Business & Operations

Dcipher Analytics

by Dcipher Analytics

Overview

Dcipher is a research and analytics platform that collects large volumes of external content — web, news, social media, your own files — and turns it into structured, analyzable data. This connector gives ChatGPT access to your Dcipher workspace, so you can work through the whole platform in conversation. ChatGPT can run research agents, build and manage knowledge bases, search them and answer questions with references back to source documents, and set up Insight Boosters, Dcipher's insight and foresight analytics engine. It can produce content landscapes, trend radar charts, comparison matrices, scenario analysis views and write reports from your sources, and schedule workflows so everything stays current. You describe what you want to know. ChatGPT figures out which parts of Dcipher get you there — whether that means collecting new material, querying what you already have, or building a dashboard on top of it.

Tools

apply_project_filter

ChatGPT

Apply the project-level filters and return document ids that match. IDs are returned in the form '<dbcollection>-<hash>'.

archive_insight_booster

ChatGPT

Archive (soft-delete) an Insight Booster project. The project becomes hidden from the default project list but remains restorable via restore_insight_booster.

ask_research_chatbot

ChatGPT

Send a question to the research bot and receive a generated answer with supporting references and document IDs. This endpoint performs search and generation; it has no side effects apart from usage reporting. This is the Landscape workbench's built-in chatbot: it is scoped to the project, not to any particular workbench, and answers using the project's knowledge bases as reference.

attach_knowledge_base_to_insight_booster

ChatGPT

Attach a Knowledge Base to an Insight Booster project. Existing attachments are preserved. Filters are optional — skip them if the Knowledge Base was created specifically for this project. A project can have multiple Knowledge Bases attached.

check_kb_has_timestamp

ChatGPT

Return a map from KB id to boolean indicating whether documents in that KB have a timestamp field.

clone_insight_booster

ChatGPT

Clone an existing Insight Booster project. The new project inherits the source's configuration, workbenches, and filters but starts with no generated reports. Returns the new project id.

create_insight_booster

ChatGPT

Create a new Insight Booster project in the caller's organization. The project is seeded with a single Landscape workbench. To add more workbenches (radar, bump, matrix, scenario, growth, report), call create_insight_booster_workbench once per workbench after this returns, then configure each with the update…WorkbenchConfig tools. Returns the new project id those tools can target.

create_insight_booster_report_template

ChatGPT

Create a new AI-generated report template from an existing report. Templates can later be applied to workbenches to generate new reports of the same shape.

create_insight_booster_view

ChatGPT

Create a new view on an Insight Booster project. A view is a saved filter + workbench selection.

create_insight_booster_workbench

ChatGPT

Create a new workbench within an Insight Booster project. A workbench holds a visualization (radar, bump, matrix, landscape, growth, or scenario) plus its config and any AI-generated report. This returns an empty shell: it accepts only a name and a type and cannot run analysis until it is configured. Creating a workbench is a three-step flow — create it here, configure it with the matching update_insight_booster_*_workbench_config tool (growth takes no config), then read the analysis with the matching result tool for its type. Configuring is not the finish line: never tell the user their analysis is ready before a result tool has actually returned. Resolve workbench ids from get_insight_booster, which lists the project workbenches — never invent one. The landscape workbench id is not visible in any URL, so look it up the same way. Each project has exactly one landscape workbench; every other type can have any number. All types except report run analysis automatically once configured — report instead opens a template editor and needs an explicit generate call.

