Shadow
Real-time AI for smarter calls and faster follow-ups
741 followers
Real-time AI for smarter calls and faster follow-ups
741 followers
Shadow is a real-time AI wingman for high-stakes calls.
It helps you ask better questions, never miss key details, and turn every conversation into clear next steps—while the call is still happening.
This is the 2nd launch from Shadow. View more
Shadow 2.0
Launching today
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.
Free Options
Launch Team / Built With
Shadow
Hi Product Hunt 👋
Shadow is a real-time AI on the call that completes your post-call to-dos while you're still on the call
The problem: A user told us something we couldn't ignore:
We did the maths. 5 calls a day. 20 minutes of post-call admin. 5 days a week. That's 8+ hours — one full working day — lost to busywork, every week.
The solution: Shadow was already on the call. It already had the context. So we asked: what if it just handled the to-dos before you hung up?
While you're still talking, Shadow detects action items in real time and executes them. Today, that means:
📝 Notion doc creation: notes and summaries written as you speak
📅 Follow-up meeting scheduling: booked before you hang up
📧 Draft email: written automatically based on what was discussed
Coming soon: Slack, Salesforce, Jira, Google Sheets, PostHog, GitHub, LinkedIn, Twitter and more. This is just the start.
What's new in Shadow 2.0: We've moved from a browser app to a native desktop app.
Shadow now:-
Auto-detects your meetings the moment they start, no manual setup
No bot joins your call, invisible to everyone else. It just works.
Who is it for? If you live on calls, sales, consulting, recruiting, ops, Shadow was built for you. Anyone who goes over back to back calls.
One question, If you could automate one thing that happens after every call, what would it be?
Drop it below, it might be the next thing Shadow handles.
Shubham
Co-Founder, Shadow
shadowlabs.ai
Shadow
@shubham16180 Shubham said it perfectly.
We’re building Shadow because post-call work shouldn’t wait until after the call - the context is already there while the conversation is happening.
Today it handles emails, Notion docs, and scheduling in real time. The bigger vision is to let people leave calls with the actual work already done.
Shadow
@shubham16180 One of the problems every industry, every professional role relates to.
As a dev, I hate updating tickets, creating tickets, Productivity tracking platforms had become counter-productive for me.
@shubham16180 Many congrats Shubham, Hersh and team! :)
How I met the makers?
I first came across Shadow through the @Velo team and the moment they walked me through what they’re building, my first thought was: “Wait… was this made for me?”
What is Shadow?
Shadow is a real-time AI agent that sits on your calls and turns conversations directly into done tasks (notes, follow-ups, docs, and next steps) before the meeting even ends.
As someone running a high-demand consulting business, I spend ~7 hours a day on calls and spoke with 1,300+ founders last year. After every call, I usually spend another 15–30 minutes processing notes, sending follow-up emails, and organizing next steps.
Why I endorse it?
A tool like Shadow doesn’t just sound useful, it feels like getting a full working day back every week.
I’ve also had the chance to work closely with the team on feedback ahead of launch, and they’ve been incredibly fast, agile and obsessed with getting better.
That combination of a sharp product and a hungry, execution-focused team is exactly why I’m excited to endorse both Shadow and the ambitious makers building it! :)
Shadow
@rohanrecommends This genuinely means a lot, Rohan. Thank you.
The "was this made for me?" moment is exactly what we've been building towards. We started Shadow because a user told us she felt like a robot running endlessly between calls. That stayed with us.
7 hours a day on calls, you feel this more than most. The fact that it resonates with someone who's lived this problem at that scale means we're on the right track.
Really grateful for your trust, your feedback, and for being part of this journey. This is just the beginning.
Shadow
@shubham16180 @rohanrecommends this means a lot - especially coming from someone who lives on calls and has felt the follow-up pain firsthand.
Your feedback before launch genuinely helped us sharpen what Shadow should do: not just record or summarize meetings, but actually turn the conversation into completed work before the call ends.
Curious - from all your calls with founders, what’s the one post-call task you think wastes the most time: follow-up emails, notes, scheduling, or sharing docs?
Shadow
@shubham16180 @rohanrecommends
Thanks a ton Rohan!
That moment you mentioned that our product was made for someone like you truly put a smile on our faces.
It validated that this is a problem that needs solving.
