respect the notetaking tools, they're great at what they do.

But there's a difference between a tool with ears and one with hands and legs.

Notes tell you what happened. Shadow gets the work done. Yours to choose. 😄

Peter Claridge

@shubham16180 I think you need to define what kind of meetings these things that get automated actually occur in and message accordingly. See my reply to @mayank_gupta40 which is typical of the kind of to-dos that get generated in a company team meeting.

On the other hand, client meetings might require a follow-up call, or a link to be sent, or a document to be shared.

Shubham Gupta

@mayank_gupta40  @peterclaridge Thanks for your thoughtful response! Let me go through the above comment and circle back

Naitik Kapadia

Turning calls into completed work instead of just notes is a big shift.

If execution during the call works reliably, this could be a game changer.

Mayank Gupta

@naitik_kapadia exactly - reliability is the whole game here.

The shift only matters if Shadow can understand the right action, prepare it with context, and still keep the user in control before anything is sent, created, or scheduled.

That’s why we’re starting with high-frequency workflows like follow-up emails, docs, and scheduling before expanding deeper into CRM/task updates.

Curious - from a product perspective, what would make you trust execution during the call: approval before every action, clear action previews, undo/edit controls, or better integrations?

Shubham Gupta

@naitik_kapadia Hey Naitik, just imagine, you get off a call with nothing to do. All the major items, already done or drafted!

Philip Kubinski

from a sales team perspective - what would be awesome is actually gather all the knowledge from these calls (and tasks) into one place where the whole sales team (especially onboarding people) could learn from. I mean - AE (let's call him John) might have the best way of preparing proposals -> it should be spread across the team.

not sure if it's not too specific of a use-case but thought I'd share it.

anyway - cool work you're doing!

Mayank Gupta

@philip_kubinski this is not too specific at all - it’s actually a really strong sales use case.

A lot of the best knowledge in a sales team lives inside calls: how someone handled an objection, framed pricing, prepared a proposal, or moved a deal forward. The problem is that it usually stays with that one AE.

This is exactly the kind of direction we want Shadow to move toward: not just completing the task from one call, but helping turn repeated patterns into shared team knowledge.

Curious - would this be more useful as a searchable sales knowledge base, or as proactive suggestions during the next similar call?

Shubham Gupta

@philip_kubinski We hear this pain everyday. Team features are on the roadmap & not just a shared learning platform, but the ability to set playbooks, tweak the answers reps should give, and have Shadow deliver real time guidance on the call.

Gong does this pathetically. The feedback cycle is brutal: listen, analyse, iterate, wait for results. That's a 3 month loop. By the time you have answers, the market has moved.

We will close that loop to zero. Pain well noted, and you'll be hearing from us. 😄

Ajeet Shah

This looks nice.

Seems like we don't need to create MOMs (minutes of meetings) and To-dos after calls.

Will it generate MOMs as well? Or maybe MOMs are no longer useful today?

(MOM = summary or minutes of a meeting)

Mayank Gupta

@iamajeets yes - Shadow can generate MoMs/meeting summaries too.

But we think the bigger shift is that MoMs should become more actionable. A summary is helpful, but the real work starts when decisions need owners, follow-ups need to be sent, and next steps need to move into the right tools.

That’s where Shadow is focused: turning the meeting into ready-to-review work before the call ends.

Curious - what would make a MoM truly useful for your team: better decision tracking, owner/deadline detection, automatic follow-ups, or pushing tasks into your existing tools?

Ajeet Shah

@mayank_gupta40 It seems like if we sort out actions well, MOMs won't be a priority. Actions > MOMs. Thanks and congratulations!

Mayank Gupta

@iamajeets This is super helpful. Thanks !

Shubham Gupta

@mayank_gupta40  @iamajeets Yes, solving actions has to be done very deliberately. Not an easy problem to solve