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 straight influence guide gross sales and reveal promotional methods price 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 rapidly turns into unsustainable.
I not too long ago 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 bought essentially the most consideration. The primary aim was to comply with what she stated about her guide, 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 vital posts.
However by the second abstract, some limitations turned obvious. Sorted by likes and impressions with generic summaries, each LinkedIn submit was receiving the identical remedy. I had solved the knowledge overload downside however now wanted a solution to extract strategic perception.
To repair this, I labored with Claude to show the immediate into one thing nearer to an agent with primary decision-making authority. I gave it particular targets and resolution standards aimed toward shedding mild on promotional patterns that aren’t at all times simple to comply with, not to mention analyze, in a flurry of posts: autonomously choose 10–15 precedence posts per week, prioritizing direct guide mentions; examine present efficiency towards historic baselines; flag uncommon engagement patterns (each optimistic and detrimental); and mechanically regulate evaluation depth primarily based on how posts are performing.
The brand new report now offers deeper evaluation centered totally on posts mentioning the guide, not simply any common submit, together with strategic suggestions to enhance submit efficiency as a substitute 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 resembling posting brief video clips associated to guide chapters or incentive-driven posts.
The report isn’t excellent. 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 knowledge I’d in any other case should get manually (and presumably overlook), and it’s starting to supply a place to begin for understanding what has labored in Bridget’s promotional program. Over time, with additional work, these insights could possibly be shared with the creator to plan promotional campaigns for brand new books, or integrated 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 leads to 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 invaluable focus is present in constructing options that tackle your particular issues utilizing these new instruments—no matter you may name them.