create_news_kb

ChatGPT

Create a News Knowledge Base by scanning news articles — use this for horizon scanning, trend monitoring, and industry news. Takes ready Opoint query params, but there is no keyword-suggestion tool: derive concrete search keywords yourself from the topic the user gave, and state the ones you chose so they can correct them. Aim for roughly 5,000-15,000 articles in the resulting KB — steer queries, filters, and time windows toward that range. Omit schedule for a ONE-TIME fetch; pass schedule to stand up a self-refreshing flow instead, where the first run fires almost immediately (now+delay) and each subsequent run fetches fresh and creates a NEW timestamp-suffixed KB. Returns the flow id immediately; runs are asynchronous and materialize the KB on completion. For a ONE-TIME fetch (no schedule), call wait_for_flow next with the returned flowId and keep calling it until done — do not ask the user whether to wait or check status, and do not hand back control in between. For a scheduled flow, this call is enough — confirm the schedule and hand back control without waiting on the first run. get_last_flow_run_status is only for a one-off check that should not block, such as the latest run of a scheduled flow. Pass insightBoosterId to auto-link each KB to that project on completion; omit it to attach later with attach_knowledge_base_to_insight_booster. If you chose the data source or its key parameters yourself rather than the user specifying them, state them and confirm with the user before calling.

create_research_agent_kb

ChatGPT

Create a Knowledge Base that GENERATES its data with a research agent scanning public web sources — use this for desk research such as government reports, academic publications, and filings. You define the agent task and (optionally) placeholder variables; the agent runs once per variable combination, writing the default output columns (Text, Source, URL, Date) plus the input variables. Omit schedule for a ONE-TIME run; pass schedule to re-run the task on a cadence, where each run creates a NEW timestamp-suffixed KB. Returns the flow id immediately; runs are asynchronous and materialize the KB on completion. For a ONE-TIME run (no schedule), call wait_for_flow next with the returned flowId and keep calling it until done — do not ask the user whether to wait or check status, and do not hand back control in between. For a scheduled flow, this call is enough — confirm the schedule and hand back control without waiting on the first run. get_last_flow_run_status is only for a one-off check that should not block, such as the latest run of a scheduled flow. Pass insightBoosterId to auto-link each KB to that project on completion; omit it to attach later with attach_knowledge_base_to_insight_booster. If you chose the data source or its key parameters yourself rather than the user specifying them, state them and confirm with the user before calling.

create_social_kb

ChatGPT

Create a Social-media Knowledge Base by scanning social posts — use this for voice-of-the-customer, sentiment, and community discussions. Takes ready Netfeedr query params and per-platform post limits, but there is no keyword-suggestion tool: derive concrete search queries yourself from the topic the user gave, and state the ones you chose so they can correct them. Aim for roughly 5,000-15,000 posts in the resulting KB — steer queries, filters, and time windows toward that range. Omit schedule for a ONE-TIME fetch; pass schedule to stand up a self-refreshing flow instead, where the first run fires almost immediately (now+delay) and each subsequent run fetches fresh and creates a NEW timestamp-suffixed KB. Returns the flow id immediately; runs are asynchronous and materialize the KB on completion. For a ONE-TIME fetch (no schedule), call wait_for_flow next with the returned flowId and keep calling it until done — do not ask the user whether to wait or check status, and do not hand back control in between. For a scheduled flow, this call is enough — confirm the schedule and hand back control without waiting on the first run. get_last_flow_run_status is only for a one-off check that should not block, such as the latest run of a scheduled flow. Pass insightBoosterId to auto-link each KB to that project on completion; omit it to attach later with attach_knowledge_base_to_insight_booster. If you chose the data source or its key parameters yourself rather than the user specifying them, state them and confirm with the user before calling.

delete_insight_booster_filter

ChatGPT

Delete a single filter from an Insight Booster project, identified by filter id and filter type.

delete_insight_booster_report_template

ChatGPT

Delete an AI-generated report template. Reports already generated from it are not affected.

delete_insight_booster_view

ChatGPT

Delete a view from an Insight Booster project.

delete_insight_booster_workbench

ChatGPT

Delete a workbench from an Insight Booster project.

detach_all_knowledge_bases_from_insight_booster

ChatGPT

Detach every Knowledge Base from an Insight Booster project. Irreversible without re-attaching.

detach_knowledge_base_from_insight_booster

ChatGPT

Detach a single Knowledge Base from an Insight Booster project.

fetch_project_metadata_schema

ChatGPT

Return the union of metadata schema entries from all KBs attached to the project. Useful to drive filter UIs and validation.

