System One models reshape custom agent harnesses
The takeaway is that pairing a fast decision model with a reasoning model gives builders lower token costs and more predictable agent behaviour than either alone. Developers building agent harnesses can follow the linked guide to try Jev and CLM directly and compare their trade-offs in speed versus verification quality.
Elvis Saravia of dair.ai argues that System One decision models like Jev and the Contrastive Language Model (CLM) make custom agent harnesses far more effective than System Two models alone.
CLM is 9x faster than Jev and appears to be a stronger verifier on long-horizon tasks.Jev is trained with Reinforcement Learning for Calibrated Decisions (RLCD) and returns typed decisions with probabilities, while CLM embeds situations and candidate actions, then ranks the best match.
Saravia links a hands-on guide on combining the two model types at academy.dair.
ai.
Own your harness, folks. I feel like System One models take custom agent harnesses to a whole different level. It's not a surprise. This comes down to needs that haven't been met with System Two models alone. A need to be in control of your intelligence stack. A need for more reliable agents. Combining System One and System Two models is way better than just relying on one alone. A need for richer agent experiences (more personal and proactive agents). A need to squeeze out more value per token used. You can check my most recent guide on building a custom harness with Pi and Jev to learn more: academy.dair.ai/resources/jev-… But let's not stop here. I expect a new wave from frontier labs pushing decision models further. And even better tools to build even more customized decision models on top. There are more layers to this. This is great news for us builders and an incredible opportunity for those who specifically build custom harnesses. elvis @omarsar0 Pay attention to this new wave of System One models if you are building custom harnesses. First Jev. Now, Contrastive Language Model (CLM). CLM is 9x faster than Jev. CLM seems to be a better verifier than Jev, particularly at long-horizon tasks. How do Jev and CLM differ? CLM is contrastive, and Jev is trained with Reinforcement Learning for Calibrated Decisions (RLCD). Jev receives a situation plus predefined questions, and returns typed decisions with probabilities. CLM embeds the situation and candidate actions, compares their similarity, then ranks or selects the best match. The point is that there are several ways to attack this problem, which is exciting. You can see my recent guide on combining System One and System Two models for building custom harnesses. academy.dair.ai/resources/jev-… 🔗 View Quoted Tweet📊 44 ⚡
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include agents, Jev, CLM, decision models.
Source attribution: curated from elvis (@omarsar0).
