Workspace

Aktiver Datenkontext und externe Zugänge.

API credentials

Endpoints and secrets used outside Sonaloop.

Reference & playground →

MCP endpoint

HTTP endpoint for MCP-compatible clients.

TypeEndpointScopeAll workspacesStatusStable
EndpointUse this URL in Claude Code, Claude.ai, ChatGPT or another MCP host.
https://api.sonaloop.com/mcp

MCP bearer token

Secret token bound to the active workspace.

TypeSecretScopeWorkspaceStatusUnavailable
Bearer tokenShown as Authorization: Bearer <token> in an MCP host.
<workspace-token>

Catalog token

Secret for premium catalog persona access.

TypeSecretScopePremium catalogStatusUnavailable
TokenUse as SONALOOP_CATALOG_TOKEN=<copied token>.
<catalog-token>

MCP role matrix

Compiled from the live MCP catalog: 293 functions.

Admin293 functions

Full MCP catalog for explicit workspace administration.

Workspace user84 functions

Normal interactive MCP surface for Claude Code and hosted clients.

Automation agent81 functions

Hosted automation runtime surface for server-side agent runs.

Function permissions
FunctionAdmin293 toolsWorkspace user84 toolsAutomation agent81 tools
add_artifactBring a REAL artifact into a project's council pool so personas react to what is ACTUALLY ...allowedallowedallowed
add_taskInsert a task into the plan (shape the breadth): bucket analyze|act|verify, a capability ...allowednot allowednot allowed
add_to_sectionAdd node ids to a section's membership (validated against the project graph).allowednot allowednot allowed
aggregate_predictionsThe segment roll-up of every predicted behavior in a project — grouped by (action, step, ...allowednot allowednot allowed
assess_coverageCoverage / diversity check over a study's PERSONA SET — a deterministic analysis that flags when ...allowednot allowednot allowed
assess_progressRecord an evidence-backed assessment of progress toward the HMW goal. `delta` is a free ...allowednot allowednot allowed
assess_projectProject-level meta-assessment (read-only, computed — no LLM verdict): coverage, open evi ...allowedallowedallowed
attach_assetAttach a file/image/screenshot to a project as citable evidence. Pass EITHER `path` (a l ...allowednot allowednot allowed
attach_evidenceAttach a real-world SOURCE (doc/url/note) to a persona to ground its claims.allowedallowedallowed
attach_prototype_shotScreenshot a registered prototype (Playwright) and attach the shot to the project as ima ...allowednot allowednot allowed
attach_survey_evidenceLoop the imported REAL responses back onto a persona as Evidence (source_type='survey') ...allowednot allowednot allowed
available_project_iconsExisting regular icons that Projects/Jobs can choose at initialization or edit time.allowednot allowednot allowed
brief_askGather one persona's loaded context (SOUL + recent events + task-keyed memory) so you ca ...allowednot allowednot allowed
brief_calibrationGather the MISSES (refuted bets, high-error predictions, each with its evidence trail) s ...allowednot allowednot allowed
brief_cohort_criticGATHER compact per-persona records across the cohort so you can judge which personas fal ...allowednot allowednot allowed
brief_completeness_criticGATHER a computed exhaustiveness snapshot for an INDEPENDENT critic: coverage + the gene ...allowednot allowednot allowed
brief_consolidationGATHER a simulated day + known entities. Returns instructions for you to author memory_d ...allowednot allowednot allowed
brief_councilGather a council. A council is scoped to a research project, so `project_id` is REQUIRED ...allowedallowedallowed
brief_dayGATHER context for planning ONE day (active projects, open threads, recall, world). Retu ...allowednot allowednot allowed
brief_digestGATHER a period for a consolidated digest (replaces hardcoded reflections).allowednot allowednot allowed
brief_eval_criticGATHER source+SOUL+sampled activities+arcs for a semantic critique. Author a verdict (an ...allowednot allowednot allowed
brief_evidence_checkGATHER profile claims + attached evidence to validate synthesis against reality.allowednot allowednot allowed
brief_flow_walkthroughGATHER one persona's artifact walkthrough: loaded persona context + the ordered screens ...allowednot allowednot allowed
brief_groundingGather the chunks + authoring contract to ground a persona in real material. WITHOUT per ...allowednot allowednot allowed
