Campaign context#

See how an AI assistant can help with campaign context in Brandwave, including example prompts and the details it may ask for.

Using your AI assistant

Connect to the Brandwave MCP server, then ask your AI assistant in natural language. It will choose the right Brandwave task and ask for any details it needs.

List campaign context#

List structured decisions, rationale, assumptions, risks, and learnings.

Tool name: list_campaign_context. Protocol hints: readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=false.

Example prompt#

text

List all campaign context in my workspace.

Details to provide#

Name	Type	Required	Description
workspaceId	`string (UUID)`	Required	Workspace identifier.
campaignId	`string (UUID)`	Required	Unique identifier (UUID v4).

What you'll get back#

Returns { items, totalCount, facets, _meta } with paginated results.

Search campaign memory#

Search campaign decisions, assumptions, risks, learnings, and future recommendations across every campaign in the workspace, so a past learning can be found without knowing which campaign produced it.

Tool name: search_campaign_context. Protocol hints: readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=false.

Example prompt#

text

Show me the details for this campaign memory.

Details to provide#

Name	Type	Required	Description
pageIndex	`integer`	Required	Zero-based page index for pagination.
pageSize	`integer`	Required	Number of items per page (1-100).
workspaceId	`string (UUID)`	Required	Workspace identifier.
searchTerm	`string`	—	Free-text term matched against memory titles and content.
contextTypes	`Array<'decision' \| 'rationale' \| 'hypothesis' \| 'assumption' \| 'creative_strategy' \| 'agency_recommendation' \| 'impact_mechanism' \| 'risk' \| 'constraint' \| 'learning' \| 'future_recommendation'>`	—	Restrict results to these context types. Defaults to every type.
campaignId	`string (UUID)`	—	Restrict results to one campaign, for example to re-read its own history.
excludeCampaignId	`string (UUID)`	—	Omit one campaign, so the current campaign does not crowd out past learnings.

What you'll get back#

Returns { items, totalCount, facets, _meta } with paginated results.

Get campaign context#

Get one campaign context entry with who recorded it, the original author and date, its current revision number, and the memory or source files it references.

Tool name: get_campaign_context. Protocol hints: readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=false.

Example prompt#

text

Show me the details for this campaign context.

Details to provide#

Name	Type	Required	Description
id	`string (UUID)`	Required	Unique identifier (UUID v4).

What you'll get back#

Returns { data, _meta } with the result.

List campaign context revisions#

List the complete revision history of one campaign context entry, including changes to its kind, title, wording, attribution, and references, so a correction can be told apart from the original wording.

Tool name: list_campaign_context_revisions. Protocol hints: readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=false.

Example prompt#

text

List all campaign context revisions in my workspace.

Details to provide#

Name	Type	Required	Description
id	`string (UUID)`	Required	Unique identifier (UUID v4).

What you'll get back#

Returns { items, totalCount, facets, _meta } with paginated results.

Create campaign context#

Create a campaign context entry of a given context type (decision, rationale, assumption, risk, learning, and others) with a title and content, optionally recording the original author name and authored date and the past memory or source file references it was based on.

Tool name: create_campaign_context. Protocol hints: readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false.

Example prompt#

text

Create a new campaign context.

Details to provide#

Name	Type	Required	Description
workspaceId	`string (UUID)`	Required	Workspace identifier.
campaignId	`string (UUID)`	Required	Unique identifier (UUID v4).
contextType	`'decision' \| 'rationale' \| 'hypothesis' \| 'assumption' \| 'creative_strategy' \| 'agency_recommendation' \| 'impact_mechanism' \| 'risk' \| 'constraint' \| 'learning' \| 'future_recommendation'`	Required	The kind of reasoning recorded: decision, rationale, hypothesis, assumption, creative_strategy, agency_recommendation, impact_mechanism, risk, constraint, learning, or future_recommendation.
title	`string`	Required	One-line summary of the entry.
content	`string`	Required	Full text of the decision, reasoning, risk, or learning.
authorName	`string \| null`	—	Who originally wrote it, when that differs from the user recording it.
authoredAt	`string \| null`	—	Date (YYYY-MM-DD) it was originally written, when known.
references	`Array<unknown>`	—	Past memory entries or attached source files this entry was based on. A memory reference may pin the exact revision that was read.

What you'll get back#

Returns { data, _meta } with the result.

Update campaign context#

Update the title, content, context type, author name, authored date, or references of one campaign context entry and record a complete new revision. Pass expectedRevisionNumber to be refused with a conflict instead of overwriting a change someone else saved first.

Tool name: update_campaign_context. Protocol hints: readOnlyHint=false, destructiveHint=true, idempotentHint=true, openWorldHint=false.

Example prompt#

text

Update the campaign context.

Details to provide#

Name	Type	Required	Description
contextType	`'decision' \| 'rationale' \| 'hypothesis' \| 'assumption' \| 'creative_strategy' \| 'agency_recommendation' \| 'impact_mechanism' \| 'risk' \| 'constraint' \| 'learning' \| 'future_recommendation'`	—	The kind of reasoning recorded: decision, rationale, hypothesis, assumption, creative_strategy, agency_recommendation, impact_mechanism, risk, constraint, learning, or future_recommendation.
title	`string`	—	One-line summary of the entry.
content	`string`	—	Full text of the decision, reasoning, risk, or learning.
authorName	`string \| null`	—	Who originally wrote it, when that differs from the user recording it.
authoredAt	`string \| null`	—	Date (YYYY-MM-DD) it was originally written, when known.
references	`Array<unknown>`	—	Past memory entries or attached source files this entry was based on. A memory reference may pin the exact revision that was read.
id	`string (UUID)`	Required	Unique identifier (UUID v4).
expectedRevisionNumber	`integer`	—

What you'll get back#

Returns { data, _meta } with the result.

Delete campaign context#

Delete one structured campaign context entry by soft deletion.

Tool name: delete_campaign_context. Protocol hints: readOnlyHint=false, destructiveHint=true, idempotentHint=true, openWorldHint=false.

Example prompt#

text

Delete this campaign context.

Details to provide#

Name	Type	Required	Description
id	`string (UUID)`	Required	Unique identifier (UUID v4).

What you'll get back#

Returns { data, _meta } with the result.