Skip to main content
The knowledge base stores information that page content cannot provide: the words your team uses, the rules a specific agent should follow, and the multi-step flows that describe how your product works. Agents retrieve relevant entries for a task and include them in their prompts as priority context. You manage it from the Knowledge section of the dashboard at app.momentic.ai/knowledge.

​
Knowledge types

You can create three types of knowledge. Pick the type that matches the information you want to provide.
  • Terminology defines a term your test or app uses so the agent resolves it the way your team means it. You provide a canonical term, a definition, and optional examples that ground how the term is used. Use this when a word is ambiguous, such as what “the selected tab” actually refers to in your UI.
  • Agent rule is a binding instruction that one agent should follow at runtime. You give it a title, choose the agent it applies to, and write the instruction. Only the selected agent receives the rule, so you can shape behavior precisely, such as how elements are located or how a failure is classified. Rules can also target the heal subagent, which repairs one failing test at a time. Product-specific recovery guidance reaches the agent that edits or verifies the repair without being applied to broader failure-bucketing.
  • Flow is a known workflow with an expected outcome. You describe the intent (the user-level goal, like “log in”), the steps (one per line), and the success state (what should be true once the flow finishes). Flows give the agent a reliable map of how a journey through your product is supposed to go.
The knowledge base can also contain generated Code insight entries. These are read-only in the knowledge editor and describe the code behind a product area. See App graph. Definitions, instructions, and steps all support Markdown. Retrieval preserves Markdown but can omit or truncate entries to fit the agent’s context budget. Keep essential rules concise and put them early in an entry. Agent-rule instructions accept up to 100,000 characters when created or edited, including through bulk upload. Existing longer instructions remain readable and can still be archived.

​
Adding knowledge

  1. Open the Knowledge section, click Add knowledge, and choose Create manually.
  2. Choose a type. The form shows the fields relevant to that type.
  3. Fill in the content and, optionally, set a scope.
  4. Save. The item is visible immediately and becomes searchable when indexing finishes.
To import many items at once, choose Bulk upload from the same menu instead (see Bulk upload).

​
Scope

By default, knowledge applies across your whole organization. You can narrow an item so it’s only retrieved in a more specific context:
  • Test scope limits the item to a single test.
  • Environment scope limits the item to a specific environment.
  • App scope limits the item to a specific app.
Leave a scope blank to keep it organization-wide. The detail view shows each item’s scope (Organization, Test, Environment, or App).

​
Bulk upload

To import an existing knowledge base in one step, choose Bulk upload from the Add knowledge menu and upload or paste a JSON array or CSV of items. Momentic accepts up to 200 rows per upload and validates the whole upload together: if any row is invalid, Momentic creates nothing and the error lists the offending rows. Each row carries a type of TERMINOLOGY, AGENT_RULE, or FLOW (defaulting to TERMINOLOGY when omitted) plus that type’s fields:
  • Terminology: canonicalTerm, definition, and optional examples.
  • Agent rule: title, agentSubtype, and instruction.
  • Flow: intent, steps, and successState.
The examples field accepts either a JSON string array or a newline-separated string (one example per line), which is convenient for a single CSV cell. Add an optional appId, testId, or environmentId to a row to scope it; omit them to keep the item organization-wide. The dialog includes JSON and CSV samples you can load as a starting point.

​
Suggestions

Momentic captures candidate knowledge from your sessions and collects it in the Suggestions tab for review. These are entries Momentic inferred about your product that aren’t part of your knowledge base yet.
  • Approve a suggestion to promote it into your organization’s knowledge base, where it starts informing agents.
  • Reject a suggestion to discard it.
The Organization tab shows knowledge that’s already in effect, and the Suggestions tab shows what’s waiting on your review. Each tab displays a count so you can see whether there’s anything to triage.

​
Enabling and disabling

Active knowledge can be turned on or off without deleting it:
  • Enabled: the item is live and eligible for retrieval.
  • Disabled: the item is kept but excluded from retrieval.
Use the toggle on an item to switch between the two. Items that are still pending review (or otherwise not yet active) must be approved or archived before they can be toggled. Momentic manages the system knowledge it authors, so it can’t be edited or disabled.

​
Trust and conflicts

Each item carries a trust score from 0 to 100 that shows how authoritative it is. Manually authored knowledge is trusted more than auto-generated suggestions, and Momentic’s own system knowledge is trusted highest by default. Prompts instruct agents to prefer the higher-trust entry when entries conflict. Agent rules are treated as binding instructions and are given extra retrieval weight.

​
How agents use knowledge

Momentic uses semantic retrieval to select entries relevant to an agent’s task and includes the retrieved entries as priority context. Heal runs also retrieve knowledge scoped to the test being repaired, so rules, terminology, and known flows can guide the repair for that specific failure. Prompts require agents to follow entries that directly address the task and cite entries they rely on in written reasoning or summaries. Use those citations to trace which knowledge influenced a decision.

​
Versioning and usage

Editing an item records a new version, and the About tab keeps the full version history alongside who changed what and when. The Usage tab lists the runs that cited the item, with the test each run belongs to and when it was cited, and links to each run so you can see how a piece of knowledge is being used in practice.