brief_head_to_headGather a HEAD-TO-HEAD (X vs Y) — run the panel on a DIRECT comparison of two (or more) concrete ...allowedallowedallowed
brief_hypothesisGATHER what is worth betting on: the project's contested findings (councils whose statem ...allowedallowedallowed
brief_monthGATHER context to author a whole month bundle (period plan + sample days + digest), chai ...allowednot allowednot allowed
brief_nextGATHER what the plan's ready frontier needs now: the primary ready task (+ the full ready ...allowednot allowednot allowed
brief_periodGATHER context for a week|month|quarter|year plan, incl. candidate sample days. Author a ...allowednot allowednot allowed
brief_personaGather the prompt + frame to AUTHOR one persona profile from a source description. You w ...allowedallowedallowed
brief_persona_revisionGATHER evidence (digests/facts) to propose SLOW identity drift. Change is the exception.allowednot allowednot allowed
brief_price_ladderGather a PRICE LADDER (pricing Job protocol — willingness-to-pay): a FIXED ascending ladder of ...allowednot allowednot allowed
brief_prototype_sessionGATHER persona context + how-to-drive + anti-steering before a persona uses the app.allowednot allowednot allowed
brief_red_teamGather a RED-TEAM (falsification) — run the panel to ATTACK the idea instead of flattering it ...allowedallowedallowed
brief_surveyGATHER everything needed to author a survey that is answerable against the graph: the pr ...allowedallowedallowed
brief_synthesisGATHER an ordered chain of councils (their exec_summaries/votes) so you can author a cro ...allowedallowedallowed
brief_synthesis_outlineGATHER the whole project graph + study content so you can author the project REPORT outline.allowedallowedallowed
brief_synthesis_sectionGATHER one section's source studies (+ councils) so you can author it with citations.allowedallowedallowed
brief_usability_sessionGATHER persona context (SOUL + state + task-keyed memory) + anti-steering framing + the ...allowednot allowednot allowed
calibration_reportMeasure calibration NOW (mean Brier + hit rate + the reliability curve over scored predi ...allowednot allowednot allowed
calibration_trendCalibration quality OVER TIME: the persisted report series, the Brier delta first→last, ...allowednot allowednot allowed
catalog_pullPull catalog personas (by slug and/or archetype `pack`) into the CURRENT store — profile ...allowedallowedallowed
catalog_recommendDeterministic, explainable persona-SET recommendation over the catalog (no LLM): spec = ...allowedallowedallowed
catalog_searchBrowse the curated persona catalog (github:jhoetter/sonaloop-data): slugs, names, roles ...allowedallowedallowed
catalog_statusThe `git fetch && git status` of the catalog: for every catalog-pulled persona in the CU ...allowedallowedallowed
chat_with_personaChat with ONE persona, durably. Returns the loaded agent context + prior turns; YOU auth ...allowedallowedallowed
checkpoint_stepAppend a completed step (task_id, bucket, key, evidence ids, 1-line summary) to the journal.allowedallowedallowed
cloud_add_memberAdd (or update) a member: owner | editor | viewer.allowednot allowednot allowed
cloud_archive_design_assetArchive an asset record without deleting content-addressed bytes.allowednot allowednot allowed
cloud_close_survey_shareClose/revoke a hosted survey share link. Existing responses stay in the survey graph.allowedallowedallowed
cloud_configure_automationSave workspace-specific settings for an automation. Scheduled triggers such as CRON use ...allowedallowednot allowed
cloud_create_automationCreate or update a structured automation definition. This is the MCP-first natural-langu ...allowedallowednot allowed
cloud_create_design_system_draftValidate and persist a draft v2 design-system version without publishing it.allowednot allowednot allowed
cloud_create_workspaceCreate a workspace with its first owner (subject = the user's OIDC `sub`).allowednot allowednot allowed
cloud_get_automation_runFetch one automation run with its append-only event trace. Linked hosted agent runs are ...allowedallowedallowed
cloud_list_automationsList Cloud automation definitions in the active workspace. Automations are structured DA ...allowedallowedallowed
cloud_list_design_assetsList assets in the workspace design-system library.allowednot allowednot allowed
