LO
PilotCognitive automation2025-07-25
At an IT consulting firm, LLM-drafted requirements saved an analyst 10–15% of drafting time but missed user stories whose knowledge was tacit, and could not replace the analyst
Junior software developeroccupation page →
Event date / reported
2025-07-25
Evidence stage
PilotSmall-scale trial in a real setting. Tells us the deployment conditions are being tested, not that they hold — so one pilot is never enough on its own; two independent ones are.
Tasks this bears on
Turning a vague request into a spec
Asking the questions that reveal what should actually be built.
Still human-led≈ Platform inference
Where this applies
A university study of language models drafting requirements specifications on one project at an IT consulting company, assessed by the company's expert analyst. A subset of user stories stayed unaddressed across all models because the knowledge analysts hold can be tacit and not written in the elicitation documents; the analyst estimated drafting time savings of 10% to 15%, and the authors conclude the models can help early documentation but cannot replace human intervention. It is one project with one expert, and the role studied is requirements analyst rather than developer.
What this means
Drafting a specification can start from a machine draft, but what makes a request buildable — the knowledge nobody wrote down — stays with the person who asks the questions.
What it does not yet show
One project and one analyst; it does not show how juniors work on requirements or anything about hiring.
What you can check
Open arXiv:2507.19113 and find "Overall, LLMs can enhance productivity in the early phases of documentation and definition of requirements but cannot replace human intervention".
Does it change the assessment?
No. The impact index is never moved by a single event, and this stage does not move one on its own: a "Pilot" record counts toward a judgement but needs a second, independent record before the judgement rests on evidence. This one is counted; on its own it changed nothing.
Source
Pasquale, Ragone et al. (University College Dublin, University of Bari) — "Exploring the Use of LLMs for Requirements Specification in an IT Consulting Company", arXiv:2507.19113 (25 July 2025) · verified 2026-09-27 · Claude (VOLO agent) · interpreted 2026-09-27 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.