Skip to main content

Documentation Index

Fetch the complete documentation index at: https://momentic.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

Momentic uses several specialized AI agents. Each is versioned independently so you can upgrade one agent without changing the others. Configure results classification and post-classification healing behavior in Settings > Classification in the dashboard.
momentic.config.yaml
ai:
  useMemory: true
  failureRecovery: true
  agentConfig:
    locator: v3
    assertion: v3
    visual-assertion: v3
    text-extraction: v3

​
Options

​
ai.agentConfig
Record<agent, version>
Choose which version of prompts and models to use for each AI task. v3 is recommended for new projects. Omit an agent to inherit the organization default. See Agents below for available versions per agent.
momentic.config.yaml
ai:
  agentConfig:
    locator: v3
    assertion: v3
    visual-assertion: v3
    text-extraction: v3
    failure-recovery: v2
​
ai.useMemory
boolean
Default: true. Allow AI agents to use data from past test runs to keep element locators and assertions consistent across runs. Sets the org-wide default; can be overridden per test. See Memory for details.
momentic.config.yaml
ai:
  useMemory: true
​
ai.failureRecovery
boolean
Failure recovery is in beta.
Default: false. Enable Failure recovery. Momentic proposes and executes step changes to recover from certain test failures.
momentic.config.yaml
ai:
  failureRecovery: true
​
ai.aiPageFiltering
boolean
Deprecated and kept only for backwards compatibility. Page filtering is always enabled for large browser pages and cannot be customized after CLI version 2.94.0. Safe to remove from existing config files.
Default: true.

​
Agents

AgentPowers
locatorClick, Type, and Element check steps
assertionAI check steps
visual-assertionVisual assertions against a screenshot
text-extractionAI extract steps
failure-recoveryFailure recovery

​
Locator

Locates elements on the page from a natural language description.
  • v1: 2024 models. Lenient matching, picks candidates that fulfill the same function as the description.
  • v2: early-2025 models. Strict about relative positioning (“the link in the header”) and single-quoted text (“the ‘Submit’ button”).
  • v3 (recommended): latest 2025 models. Smarter caches that store referenced attributes and relative elements, so meaningful changes invalidate the cache. Writes clearer reasoning for chosen elements.

​
Assertion

Evaluates natural language statements against a snapshot of the page.
  • v1: 2024 models. Lenient, evaluates statements as “overall true/false”.
  • v2: early-2025 models. Stronger at sorted order, visual positioning, and relative criteria. Strict about single-quoted text.
  • v3 (recommended): latest 2025 models.

​
Visual assertion

Evaluates natural language statements purely from a viewport screenshot.
  • v1: 2024 models. Faster (~3s avg). Lenient on color assertions.
  • v2: early-2025 models. Slower but sharper on small visual details, logical reasoning, negations, and container-scoped assertions. Strict about “exactly” and single-quoted text.
  • v3 (recommended): latest 2025 models.

​
Text extraction

Extracts structured data from the page given a JSON schema.
  • v1: 2024 models.
  • v2: early-2025 models. Tighter schema adherence; throws if extracted data doesn’t conform. Understands the pattern JSON schema option.
  • v3 (recommended): latest 2025 models. Handles nested objects and arrays. Better at following transformation instructions before returning data.

​
Failure recovery

Generates and executes recovery steps when a recoverable failure is detected. Requires ai.failureRecovery to be enabled. See Failure recovery for details.
  • v1: original recovery agent.
  • v2 (recommended): latest model and prompt with broader scenario coverage, goal-oriented recovery instructions, and a tool-based agent that can bust caches when needed.