fetch_research_chatbot_conversation_history

ChatGPT

Return the last N messages from the research-bot conversation

generate_insight_booster_workbench_report_from_template

ChatGPT

Generate a new AI-generated report on a workbench by applying a saved report template. Returns the new report id.

generate_report_sections_from_landscape

ChatGPT

Generate structured report sections for a given interest area. The returned object contains sections suitable for inclusion in a generated report. This operation can be useful to decide on Report Generator sections based on project data.

get_bump_result

ChatGPT

MCP version of generate_bump. Returns {'result': ...}. Projection is applied to the value inside result, not to the result envelope. Before projection, result has the BumpChartResponse schema. Top-level fields are day, week, month, quarter, semiyear, and year. Each top-level field is an array of BumpChartDataPoint objects. Each data point has x: string (time bucket label), y: string (series or category label), and val: integer (rank or numeric value). Always provide projection as {'pipeline': [...]} using MongoDB aggregation syntax. Use $project for selecting granularities such as week or month. Use $map when reshaping data point arrays. Use $slice to limit large arrays. Use $filter to keep only data points matching x, y, val, or other conditions. Do not project result.* paths; project day, week, month, quarter, semiyear, year, and their nested fields directly. Use the smallest projection that returns only the fields needed to answer the user, because the projected result will be sent to an LLM.

get_file_by_name

ChatGPT

Resolve an uploaded file by name. Returns { ready: true, file } once the file is registered in storage, or { ready: false } while it is not yet available. Use this to poll after the file was uploaded through the app — file registration happens asynchronously once the bytes land, so a just-uploaded file may briefly report not-ready before it can be used.

get_growth_result

ChatGPT

MCP version of analyze_growth. Returns {'result': ...}. Projection is applied to the value inside result, not to the result envelope. Before projection, result is an array of GrowthChartTopicPoint objects. Each topic point has id: string, title: string, summary: string, examples: array, metadata: object, size: integer, growths: object, and volumes: object. examples is an array of source example objects. Each example has text: string, source: string or null, and url: string or null. metadata is an object with string keys and string/number values. growths is an object keyed by time-bucket label with number or null values. volumes is an object keyed by time-bucket label with integer values. Always provide projection as {'pipeline': [...]} using MongoDB aggregation syntax. Use $project for field selection and reshaping. Use $map when selecting fields from nested examples. Use $slice or $limit to reduce large arrays. Use $filter or $match to keep only topics matching title, size, growth, volume, or metadata conditions. Do not project result.* paths; project id, title, summary, examples, metadata, size, growths, volumes, and their nested fields directly. Use the smallest projection that returns only the fields needed to answer the user, because the projected result will be sent to an LLM.

get_insight_booster

ChatGPT

Fetch full details for an Insight Booster project by id, including workbenches, attached Knowledge Bases, filters, and research-bot configuration. Use this before making changes to inspect current state.

get_insight_booster_research_bot_config

ChatGPT

Get the research-bot configuration for an Insight Booster project (allowed domains, rate limit, UI prefs).

get_insight_booster_workbench

ChatGPT

Get a single workbench by id along with its current AI-generated report output.

get_kb_field_statistics

ChatGPT

Return aggregated statistics for the requested metadata field (categoric counts, numeric min/max/mean, or date range).

get_landscape_max_broadness

ChatGPT

Retrieve the maximum broadness level supported for analyze_growth. This value determines the highest level of topic aggregation available for the landscape. Use to validate or bound broadness parameters in growth analysis requests.

get_landscape_result

ChatGPT

MCP version of generate_landscape. Returns {'result': ...}. Projection is applied to the value inside result, not to the result envelope. Before projection, result has the LandscapeGeneratorResponse schema. Top-level fields are documents and topics. documents is an array of document point objects. Each document has id: string (document identifier), x: number and y: number (map coordinates), radius: number or null (visual size), and color_value: string or null (visual color bucket). topics is an array of topic level objects. Each topic level has level: integer (broadness level) and topic_points: array. topic_points is an array of topic objects. Each topic has id: string, x: number, y: number, radius: integer, title: string, summary: string, examples: array, and metadata: object with string keys and string/number values. examples is an array of source example objects. Each example has text: string, source: string or null, and url: string or null. Always provide projection as {'pipeline': [...]} using MongoDB aggregation syntax. Use $project for top-level field selection and reshaping. Use $map when selecting fields from nested arrays such as topics, topic_points, or examples. Use $slice to limit large arrays. Use $filter to keep only array items matching a condition. Do not project result.* paths; project documents, topics, and their nested fields directly. Use the smallest projection that returns only the fields needed to answer the user, because the projected result will be sent to an LLM.

