Speakers: Vighnesh Deshpande (Vivanti Consulting)
Track: AI Engineering
Most production AI guidance assumes you want consistency: pin the prompt, lower the temperature, eval for drift. But a whole class of enterprise use cases - idea generation, recommendation, exploration, synthesis - is worthless if the output is predictable. The engineering problem flips: how do you make variance useful, keep it safe, and convince a governance function that a system with no single right answer is still under control?
This talk is the build story of a production AI concept-generation pipeline. I'll cover the concrete decisions: constraining the shape of outputs with strict schemas while leaving the content free; grounding generation in competitive and regulatory data so novelty stays feasible; designing a three-stage human funnel (expert weighted scoring, swipe-based crowd screening, review loop) that turns volume into a shortlist.
The evaluation approach when there's no ground truth - measuring diversity, feasibility, and survival-through-funnel instead of correctness.
https://data.webdirections.org/ai-engineer-sydney/sessions.json#c3b36efa-9a99-44c6-ae31-b8c9fe242dd2
Full text on webdirections.org
.