PostHog has demonstrated that decision models can be up to 444.6 times cheaper and 193.6 times faster than frontier models for simple tasks. In its Replay Vision product, the company utilizes targeted yes-or-no queries to stop 98.7 percent of clean session summaries from reaching Gemini. Teams adjust probability thresholds depending on whether missing sensitive data poses a risk or unwarranted interruptions must be prevented. To handle shifting calibration requirements across different model updates, the company built an internal AI gateway to benchmark models against hand-labeled data.
Key points
Decision models provide structured typed answers alongside explicit probability scores to…: Decision models provide structured typed answers alongside explicit probability scores to simplify uncertainty tracking.
Engineering teams can deploy decision models as cost-effective routers to assign simple t…: Engineering teams can deploy decision models as cost-effective routers to assign simple tasks like lookups to cheaper options such as GPT Luna.
Calibrations shift across versions and tasks, requiring internal AI gateways to continual…: Calibrations shift across versions and tasks, requiring internal AI gateways to continually test system performance against hand-labeled datasets.
Sources checked by our analysis pipeline: 1
LLMs love to yap. Ask a simple question and you get a few hundred words of "it depends." It's annoying as hell.
This is why we love decision models like Jev for simpler tasks. You ask a structured question and get a typed answer with a probability, which looks something like this:
Noul. Are hedgehogs mammals? → Yes, 0.99
Choice. Which animal family do hedgehogs belong to? → Mammal, 0.99
Score. What is the current conservation status of hedgehogs? → Least Concern, 0.77
Whereas LLMs return free-form and overly confident prose, decision models make model uncertainty explicit. In a calibrated model, answers that score 0.8 are right about 80% of the time. That means a score of 0.5 is a coin flip.
We've been experimenting with them at PostHog and several use cases have made it to production. This is everything we've learned about using decision models so far: when to use them, how to use them, and mistakes to avoid.
1. Use them to gate expensive LLM calls
Decision models are up to 444.6x cheaper and 193.6x faster than…
The substantial equity positions secured through prior multibillion-dollar investments solidify deep technical alliances between the artificial intelligence startup and the tech sector's largest cloud infrastructure operators. These non-voting share structures enable major cloud giants to capture financial upside and long-term compute contracts without assuming direct voting governance. Meanwhile, a broader consortium of semiconductor and software powerhouses is pouring tens of billions into private placements tie…
The company's equity value surged after it introduced a specialized integration designed specifically for sales use cases. Investors responded favorably to the commercial deployment connected to the artificial intelligence platform. This rapid positive market reaction highlights strong immediate demand for enterprise generative tools.
The audio generation platform is expanding its creative capabilities into motion by enabling users to assemble longer video productions from short segments. This integration relies on third-party generative technology provided by MiniMax. However, accessing the media creation tools requires an additional financial commitment beyond standard usage.