get_last_flow_run_status

ChatGPT

Get the LATEST run status of a KB flow, without blocking — works for both one-shot and scheduled flows. After a one-shot create (create_news_kb / create_social_kb / create_research_agent_kb), use wait_for_flow instead; reach for this one when a single non-blocking check is all you need. It returns the task status and, once complete, the resolved knowledgeBaseId to attach downstream. For a scheduled flow it reports the MOST RECENT run on the schedule cadence — mind the run times: between runs it shows the last completed run, and the returned knowledgeBaseId is the first run's KB (each run materializes a new timestamp-suffixed KB). When a run FAILED, the returned message carries the failure reason; it is omitted otherwise.

get_matrix_result

ChatGPT

MCP version of generate_matrix. Returns {'result': ...}. Projection is applied to the value inside result, not to the result envelope. Before projection, result is an array of GenerateMatrixUnitResponse objects. Each matrix cell has id: integer, row: string, column: string, output: string, size: integer, and references: array. references is an array of objects with source: string and url: string or null. Always provide projection as {'pipeline': [...]} using MongoDB aggregation syntax. Use $project for field selection and reshaping. Use $map when selecting fields from nested references. Use $slice or $limit to reduce large arrays. Use $filter to keep only cells matching row, column, size, or other conditions. Do not project result.* paths; project id, row, column, output, size, references, and their nested fields directly. Use the smallest projection that returns only the fields needed to answer the user, because the projected result will be sent to an LLM.

get_project_time_range

ChatGPT

Compute and return the earliest and latest timestamps available across the project's knowledge bases.

get_radar_result

ChatGPT

MCP version of generate_radar. Returns {'result': ...}. Projection is applied to the value inside result, not to the result envelope. Before projection, result is an array of RadarSegment objects. Each segment has id: string, title: string, and bubbles: array. bubbles is an array of RadarBubble objects. Each bubble has id: string, title: string, summary: string, count: integer, angularScale: number, radialScale: number, sizeScale: number or object, references: array, examples: array of strings, and isPredefined: boolean. references is an array of source example objects. Each reference has text: string, source: string or null, and url: string or null. Always provide projection as {'pipeline': [...]} using MongoDB aggregation syntax. Use $project for field selection and reshaping. Use $map when selecting fields from nested arrays such as bubbles or references. Use $slice or $limit to reduce large arrays. Use $filter to keep only segments or bubbles matching a condition. Do not project result.* paths; project id, title, bubbles, and their nested fields directly. Use the smallest projection that returns only the fields needed to answer the user, because the projected result will be sent to an LLM.

get_report_result

ChatGPT

MCP JSON version of generate_report. Returns {'result': ...}. Projection is applied to the value inside result, not to the result envelope. Unlike the REST endpoint, this endpoint returns generated report section JSON instead of a streamed file. Before projection, result is an array of section body objects. Each section body has output: string (generated section text), references: array, and match_score: integer (reference match count; 0 for agentic-generated sections). references is an array of source reference objects; each reference has source: string or null and url: string or null. Always provide projection as {'pipeline': [...]} using MongoDB aggregation syntax. Use $project for field selection and reshaping. Use $map when selecting fields from nested references. Use $slice or $limit to reduce large arrays. Do not project result.* paths; project output, references, match_score, and their nested fields directly. Use the smallest projection that returns only the fields needed to answer the user, because the projected result will be sent to an LLM.

get_search_queries_from_agent

ChatGPT

Maps an open-ended interest area onto experimentally validated search keywords by calling the workflow backend search-query agent, which tries candidate queries against live News/social-media APIs instead of guessing keywords. Call this before creating a News or social-media knowledge base whenever the user has not already supplied concrete search keywords.

