As an acquisitions editor at O’Reilly, I spend appreciable time monitoring our authors’ digital footprints. Their social media posts, talking engagements, and on-line thought management don’t simply replicate experience—they immediately impression e-book gross sales and reveal promotional methods value replicating. Not surprisingly, a few of our best-selling authors are social media experts whose posting output is staggering. Maintaining with a number of superposters throughout platforms shortly turns into unsustainable.
I just lately constructed an AI answer to handle this problem. Utilizing Relay.app, I created a easy workflow to scrape LinkedIn posts from one creator (let’s name her Bridget), analyze them with ChatGPT, and ship me weekly electronic mail summaries about her posts and which received essentially the most consideration. The primary objective was to comply with what she mentioned about her e-book, adopted by thought management in her discipline. The setup took 5 minutes and labored instantly. No extra periodically reviewing her profile or worrying about lacking necessary posts.
However by the second abstract, some limitations grew to become obvious. Sorted by likes and impressions with generic summaries, each LinkedIn submit was receiving the identical therapy. I had solved the knowledge overload downside however now wanted a method to extract strategic perception.
To repair this, I labored with Claude to show the immediate into one thing nearer to an agent with fundamental decision-making authority. I gave it particular targets and determination standards aimed toward shedding gentle on promotional patterns that aren’t all the time straightforward to comply with, not to mention analyze, in a flurry of posts: autonomously choose 10–15 precedence posts per week, prioritizing direct e-book mentions; examine present efficiency towards historic baselines; flag uncommon engagement patterns (each constructive and damaging); and routinely modify evaluation depth based mostly on how posts are performing.
The brand new report now gives deeper evaluation centered totally on posts mentioning the e-book, not simply any standard submit, together with strategic suggestions to enhance submit efficiency as an alternative of “this had essentially the most likes.” Suggestions are sorted into short-term and long-term promotion concepts, and it has even proposed testing novel methods corresponding to posting quick video clips associated to e-book chapters or incentive-driven posts.
The report isn’t good. The historic evaluation isn’t fairly proper but, and I’m engaged on producing visualizations. On the very least, it’s saving me time by automating the supply and evaluation of data I’d in any other case should get manually (and probably overlook), and it’s starting to offer a place to begin for understanding what has labored in Bridget’s promotional program. Over time, with additional work, these insights may very well be shared with the creator to plan promotional campaigns for brand spanking new books, or included into bigger comparisons of promotional methods between authors.
Whereas engaged on this, I’ve requested myself: Is that this an AI-enhanced automated workflow? An agent? An agentic workflow? Does it matter?
For my functions, I don’t assume it does. Typically you want easy automation to seize data you may miss. Typically you want extra goal-directed, versatile evaluation that ends in deeper perception and strategic suggestions. Extra of a useful assistant working behind the scenes week after week in your behalf. However getting caught up in definitions and labels could be a distraction. As AI instruments change into extra accessible to everybody within the office, a extra priceless focus is present in constructing options that deal with your particular issues utilizing these new instruments—no matter you may name them.