Skip to content
All tags

#versioning

3 posts

Prompt Version Control: Changing One Word Can Drop an Eval from 5/5 to 0/5

Rivumi's prompt is now `m3-exact-edit-v4`: the version persists into artifacts; core/tool/interaction/runtime/instructions/skills/workspace/memory are composed as stable or dynamic sections; and positive/negative examples cover replace_text, unified diffs, and direct replies. Unit tests pin the structure, while live-eval coverage still needs expansion.

tech

Agent Platform Deep Dive (Part 2) — Flow Runtime: Versioned Flows, Checkpoints, and Resume/Retry Mechanisms

Flow Runtime is the heart of Agent Platform: a Flow becomes immutable when published, each Run is bound to a specific version and preset, Steps move through a DAG according to edge conditions, every boundary saves a checkpoint, and resume/retry-step preserves the complete trace history.

tech

Agent Platform Deep Dive (3) — Skill System: Versioned Capability Packages, Explicit Binding, and the Learning Loop

A Skill is a versioned, installable, and auditable capability package. Its dual-file architecture separates metadata from instructions, explicit binding replaces model-driven routing, and every invocation is recorded. The Learning Loop turns run signals into proposals, sandbox evaluations, human review, and publication while enforcing the principle: agents propose, humans review, and evals serve as the gate.