cloud_list_design_system_auditList governance events for workspace design-system drafts, assets, publishes and exports.allowednot allowednot allowed
cloud_list_design_system_versionsList the workspace design-system version history.allowednot allowednot allowed
cloud_list_survey_sharesEvery hosted survey share in the active workspace, optionally filtered by survey_id.allowedallowedallowed
cloud_list_workspacesEvery workspace with its members (row tenancy: a project belongs to a workspace by its w ...allowednot allowednot allowed
cloud_publish_design_system_versionPublish one draft design-system version and archive the prior published version.allowednot allowednot allowed
cloud_publish_surveyPublish a core survey as a hosted Cloud share link. Core already owns survey authoring/e ...allowedallowedallowed
cloud_remove_memberRemove a member (the last owner cannot be removed).allowednot allowednot allowed
cloud_rollback_design_system_versionRestore an earlier published/archived design-system version for a workspace.allowednot allowednot allowed
cloud_set_design_systemSet (or clear, with null/{}) and publish the workspace's v2 customer design system. The ...allowednot allowednot allowed
cloud_set_member_roleChange a member's role (the last owner cannot be demoted).allowednot allowednot allowed
cloud_start_automationStart one concrete automation run. The returned run id is the audit handle; inspect it w ...allowedallowednot allowed
cloud_upload_design_assetUpload a logo/font/image asset. content_base64 is decoded and validated server-side.allowednot allowednot allowed
cloud_validate_design_system_versionReturn the publish validation report for one design-system version.allowednot allowednot allowed
cohort_memory_depthHow deep is the cohort's simulated memory (avg facts+events/persona)? A thin cohort should be ...allowednot allowednot allowed
complete_taskMark a ready task done. Verify tasks are gate-checked (breadth + gate judgment + artifacts/ ...allowednot allowednot allowed
create_noteCreate a lightweight NOTE node — the ONE note entity (from a raw observation to a worked-out ...allowedallowedallowed
create_research_projectCreate a research Project: a themed GRAPH of studies (syntheses). Distinct from the memo ...allowednot allowednot allowed
create_sectionCreate a labeled overlay grouping of graph nodes (e.g. 'Initial user research', 'Problem ...allowednot allowednot allowed
define_flowDefine an ORDERED flow from the project's screenshot assets — each step is {asset_id, ca ...allowednot allowednot allowed
delete_artifactRemove an artifact (by id or label) from a project's pool.allowednot allowednot allowed
delete_councilDelete a council session.allowednot allowednot allowed
delete_noteDelete a note node from the project.allowednot allowednot allowed
delete_personaDelete a persona + all its persona-scoped rows and rendered SOUL/avatar files.allowedallowedallowed
delete_prototypeDelete a prototype artifact record (files on disk are kept).allowednot allowednot allowed
delete_research_projectDelete a project container + its edges/open-questions. Syntheses (incl. reports) are kept.allowednot allowednot allowed
delete_sectionDelete a section. Member nodes are kept (reference, not containment).allowednot allowednot allowed
delete_synthesisDelete a synthesis (study) and detach it from any project graphs.allowednot allowednot allowed
derive_sectionsAuto-organize: derive persisted SECTION overlays from the plan — one per methodology phase ...allowednot allowednot allowed
describe_frameworkOne Framework's plain-language description by stable id (e.g. 'double_diamond'): {id, na ...allowednot allowednot allowed
drop_hypothesisRetire an OPEN bet without scoring it (the question became moot, the metric unmeasurable ...allowednot allowednot allowed
eval_scorecardAggregate the hit-rate across RESOLVED hypotheses (per project, or global with a per-pro ...allowednot allowednot allowed
evaluate_cohort_diversityStructural bulk-generation gate: flag near-duplicate personas and implausibly uniform co ...allowednot allowednot allowed
evaluate_simulationRun the quality harness (uniformity, repetition, continuity, project movement, consisten ...allowednot allowednot allowed
evaluate_simulation_fullCombined 'top' verdict: structural harness + latest LLM critic (definition v2).allowednot allowednot allowed
export_council_sessionExport one council session as a document (md|json) for sharing.allowednot allowednot allowed