ib_get_documents

ChatGPT

Return full document objects for use in a text-view component. Supports selection_ids to fetch a specific set of documents.

ib_search_documents

ChatGPT

Search across all knowledge bases attached to the project and return matching document ids. This returns ids only; use text-view endpoints for document text.

kb_search_documents

ChatGPT

Perform a full-text or metadata-restricted search inside the specified knowledge base. This endpoint returns full texts.

list_archived_insight_boosters

ChatGPT

List the caller's archived Insight Booster projects (soft-deleted). Use this when the user asks about previously archived projects or wants to restore one.

list_files

ChatGPT

List the files stored in the caller’s organization, each with its name, group, extension and size. Use it to discover the exact stored name to pass to file-consuming tools.

list_insight_booster_knowledge_bases

ChatGPT

List the Knowledge Bases attached to an Insight Booster project, with their current sync status.

list_insight_booster_report_templates

ChatGPT

List all AI-generated report templates in the caller's organization (compact form).

list_insight_boosters

ChatGPT

List the caller's Insight Booster projects in compact form. Use this to discover what projects exist before fetching details on a specific one.

list_knowledge_bases

ChatGPT

Knowledge Bases are structured text datasets indexed semantically, supporting querying, filtering, and RAG; once ready, one can be linked to Insight Booster projects. List the Knowledge Bases in the caller's organization. Use this to recover a knowledgeBaseId you no longer have, or to discover what Knowledge Bases exist before attaching one to an Insight Booster or inspecting it — do NOT guess an id. Each entry includes the id, name, status, document volume, creation/update timestamps, whether it is fed by a scheduled flow, and the Insight Booster projects it is linked to. Optionally pass nameContains to narrow the list by a case-insensitive name substring.

list_owned_insight_booster_report_templates

ChatGPT

List AI-generated report templates owned by the caller (subset of list_insight_booster_report_templates).

rename_insight_booster

ChatGPT

Rename an Insight Booster project.

rename_insight_booster_workbench

ChatGPT

Rename a workbench within an Insight Booster project.

reorder_insight_booster_workbenches

ChatGPT

Reorder workbenches within an Insight Booster project. Provide the desired final position list.

restore_insight_booster

ChatGPT

Restore a previously archived Insight Booster project so it appears in the active project list again.

run_scenario_analysis

ChatGPT

MCP version of generate_scenarios. Run a morphological scenario analysis for a scenario workbench, based on the trends/topics found by the radar workbench it references. Returns {'result': ...}. Projection is applied to the value inside result, not to the result envelope. Before projection, result is an object with dimensions: array and scenarios: array. dimensions lists the final dimensions (driving forces) and their options used to build the scenarios, each with id: string, title: string, enableAdditionalOptions: boolean, source: string ('user' or 'llm'), and options: array of {id: string, title: string, source: string}. scenarios is an array of ScenarioResult objects. Each scenario has id: string, title: string or null, description: string or null, dimensions: array, likelihood_rationale: string, likelihood_score: number (0-1), impact_rationale: string, impact_score: number (0-1), and highlighted: boolean. title and description are only generated for highlighted scenarios (both scores above the highlighting threshold); for all other scenarios they are null. A scenario's dimensions is an array of objects, each with label: string (the dimension title) and value: string (the title of the option chosen for that dimension). Always provide projection as {'pipeline': [...]} using MongoDB aggregation syntax. Use $project for field selection and reshaping. Use $map when selecting fields from nested arrays such as dimensions, scenarios, and options. Use $slice or $limit to reduce large arrays. Do not project result.* paths; project dimensions, scenarios, and their nested fields directly. Use the smallest projection that returns only the fields needed to answer the user, because the projected result will be sent to an LLM.

sample_kb

ChatGPT

Return a small sample of documents from the specified knowledge base for preview.

set_insight_booster_document_filter

ChatGPT

Set the document filter on an Insight Booster project. Replaces any previously configured document filter.

