AI-DLC Glossary

Quick reference for all AI-DLC terminology and concepts.

A

Adoption
The process of reverse-engineering an existing feature into AI-DLC intent artifacts, enabling operational management and structured iteration without requiring the feature to have been built through AI-DLC's construction phase
AHOTLSee in paper
Autonomous Human-on-the-Loop: human defines criteria and reviews output; AI operates autonomously within boundaries; used for well-defined, programmatically verifiable work

B

BackpressureSee in paper
Quality gates that automatically reject work not meeting criteria, providing feedback for iteration
BoltSee in paper
Smallest iteration unit in AI-DLC 2026; operates in supervised (HITL), observed (OHOTL), or autonomous (AHOTL) mode

C

Completion CriteriaSee in paper
Programmatically verifiable conditions that define when work is successfully done
Completion PromiseSee in paper
Signal (e.g., COMPLETE, BLOCKED) that autonomous execution has finished
Context BudgetSee in paper
Available attention capacity in AI context window; quality degrades when overloaded

D

Design Blueprint
A structured artifact produced by the Design Direction phase that defines a project's visual language — archetype, parameters, component patterns — and seeds the design knowledge artifact
Design Direction
Elaboration phase (2.75) where greenfield or early-stage projects select a visual archetype and tune design parameters, producing a design blueprint that guides wireframe generation and builder context

H

HITLSee in paper
Human-in-the-Loop: human validates each significant step before AI proceeds; used for novel, high-risk, or foundational work

I

IntegratorSee in paper
Final validation hat that runs conditionally based on VCS strategy; validates auto-merged state (trunk) or creates single PR (intent); skipped for unit/bolt strategies
IntentSee in paper
High-level statement of purpose with completion criteria that serves as starting point for decomposition

K

Knowledge Artifact
A structured file in `.ai-dlc/knowledge/` capturing project intelligence in one of five types: design, architecture, product, conventions, domain; persists across intents
Knowledge Layer
The collection of knowledge artifacts that accumulate project intelligence over time, serving as persistent cross-intent context for elaboration and execution

M

Memory ProviderSee in paper
Source of persistent context (files, git, tickets, ADRs, runbooks) accessible to AI agents
Mob ElaborationSee in paper
Collaborative ritual where humans and AI decompose Intent into Units with Completion Criteria
Mob Execution
Collaborative ritual where multiple teams build Units in parallel with AI assistance

O

OHOTLSee in paper
Observed Human-on-the-Loop: human watches AI work in real-time with ability to intervene; synchronous awareness with asynchronous control; used for creative, subjective, or training scenarios
Operation
A file-based operational task spec (`.md` with YAML frontmatter) defining scheduled, reactive, or process-type work with agent or human ownership; stored in `.ai-dlc/{intent}/operations/`

P

Pass
A typed iteration through the standard AI-DLC loop (elaborate, units, execute, review) that refines an Intent through a specific disciplinary lens; defined as frontmatter-enabled markdown files with instructions and workflow constraints; three built-in passes (design, product, dev) can be augmented or extended by project-level definitions; passes are optional (zero overhead when unused) and configurable via `default_passes` in settings; output of one pass becomes input to the next

Q

Quality GateSee in paper
Automated check (tests, types, lint, security) that provides pass/fail feedback

R

Ralph Wiggum PatternSee in paper
Autonomous loop methodology: try, fail, learn, iterate until success criteria met

S

Stack Config
Infrastructure stack configuration in `.ai-dlc/settings.yml` describing deployment, compute, monitoring, alerting, and operations layers

U

UnitSee in paper
Cohesive, independently deployable work element derived from an Intent; named with numerical prefix + slug (e.g., `unit-01-setup-auth`); can declare dependencies via `depends_on` forming a DAG
Unit DAGSee in paper
Directed Acyclic Graph of unit dependencies enabling parallel execution (fan-out) and convergence (fan-in)