export_personaExport one persona (profile + SOUL/memory) as json/markdown.allowednot allowednot allowed
export_plan_mdRender the plan as a human-readable, bucketed plan.md (analyze/act/verify + status + gates).allowednot allowednot allowed
export_sectionSelf-contained export of a section (md|json): its members' summaries, for a downstream agent.allowednot allowednot allowed
export_surveyRender the survey as a SENDABLE, self-contained static HTML form (spa-min template) — wo ...allowedallowedallowed
export_synthesisExport a report (synthesis). format: `md`|`json` returned inline · `pdf`|`pptx` rendered as a ...allowedallowedallowed
export_synthesis_htmlExport a report (synthesis) as a SHAREABLE read-only static HTML bundle — `data/export/s ...allowedallowedallowed
extract_pain_pointsSurface a persona's pain-point observations over a date range.allowednot allowednot allowed
fetchFetch ONE research record by id (a project/council/synthesis/hypothesis/persona id, e.g. ...allowedallowedallowed
finish_runMark the run finished/stopped.allowedallowedallowed
flow_funnelThe segment funnel of one flow: per step entered/continued/dropped with the drop reasons ...allowednot allowednot allowed
generate_avatarGenerate (or regenerate) the persona's avatar image — needs OPENAI_API_KEY. Without the ...allowedallowedallowed
generate_project_iconCreate a fitting custom SVG icon for a Project/Job from its title/goal plus an optional ...allowednot allowednot allowed
get_activityFetch one simulated activity (block) by id.allowednot allowednot allowed
get_artifactOne artifact (by id or A/B label) with its full captured snapshot.allowednot allowednot allowed
get_assetOne asset record (by id or filename) — includes the text excerpt for documents.allowednot allowednot allowed
get_calendarA persona's calendar events for one day.allowednot allowednot allowed
get_calendar_periodA persona's calendar for a day|week|month|year view — LEAN event rows (id/timestamp/even ...allowednot allowednot allowed
get_chatOne chat with its full turn history.allowednot allowednot allowed
get_corpusOne corpus record; include_chunks=True adds a PAGE of chunks (`chunk_list`, shared pagin ...allowednot allowednot allowed
get_councilFetch one council session by id (prompt, turns/statements, votes, summary).allowedallowedallowed
get_current_stateA persona's live state — what they're doing now / at a given time.allowednot allowednot allowed
get_day_planFetch the stored day plan for a persona on a given date.allowednot allowednot allowed
get_decisionOne decision record by id — what was decided, the evidence cited (based_on), the rejecte ...allowedallowedallowed
get_formInspect one registered primitive form by canonical id or compatibility alias.allowednot allowednot allowed
get_head_to_headFetch one head-to-head result by session id — its options, per-persona preferences, the ...allowedallowedallowed
get_hypothesisOne hypothesis by id — the bet, its prediction, and (once resolved) the recorded result ...allowedallowedallowed
get_ideationFetch one ideation summary by session id — problem, HMW questions, idea pool, ranked sho ...allowednot allowednot allowed
get_job_presetOne Job preset by stable taxonomy id (e.g. 'positioning'): framework + framework_options + ...allowednot allowednot allowed
get_languageRead the active content language (host-authored text) and UI language.allowedallowedallowed
get_methodologyThe full constellation spec for one methodology (steps, tags, consumes, produces, requires).allowednot allowednot allowed
get_open_loopsA persona's unresolved threads / open loops (filter by status).allowednot allowednot allowed
get_period_planFetch a stored period plan (week|month|quarter|year) for a persona.allowednot allowednot allowed
get_personaFull persona record + recent calendar/experience/pain points.allowedallowedallowed
get_persona_memoryRender + return MEMORY.md: active projects (timelines), open threads, digests.allowednot allowednot allowed
get_persona_soulThe persona's SOUL.md (authoritative identity + grown drift).allowednot allowednot allowed
get_planThe project's research plan (analyze/act/verify task DAG + evidence refs + judgments).allowedallowedallowed
get_price_ladderFetch one price-ladder result by session id — the ladder, the raw per-persona/per-rung banded ...allowednot allowednot allowed