set_insight_booster_knowledge_base_filters

ChatGPT

Set the pre-filters for a single Knowledge Base attached to an Insight Booster project. Pre-filters scope which documents from that Knowledge Base feed downstream analyses. Replaces ALL of this Knowledge Base's pre-filters with the ones provided — include every filter you want to keep; an omitted kind (metadataFilters / semanticFilter / timestampFilter) is removed, and an empty call clears them all. Other Knowledge Bases are never affected.

set_insight_booster_metadata_filter

ChatGPT

Set the metadata filter on an Insight Booster project. Replaces any previously configured metadata filter.

set_insight_booster_timestamp_filter

ChatGPT

Set the timestamp (date-range) filter on an Insight Booster project.

update_insight_booster_bump_workbench_config

ChatGPT

Update the data configuration of a bump (trend-evolution) workbench (source type, broadness level, metadata field). The target workbench must be of type "bump" — call get_insight_booster_workbench first if the type isn't known. This tool validates field shape only, not meaning: a call can succeed and still leave a workbench that produces no real analysis. Which extra field is required depends on the source type — set the metadata field when the source is a document field, the broadness level when the source is topics, and both the radar source type and source workbench id when the source is a radar. Omitting the field the chosen source type needs still returns success.

update_insight_booster_landscape_workbench_config

ChatGPT

Update the data configuration of a landscape workbench (sizing/coloring fields, outlier policy, display flags). The target workbench must be of type "landscape" — call get_insight_booster_workbench first if the type isn't known.

update_insight_booster_matrix_workbench_config

ChatGPT

Update the data configuration of a matrix workbench (cell instruction, engine, row/column definitions). Per-row/column overrides (instruction, inputs, viewInputs) may be set on one axis only — on rows or on columns, never both. The target workbench must be of type "matrix" — call get_insight_booster_workbench first if the type isn't known. This tool validates field shape only, not meaning: a call can succeed and still leave a workbench that produces no real analysis. Row and column variables must be $-prefixed (e.g. $company, $country) and the cell instruction must literally contain both tokens as substrings. A missing $ is added silently to the variable names, but the instruction is never checked against them — an instruction with no matching tokens saves successfully and produces a matrix with no per-cell substitution.

update_insight_booster_radar_workbench_config

ChatGPT

Update the data configuration of a radar workbench (analysis mode, angular/radial/size axes, predefined segments). The target workbench must be of type "radar" — call get_insight_booster_workbench first if the type isn't known. This tool validates field shape only, not meaning: a call can succeed and still leave a workbench that produces no real analysis. The angular, radial and size scale parameters each accept three mutually exclusive ways to define an axis (an aggregated metadata field, an open-ended definition, or a raw metadata field as scale) — set exactly one per axis. The schema permits more than one, but only one takes effect.

update_insight_booster_report

ChatGPT

Update an AI-generated report. Pass templateId to update a saved template, or id + workbenchId to update the report attached to a workbench — exactly one of the two, never both. The name field applies to templates only. For a report workbench, this call — not an update_insight_booster_*_workbench_config tool — is how it gets configured.

update_insight_booster_research_bot_config

ChatGPT

Update the research-bot configuration for an Insight Booster project.

update_insight_booster_scenario_workbench_config

ChatGPT

Update the data configuration of a scenario workbench (dimensions/options scenarios are built from, generation language, focus, and the source radar workbench). The target workbench must be of type "scenario" — call get_insight_booster_workbench first if the type isn't known. This tool validates field shape only, not meaning: a call can succeed and still leave a workbench that produces no real analysis. It requires an existing Radar workbench in the same project — radarWorkbenchId is mandatory, and that Radar workbench's trends and segments seed scenario generation. If the project has no Radar workbench yet, create and configure one first, confirming with the user before creating it.

update_insight_booster_view

ChatGPT

Update an existing view on an Insight Booster project.

update_insight_booster_workbench_ui_config

ChatGPT

Update a workbench's UI configuration (color schemes, layout prefs, etc.).

