Who it is forA developer with an open LLM already downloaded who needs a routing or classification step and has no labeled data to train on.
The problemRaw label logits change when the options are reordered and carry the model's bias toward some labels, so the probabilities are not trustworthy.
The outcomeA Decision with a distribution over the options and a level value of L0, which downstream code can require before acting.
What you need first
- Python with pip
- A GPU or a vLLM server for the 9B-class models, or a smaller open causal LM for the training-free path
- Access to the Hugging Face model you choose, for example morriszjm/Tacit-9B or Qwen/Qwen3-8B
Steps
- Run
pip install anyjevin a Python environment with the backend you need. (inferred, check the README) - Create the backend with
HFBackend("Qwen/Qwen3-8B")and build a Decider withDecider(backend). - Define a choice question with
Question.choice("Which team should handle this?", ["billing", "technical", "sales", "other"], name="route"). (inferred, check the README) - Call
d.decide(<ticket text>, [route])["route"]and readr.distributionandr.level. (inferred, check the README) - Optionally enable the rotation budget with
Decider(backend, adaptive_shifts=True, canonical_order=True)and calibrate it on a few hundred unlabelled tickets usingcalibrate_adaptive.
Prompt for your agent
Using the repo AnyJev (nokia-applied-research/AnyJev), build a Decider on Qwen/Qwen3-8B with HFBackend and route the ticket <ticket text> using a choice question over <option list>. Expected output: a distribution over the options and the level L0. Verify that the distribution is returned for every option and that the level is L0 before acting on the result.
Caveat. The README's accuracy and automation figures come from BANKING77 with Qwen3-8B, so measure on your own tickets before trusting the threshold.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page