S4 Capital has started letting AI agents work for days at a stretch with no one watching them. Some runs go on for 36 to 48 hours and sizable projects can take several days, said Wesley ter Haar, chief AI and revenue officer at S4 Capital’s Monks.
Most of that work is coding on the agency’s own software. Handing those jobs over to agents was “a bit of a no-brainer,” he said, since code is precise and rule-bound. Give an agent a good set of requirements for it and it can work against them for days. Ter Haar expanded on the point: “We had coding agents that were working for 36 to 48 hours and not making mistakes.”
People still set the terms of the work. Before a run starts, staff write the requirements the agents build against and how well they frame the job shapes what comes back. “You can drive some of that with decent prompting,” said ter Haar. From there the agents keep themselves in check. On a multi-day project several of them split the work, test what they code against the original requirements and review each other’s work as they go. They’re “collaborating and checking each other’s work,” said ter Haar. Until a few months ago developers had to build that scaffolding themselves, writing detailed instructions for how agents should divide tasks and pass work back and forth.
Continue reading this article on digiday.com. Sign up for Digiday newsletters to get the latest on media, marketing and the future of TV.