We appreciate your feedback and thanks for joining us on this ride. We're just getting started!
Visla
@shubham16180 There are a lot of tools that do this currently, Krisp, Granola, etc...you get the idea.
But I love the immediate integrations that Shadow offers, nobody lives inside of just 1 tool, so this is very helpful! Good luck!
Shadow
@mogabr Totally agree - there are already a lot of tools in this space.
The part we’re trying to push harder on is not just capturing what happened, but helping get the actual work done across the tools people already use. Because yeah, nobody lives in just one app.
Appreciate you checking it out - curious, which integrations would make this most useful for your workflow?
@mogabr @mayank_gupta40 I like the way you phrased this a lot. You aren't building a tool that everyone needs to adjust their workflow around but instead trying to accommodate and integrate with the tools people already have. Your already on the meeting might as well have a tool that can do a lot of the follow up work automatically instead of just being a note taker. Also "Shadow" is a great name by the way.
Shadow
@mogabr @blaize_olle Thanks. Super helpful, what you just mentioned.
Shadow
@mogabr Solving note-taking vs reducing work load in real time are two different problems is how we look at it. Everything from product building, ux, and architecture changes from that.
Shadow
@mogabr The way I see it, those tools solve better note-taking. We solve on-call actions. Two very different problems, UX, architecture, and roadmap. Looks similar on paper, excruciatingly different in execution. They provide ears, we provide brains and limbs to take action live.
DiffSense
How is this different than the other AI meeting assistants? whats the differentiator? The innovation? The novelty? :D How does it stand out from the 1000s of live meeting HUD AI systems for meetings? Sorry for the roasty question. but you asked for it so here it is 😸
Shadow
@conduit_design Sharing an analogy, one of our users gave,
"I have been paying salary to AI assistants that only had ears, finally something that comes with hands and legs... getting work done is what was needed, not dumping notes"
DiffSense
@priyansh_agrawal2 Okay i'll bite. What type of work can it complete?
Shadow
@conduit_design fair question - and probably the right roast 😄
The way we think about it: most AI meeting assistants are built around capture - record the call, summarize it, extract action items, and give you something to process after.
Shadow is built around execution during the call.
So instead of ending with “here are your action items,” Shadow helps complete them while the context is still live - draft the follow-up email, create the doc, schedule the next meeting, prepare the next-step task - with the user reviewing/approving before anything goes out.
The novelty isn’t “AI understands meetings.” The bet is: meetings should end with the work already done, not with another to-do list.
Curious - what would make this feel truly different for you: acting during the call, approval before execution, deeper tool integrations, or better context from past meetings?
DiffSense
@mayank_gupta40 Okay so the promise land is doing work before the meeting is over. so not actual work more like meeting assistant chors. like 1 creating summary,2. sending followup meeting emails, 3 prep todo lists of meeting context but lots of meeting AIs handle all that already. Otter, Fireflies, Avoma, even zoom does this now ref this breakdown: https://gist.github.com/eonist/24988ce06104f8ed627e219381aa8c23 . What makes shadow different? Im asking because this is crucial to get right. Users only convert to new users if they can clearly understandhow your product makes their life better. If they cant clearly understand that, no conversion happens. Right now your not making your differentiator clear for that to happen. You know what I mean? only trying to help here. product communication is tricky!
Shadow
@conduit_design you’re right - and I think our earlier explanation made Shadow sound too close to the existing “summaries + action items + follow-up drafts” category.
The difference we’re aiming for is more specific:
Most meeting assistants work like this:
meeting → transcript/summary → action items → user does the work later
Shadow is built to work like this:
meeting → detects the action live → prepares the actual output → user approves → work is done before the call ends
For example:
“Can we track this bug?” → Shadow creates a Jira ticket with title, description, priority, owner, and acceptance criteria
“Let’s send them an NDA” → Shadow drafts the NDA from the right company template, fills in the customer details, and prepares it for approval
“We need a contract for this scope” → Shadow creates a first draft from the approved template with scope, pricing, timeline, and terms discussed on the call
“Let’s meet next week” → Shadow creates the calendar invite before the call ends
“Send me the proposal” → Shadow drafts the email and attaches/shares the right doc
The important part: Shadow doesn’t silently act on its own. The user reviews and approves before anything is sent, created, or scheduled.
