jevbooks

← All projects

tinystruct-typesafe-sdk

tinystruct/tinystruct-typesafe-sdk · Homepage

Type-safe semantic dispatcher for tinystruct actions using Jev.

Automated README summary

Automatically summarized from the README on 30 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A tinystruct-based SDK that lets natural language invoke existing tinystruct @Action methods. It uses TypeSafe Jev as a semantic dispatcher to route user input to allowlisted actions with typed arguments, for Java developers building classification and routing decisions.

How it uses Jev

Jev answers typed questions (choice, noul) about which allowlisted action to invoke and what values its parameters should take, based on the user's input and action descriptions. The returned probability distribution is used to select an action and bind arguments; confidence scores determine whether the action executes, needs confirmation, or is rejected.

Primitives:choicenoul

Technique worth stealing

Use Jev as a semantic dispatcher: ask typed questions over allowlisted actions and parameter spans, then gate execution by confidence thresholds.

Try it

mvn package, export TYPESAFE_API_KEY, cd tinystruct-typesafe-demo, bin/dispatcher semantic --input "create an admin account for John"

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.83
  • Shows a System One patternnot found in the excerpt0.25
  • Describes handling uncertaintynot found in the excerpt0.05
  • Reports measured numbersnot found in the excerpt0.05
  • Is a runnable toolFound in material0.90
  • Top-10 learning shortlist signalnot found in the excerpt0.28
  • Is a replica of the modelnot found in the excerpt0.18
  • Solves a common problem (0–2)score on a 0–2 scale1.20 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.83Shows a System One pattern0.25Describes handling uncertainty0.05Reports measured numbers0.05Is a runnable tool0.90Top-10 learning shortlist signal0.28Is a replica of the model0.1800.51Solves a common problem (0–2)1.20 / 2012

no-judgment band (0.40–0.60)

Design patterns
Traffic light0.96Funnel0.94Scorecard0.88Thermostat0.49Inspection0.44Questionnaire0.43Grey zone0.35Fail open, fail closed0.21Prefetch0.2000.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 30 Sept 2026.