StackMap
Subscribe
Explore / strands-decider
strands-labs

strands-decider

Strands' small decision model (2B, Qwen3.5-based): pick between options, answer yes/no or rate on a scale with calibrated confidence. CLI and /v1/systemone server on CUDA, MPS, MLX or CPU.

579 77 Python Apache-2.0updated 2 days ago
decision-modelslocal
View on GitHubDispute this mapping →
Curator's take

Use it for the many small judgments inside an agent workflow — routing, triage, urgency, sentiment — where an LLM call is too slow and training a classifier too much work; answers at ≥0.9 confidence were right ~95% of the time on unseen tasks, so threshold and escalate the rest. It decides, never writes. At 2B it runs on a laptop; for agent-action ranking at scale, CLM's cached-embedding design is faster.

Mapped by ShipWithAI editors · links verified

Continue your stack

What teams reach for next — and why each earns a place beside strands-decider. Ranked by curator confidence.

pairs wellalternativealternativealternativealternativeharness-sdklayaCLMkevAnyJevstrands-decider
pairs wellalternativebuilt withpick a node for the why · open it from the panel
Weekly digest
README.md2 min read

Strands Decider

A small, fast decision model for agentic AI.

Commit Activity Open Issues Open PRs Discord

Strands decider is one of a new class of decision models, or "system one" models. Unlike an LLM, which can generate arbitrary text, a decision model picks between sets of options and rates things on a scale. This class of model works best for problems that fall between LLMs and traditional classification models: it is a general-purpose classification and scoring model that responds faster than an LLM and does not take the time and expertise to train that a traditional classifier does. That makes it a natural fit for the decisions inside agentic workflows built with the Strands Agents SDK.

  • Pick from options — "Are there three r's in strawberry? Yes or no." "What language is the phrase 'sihamba ngokushesha' in? English, Zulu, or Dutch."
  • Rate on a scale — "How positive is 'this is the best doc I've ever read'? Between 0 and 1."
  • Calibrated reliability scores — every decision carries a confidence. On short classification tasks it has never seen, answers at a confidence of 0.9 or more are right about 95% of the time (evaluation/results.md); below that, confirm or ask a person. Frontier LLM inference APIs do not expose anything equivalent.

Getting Started

The easiest place to get started is through the strands-decider cli:

pip install strands-decider

On an Apple-silicon Mac, --device mlx runs the model through MLX, 1.4 to 1.6x faster than MPS. It needs the mlx extra, which ships with the next release; until then, install from a clone with pip install -e ".[mlx]". The cuda, mps and cpu extras name the other devices (docs/inference.md). The example outputs below are from strands-decider-2B-qwen3.5-v1-2610, recorded with --device cpu; other devices differ in the last digits.

Choice question

You can ask the model to choose based on some state and a question:

strands-decider ask StrandsAgents/strands-decider-2B-qwen3.5-v1-2610 \
  --state "Help! My payouts have been failing for 3 days! " \
  --choice "Which team should handle this?=billing,sales,retail"

Example Output:

choice_0 -> billing (confidence 0.659)
  billing                  0.773
  sales                    0.121
  retail                   0.106

Noul question

You can also ask the model a Yes/No question:

strands-decider ask StrandsAgents/strands-decider-2B-qwen3.5-v1-2610 \
  --state "Help! My payouts have been failing for 3 days! " \
  --noul "Does this convey urgency?"

Example Output:

noul_0 noul = 0.858

Closer to 1 is leaning more toward Yes

Score question

Or give a question a score:

strands-decider ask StrandsAgents/strands-decider-2B-qwen3.5-v1-2610