Platform Aeronaut Transcripts: Earnings Transcripts, Decks & Summaries in One Place | PA Dispatch No. 11
A quick view of this week’s shifts in platforms, valuations, and AI adoption. Numbers, context, and curated reads you can use.
Earnings season is a scavenger hunt: transcript here, deck there, Q&A buried, calendar in a different tab. For awhile I’ve had a tool I made that automatically captures and summarizes earnings call transcripts. There’s no replacement for listening to the call yourself and taking notes, but sometimes the ability to look across sectors and to companies you’re only mildly interested in makes summarization helpful.
I’ve taken that personal tool and productized it into a full fledged website: Platform Aeronaut Transcripts to help ease that scavenger hunt.
What it is
Platform Aeronaut Transcripts is a workflow-first research site focused on public-company earnings calls that provides one place to monitor what’s new, read the call, skim a structured summary, grab the deck, and track what’s next.
At a high level, it’s one place to:
Read and search transcripts in a clean format
Use structured AI summaries as a fast first-pass
Pull up the slide deck without hunting
Monitor upcoming earnings dates
Compare communication patterns across companies / execs / analysts
I’ve already built out 70+ companies, 1,400+ transcripts and 800+ summaries and growing.
Why I built it
Two reasons: one practical, one philosophical.
Practical: time and focus are the scarce resources.
The raw materials (transcripts, decks, dates) are abundant. The friction is in retrieval + formatting + cross-referencing. If you cover a basket of companies, the meta-work becomes its own job.
Philosophical: the edge is rarely “having the transcript.”
It’s being able to track narrative and intent over time and to separate what management said from what the market heard. That only happens when your workflow is consistent enough to notice the deltas.
How to use it (3 simple workflows)
Homepage → Company Page → Calendar
1) The “morning scan”
Open the homepage, and use it like a dashboard:
What new transcripts dropped?
What new AI summaries are available?
What calls are coming up next?
Any new decks worth pulling?
This is the “don’t make me think” entry point. The goal is to replace the mental overhead of “where should I look today?” with one page (for those who don’t have Bloomberg)
2) The “Company Page”
Every company page is designed to answer three questions immediately:
What just happened?
What’s next?
How has the stock moved on prior earnings?
From there, the company page becomes your hub: event history, links to the transcript, AI summary, and the deck (when available), plus a quick way to contextualize the market’s reaction.
3) Personalization: Make it Yours (Watchlist + Alerts)
If you want the site to work “for you” instead of you checking it manually, log in and build a watchlist. Your watchlist powers the calendar filters and alerts do you don’t have to check manually.
From there you can enable alerts for new transcripts and new AI summaries and choose immediate, daily digest, or both.
The daily digest is designed to be a predictable “earnings inbox” that shows up on schedule and lets you plan your day.
The Fun Stuff
Statistics
Now that I have a giant database of transcripts, executives, Q&A, and other details I can compile statistics. There’s a lot of heavy lifting to do and I’ll continue to flesh this out, but for now I have tagged stats like what % of time is an executive’s Q&A response evasive vs a partial answer vs direct?
Login Using Your Substack Subscription
If you’re a Platform Aeronaut substack subscriber, you already have access. With all of the work put in I decided to gate the AI summaries and the presentations into behind a login.
At the pop-up just type in the same email you’ve subscribed to my substack with and you’ll get a magic link email to login, no additional effort required. If you’re not a subscriber simply subscribe and you’ll get automatic access. This is part growth hack and part a gut feeling of wanting some sort of reward for the effort put in. Call it a perk, if you support me you get the parts that take the most work.
User Requests
Coverage is never perfectly complete. So instead of emailing me “can you add X” or “can you summarize Y,” the site has visible request flows to request a new company coverage or request specific AI summaries when the transcript exists but the summary doesn’t yet. There’s a little bit of manual tagging required for new companies are first added, but I’m continuing to add names.
Roadmap
Next plans include something I’m really excited about: a transcript and summary MCP server that you can plug into ChatGPT or Claude. Rather than doing the heavy lifting myself and setting up a full AI chat interface into the website, I’m working on a server anybody can use that can do full expansive analysis across transcripts and time periods and companies while offloading the inference costs to your existing ChatGPT subscription.
There’s also some data quality issues around event dates for some tickers that I’m still working out, but if you notice anything obvious let me know.
Performance & Valuation Snapshot
Note: Email renders these as images, click through for interactive filters or view on Platform Aeronaut.
What I Read This Week
Marriott says Google’s “AI Mode” will process hotel bookings: First major hotel chain to discuss building with Google’s agentic booking tools.
DoorDashers paid to close Waymo robotaxi doors: New Atlanta pilot pays nearby couriers to shut doors so vehicles can depart.
Tripadvisor flags AI Overviews drag: CEO says changing search (AI summaries) is pressuring traffic; options on the table.
Waymo unveils 6th-gen robotaxi stack: Fewer cameras, upgraded lidar/radar; targets high-volume production and scaling.
Uber Eats adds “Cart Assistant”: AI builds a grocery cart from a text or photo list; launches with major U.S. grocers.
TikTok launches “Local Feeds” in the U.S.: Opt-in, GPS-based feed for nearby travel, dining, events and shopping content.
Coveo launches a Hosted MCP Server: Enterprise-grade MCP hosting to wire LLMs into systems with governance.
Chesky: Airbnb’s native AI is a moat: CEO argues rivals’ chatbots are copyable; building AI deep into product is harder to replicate.
Recent Posts
The information presented in this newsletter is the opinion of the author and does not reflect the view of any other person or entity, including Altimeter Capital Management, LP (”Altimeter”). The information provided is believed to be from reliable sources but no liability is accepted for any inaccuracies. This is for informational purposes and should not be construed as investment advice or an investment recommendation. Past performance is no guarantee of future performance. Altimeter is an investment adviser registered with the U.S. Securities and Exchange Commission. Registration does not imply a certain level of skill or training. Altimeter and its clients trade in public securities and have made and/or may make investments in or investment decisions relating to the companies referenced herein. The views expressed herein are those of the author and not of Altimeter or its clients, which reserve the right to make investment decisions or engage in trading activity that would be (or could be construed as) consistent and/or inconsistent with the views expressed herein.
This post and the information presented are intended for informational purposes only. The views expressed herein are the author’s alone and do not constitute an offer to sell, or a recommendation to purchase, or a solicitation of an offer to buy, any security, nor a recommendation for any investment product or service. While certain information contained herein has been obtained from sources believed to be reliable, neither the author nor any of his employers or their affiliates have independently verified this information, and its accuracy and completeness cannot be guaranteed. Accordingly, no representation or warranty, express or implied, is made as to, and no reliance should be placed on, the fairness, accuracy, timeliness or completeness of this information. The author and all employers and their affiliated persons assume no liability for this information and no obligation to update the information or analysis contained herein in the future.