So the differentiator is not transcription, summaries, or action-item detection. Those are table stakes now.
The differentiator is: turning live meeting intent into approved execution inside your tools before the meeting ends.
DiffSense
@mayank_gupta40 Gotcha. so its the "one-click approval before hangup" thats the real differentiator. why didnt you just say that to begin with? That really neat! I could find only one true competitor: Acta.ai full breakdown analysis: https://gist.github.com/eonist/ee31b95c63c1281f30566519755a7f2a
Shadow
@conduit_design fair roast!
Most tools are just Voldemort's diary: Self-writing, forever. We're building a chief of staff.
They're stuck at note-taking. We're solving getting work done. 😄
Product Hunt
Shadow
@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.
StreamAlive - Interactive PPT slides
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.
Shadow
@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?
StreamAlive - Interactive PPT slides
@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.
Shadow
@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.
StreamAlive - Interactive PPT slides
@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.
Shadow
@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. 😄
StreamAlive - Interactive PPT slides
@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.
Shadow
@mayank_gupta40 @peterclaridge Thanks for your thoughtful response! Let me go through the above comment and circle back
Nice concept. But what about privacy and human in the loop?
My question comes from the POV of different types of calls that could happen.
For eg, I do not want my sales numbers to be broadcasted to people just yet even though they were discussed in the meeting. Are there required settings that can enable/disable on-call actions?
What I want to essentially a queue of tasks that I could review and control before they are dispatched for action across different teams/people.
Also, can I add an existing knowledge base to the tool so that the actions could be enhanced. For eg. Instead of sending a meeting invite for the next meeting, enhance the engagement by also sending a company presentation or latest trends in the industry.
Shadow
@kaushal_bundel this is exactly the right way to think about it.
Shadow should not blindly execute everything it hears on a call. The model we believe in is:
call → proposed actions → review queue → user approves → action goes out
So if sales numbers, pricing, internal context, or anything sensitive comes up, it should not be automatically broadcasted. The user should be able to review, edit, reject, or approve actions before they are sent to anyone or pushed into tools.
And yes, the knowledge base point is a big part of the product direction. The goal is not just “schedule the next meeting,” but to make the action smarter using company context - for example, attach the right deck, include relevant case studies, or add industry trends based on who you’re speaking with.
So the two principles are:
Human-in-the-loop by default
Company context to make actions more useful
Curious - would you want controls at the workspace level, or per action type, like emails can auto-draft but external sharing always needs approval?
@mayank_gupta40 It depends on the profile, if I am building for enterprise then the context is very different than what I am making for freelancers/Single business owners etc. Also the "shared context", like slack, email or a calendar schedule will play a part here.
So what is your target customer at this point in time?
Shadow
@kaushal_bundel completely agree - context changes a lot by customer profile.
Right now, our sharpest focus is on people who live in back-to-back external calls where follow-up work matters: founders, sales teams, consultants, recruiters, and operators.
Within that, GTM/sales teams are the strongest initial use case because the post-call work is very repetitive and high-value: follow-up emails, proposals, docs, next meetings, CRM/task updates, etc.
And yes, shared context is key. Shadow becomes much more useful when it understands the team’s docs, emails, calendar, CRM, Slack, and past meeting context - not just the current call.
So the direction is: start with high-frequency meeting workflows, then make execution smarter with company/team context.
@mayank_gupta40 Great!. Glad to hear this.
All the best!!
Velo
This is actually super relatable 😅 every call quietly turns into a mini to-do list.
Love the idea of handling things during the call instead of after. Curious how well it picks up on action items in meetings with larger groups (>10 people)
Shadow
@ajaykumar1018 Hey Ajay, really glad it resonates!
Great question, larger group calls are something we're actively working towards. Right now Shadow works best in smaller focused calls, but scaling it up is on the roadmap. Would love to keep you in the loop as we get there!
Shadow
@ajaykumar1018 exactly — that “mini to-do list after every call” pain is what pushed us to build this.
For larger groups, we’re focusing on picking up clear ownership, decisions, and next steps without turning every discussion point into noise.
Curious - in your experience, do action items get missed more in large internal meetings or customer calls with multiple stakeholders?
Shadow
@ajaykumar1018 Hi Ajay, glad to hear you resonate
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
Shadow
@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?
Shadow