The address that I use for this newsletter has long since been overrun by nonsense. Seemingly every PR and marketing firm in existence has gleefully added it to the various mailing lists that they use to convince their clients that they offer global reach. I recently received, for example, a message announcing a new uranium mining venture. Yesterday morning, someone helpfully sent me a note to alert me that “CPI Aerostructures Reports Third Quarter and Nine Month 2025 Results.”
Here’s the problem: this is also the address where my readers send me interesting notes about my essays, or point me toward articles or books they think I might like. I want to read these messages, but they’re often hidden beneath unruly piles of digital garbage.
So, I decided to see if AI could solve my problem.
The tool I chose was called Cora, as it was among the more aggressive options available. Its goal is to reduce your inbox to messages that actually require your response, summarizing everything else in a briefing that it delivers twice a day.
Cora’s website notes that, on average, ninety percent of our emails don’t require a reply, “so then why do we have to read them one by one in the order they came in?” Elsewhere, it promises: “Give Cora your Inbox. Take back your life.”
This all sounded good to me. I activated Cora and let it loose.
~~~
I detail the story of my experience with Cora in my latest article for The New Yorker, which is titled “Why Can’t A.I. Manage My E-Mail?”, and was published last week.
Ultimately, the tool did a good job. This inbox has indeed been reduced to a much smaller collection of messages that almost all actually interest me. The AI is sometimes overzealous and filters some messages that it should have left behind, but I can find those in the daily briefings, and nothing that arrives here is urgent business, so the stakes are low.
The bigger question I ask in this article, however, is whether AI will soon be able to go beyond filtering messages to answering them on our behalf, automating the task of email altogether. This would be a big deal:
I’ve come to believe that the seemingly humble task of checking e-mail—that unremarkable, quotidian backbeat to which digital office culture marches—is something more profound. In 1950, Alan Turing argued in a seminal paper that the question “Can machines think?” can be answered with a so-called imitation game, in which a computer tries to trick an interrogator into believing it’s human. If the machine succeeds, Turing argued, we can consider it to be truly intelligent. Seventy-five years later, the fluency of chatbots makes the original imitation game seem less formidable. Yet no machine has yet conquered the inbox game. When you look closer at what actually goes into this Sisyphean chore, an intriguing thought emerges: What if solving e-mail is the Turing test we need now?
Cora, as it turns out, cannot solve the Inbox Game – it can organize your messages, but not handle them on your behalf. Neither can any other tool I surveyed, from SuperHuman to SaneBox. As I go on to explain in my article, this is not for lack of trying: there are key technical obstacles that make answering emails something AI tools aren’t yet close to solving.
I encourage you to read my full article for the entire computer science argument. But I want to emphasize here the conclusion I reached: even with their current constraints, which limit AI-based tools mainly to filtering and summarizing messages, there’s still much room for them to evolve into increasingly interesting and useful configurations.
In my article, for example, I watched a demo of an experimental AI tool that transforms the contents of your inbox into a narrative “intelligence briefing.” You then tell the tool in natural language what you want it to do – “tell Mary to send me a copy of that report and I’ll take a look” – and it writes and sends messages on your behalf. The possibilities here are intriguing!
Here’s how I ended my piece:
“Although A.I. e-mail tools will probably remain constrained…they can still have a profound impact on our relationship with a fundamental communication technology. …Recently, I returned from a four-day trip and opened my Cora-managed inbox. I found only twenty-four new e-mails waiting for my attention, every one of them relevant. I was still thrilled by this novel cleanliness. Soon, a new thought, tinged with some unease, crept in: This is great—but how could we make it better? I’m impatient for what comes next.”
This is the type of AI that interests me. Not super-charged chatbot oracles, devouring gigawatts of energy to promise me wise answers to any conceivable query, or the long-promised agents that can automate my tasks completely. But instead, practical improvements to chores that have long been a source of anxiety and annoyance.
I don’t need HAL 9000; an orderly inbox is enough for now.