validate_insight_booster_name

ChatGPT

Check whether a proposed Insight Booster project name is available in the caller's organization.

validate_insight_booster_report_name

ChatGPT

Check whether a proposed report template name is available in the caller's organization.

validate_insight_booster_view_name

ChatGPT

Check whether a proposed view name is available on the project (i.e. not already taken by another view).

wait_for_flow

ChatGPT

Wait for a KB flow run to finish. Blocks for up to maxWaitMs (default and maximum 25s) and returns as soon as the run reaches a terminal status. Prefer this over get_last_flow_run_status after any createXKb call. When done is false the run is still going — call this again with the same flowId; a News or Social KB typically takes ~10 minutes, i.e. ~24 consecutive calls, so do not stop after two. Do not hand back to the user between calls and do not narrate each one: state the flowId once when the build starts, then report again when done is true. On done the response carries knowledgeBaseId, or the failure reason in message. Calling it after a gap is safe and cheap — a run that finished meanwhile returns immediately, so a dropped wait can always be resumed from the flowId.

apply_project_filter

Claude

archive_insight_booster

Claude

ask_research_chatbot

Claude

attach_knowledge_base_to_insight_booster

Claude

check_kb_has_timestamp

Claude

clone_insight_booster

Claude

create_file_kb

Claude

create_insight_booster

Claude

create_insight_booster_report_template

Claude

create_insight_booster_view

Claude

create_insight_booster_workbench

Claude

create_news_kb

Claude

create_research_agent_kb

Claude

create_social_kb

Claude

delete_insight_booster_filter

Claude

delete_insight_booster_report_template

Claude

delete_insight_booster_view

Claude

delete_insight_booster_workbench

Claude

detach_all_knowledge_bases_from_insight_booster

Claude

detach_knowledge_base_from_insight_booster

Claude

fetch_project_metadata_schema

Claude

fetch_research_chatbot_conversation_history

Claude

generate_insight_booster_workbench_report_from_template

Claude

generate_report_sections_from_landscape

Claude

get_bump_result

Claude

get_file_by_name

Claude

get_file_upload_url

Claude

get_growth_result

Claude

get_insight_booster

Claude

get_insight_booster_research_bot_config

Claude

get_insight_booster_workbench

Claude

get_kb_field_statistics

Claude

get_landscape_max_broadness

Claude

get_landscape_result

Claude

get_last_flow_run_status

Claude

get_matrix_result

Claude

get_project_time_range

Claude

get_radar_result

Claude

get_report_result

Claude

get_search_queries_from_agent

Claude

ib_get_documents

Claude

ib_search_documents

Claude

kb_search_documents

Claude

list_archived_insight_boosters

Claude

list_files

Claude

list_insight_booster_knowledge_bases

Claude

list_insight_booster_report_templates

Claude

list_insight_boosters

Claude

list_knowledge_bases

Claude

list_owned_insight_booster_report_templates

Claude

rename_insight_booster

Claude

rename_insight_booster_workbench

Claude

reorder_insight_booster_workbenches

Claude

restore_insight_booster

Claude

run_scenario_analysis

Claude

sample_kb

Claude

set_insight_booster_document_filter

Claude

set_insight_booster_knowledge_base_filters

Claude

set_insight_booster_metadata_filter

Claude

set_insight_booster_timestamp_filter

Claude

update_insight_booster_bump_workbench_config

Claude

update_insight_booster_landscape_workbench_config

Claude

update_insight_booster_matrix_workbench_config

Claude

update_insight_booster_radar_workbench_config

Claude

update_insight_booster_report

Claude

update_insight_booster_research_bot_config

Claude

update_insight_booster_scenario_workbench_config

Claude

update_insight_booster_view

Claude

update_insight_booster_workbench_ui_config

Claude

validate_insight_booster_name

Claude

validate_insight_booster_report_name

Claude

validate_insight_booster_view_name

Claude

Capabilities

InteractiveWrites

Example Prompts

Click any prompt to copy it.

Links

Documentation ↗Privacy Policy ↗

App Stats

143

Tools

Prompts

ChatGPT, Claude

Platforms