CIR: Arrowheads and Circles: Building Self-Evaluating Loops in the Team and in the Product
Presentation: Arrowheads and Circles: Building Self-Evaluating Loops in the Team and in the Product
Abstract: As AI systems take on more real work, the hard problem shifts from producing output to knowing whether to trust it. Large Language Models (LLMs) made generation cheap; they did not make trust cheap. This talk is about building self-evaluating loops around AI, guided by one rule at two levels: no participant grades work it has a stake in. First in the team, in the engineering process, through review by a second model prompted to disprove the first, contracts that check the boundaries between components, and pipelines that allow only one source of truth for each piece of data. Then in the product, inside Orion, a collaborative AI analyst platform whose claims ship with automatic checks, tested against live data and replaced rather than quietly edited when they go stale. Real production results included, failures and all. Attendees leave with a one-afternoon audit they can run on their own systems: which feedback signals actually change what the system does, and which are just decoration.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
Loading virtual attendance info...
- Starts 16 July 2026 11:00 PM UTC
- Ends 27 August 2026 06:00 AM UTC
- No Admission Charge
Speakers
Mr. Abijith Ramachandran
Arrowheads and Circles: Building Self-Evaluating Loops in the Team and in the Product
As AI systems take on more real work, the hard problem shifts from producing output to knowing whether to trust it. Large Language Models (LLMs) made generation cheap; they did not make trust cheap. This talk is about building self-evaluating loops around AI, guided by one rule at two levels: no participant grades work it has a stake in. First in the team, in the engineering process, through review by a second model prompted to disprove the first, contracts that check the boundaries between components, and pipelines that allow only one source of truth for each piece of data. Then in the product, inside Orion, a collaborative AI analyst platform whose claims ship with automatic checks, tested against live data and replaced rather than quietly edited when they go stale. Real production results included, failures and all. Attendees leave with a one-afternoon audit they can run on their own systems: which feedback signals actually change what the system does, and which are just decoration.
Biography:
Abijith Trichur Ramachandran
AI Software Engineer
Gravity
Abijith Trichur Ramachandran earned a BS in Computer Science from Rashtreeya Vidyalaya College of Engineering, India. and a MS in Computer Science from the University of Colorado Boulder. Mr. Ramachandran works as an Artificial Intelligence (AI) software engineer at Gravity, where he builds Orion, a collaborative analyst platform that investigates why business metrics change and delivers the findings to non-technical teams. Mr. Ramachandran has additionally designed Observatory, the layer that turns metric anomalies into a confidence-scored knowledge base, moving the product from reactive Q&A to proactive analysis. Mr. Ramachandran has co-authored a system demonstration paper at ACL 2025, and has mentored engineering students at CU Boulder. Mr. Ramachandran’s research centers on self-evaluating AI pipelines and the systems layer that makes AI products safe to ship.