get_projectFull fact/status timeline of one project (use `as_of` for how it looked then).allowedallowedallowed
get_project_graphThe core navigation call: nodes (studies + theme tags + sentiment), typed edges, themes, ...allowednot allowednot allowed
get_prototypeOne prototype artifact by id or slug.allowednot allowednot allowed
get_red_teamFetch one red-team result by session id — its stance, adversarial roles, per-persona objections ...allowedallowedallowed
get_research_frontierThe anti-explosion surface: the project's still-open questions + structural notes.allowednot allowednot allowed
get_result_schemaOne domain-neutral result schema by id, e.g. stimulus_reaction.v1.allowednot allowednot allowed
get_sectionGet one section by id.allowednot allowednot allowed
get_section_membersResolve a section's members into {kind,title,summary,href} records (section-scoped view).allowednot allowednot allowed
get_session_funnelAggregate ALL usability sessions of one subject into a step-indexed funnel: per step the ...allowednot allowednot allowed
get_state_atTime-travel: entities + facts + open threads + world valid at a given date.allowednot allowednot allowed
get_study_resultONE structured study result: lean project row + run state + council rows + the FULL synt ...allowednot allowednot allowed
get_surveyOne survey by id or slug — the instrument document + its live response_count.allowedallowedallowed
get_synthesisFetch one report (synthesis) by id — its findings/sections/scope and metadata.allowedallowedallowed
get_timelineChronological facts + experience events for a persona over a date range (optionally one ...allowednot allowednot allowed
get_usability_sessionOne recorded usability session by id — the full replayable trace (steps + outcome + stat ...allowednot allowednot allowed
get_world_contextThe shared world context (macro facts personas live in) valid at a given date.allowedallowedallowed
import_survey_responsesIngest a batch of REAL responses — a JSON list (the export form's payload shape: {respon ...allowedallowedallowed
ingest_corpusIngest one REAL document (interview transcript, support-ticket export, review dump, surv ...allowednot allowednot allowed
inject_workTurn one critic `missing` item {kind, what, ...} into a real plan task/open-question (the ...allowednot allowednot allowed
iterate_taskOpen the NEXT iteration round on a done-or-ready task with a `loop_back` target (HOST-judged ...allowednot allowednot allowed
link_evidenceAttach an evidence ref (kind=council|synthesis|artifact|session, id) to a task (usually the ...allowednot allowednot allowed
list_active_projectsCompact list of the persona's open projects with status + open-loop counts.allowedallowedallowed
list_artifactsList every artifact ingested into a project (id, label A/B/…, kind, url, capture status).allowedallowedallowed
list_assetsEvery asset attached to a project (lean records; excerpt via get_asset, pixels via view_ ...allowednot allowednot allowed
list_chatsPaginated lean chat rows (newest first), optionally scoped to one persona.allowednot allowednot allowed
list_corporaEvery ingested corpus (id, title, source_type, chunk count).allowednot allowednot allowed
list_councilsList council sessions (id, prompt, persona count, votes), newest first. Paginated per th ...allowedallowedallowed
list_decisionsList decision records (optionally per project and/or status: proposed|adopted|superseded ...allowedallowedallowed
list_digestsList a persona's consolidated digests (optionally filtered by scope).allowednot allowednot allowed
list_examplesThe example projects shipped with Sonaloop: slug, title, one-line tagline, and whether e ...allowedallowedallowed
list_flowsEvery defined flow on a project (id, title, step count).allowednot allowednot allowed
list_formsList registered primitive forms, optionally filtered by primitive id.allowednot allowednot allowed
list_frameworksThe Frameworks (the methodologies that seed a study's plan) in PLAIN LANGUAGE, as one clean ...allowednot allowednot allowed
list_hooksAll durable hook registrations (id, event pattern, kind, target, label).allowednot allowednot allowed
list_hypothesesList hypotheses (optionally per project and/or status: open|validated|refuted|inconclusi ...allowedallowedallowed
list_ideasThe project's idea records, filterable by HMW question, source persona, or cluster tag — ...allowednot allowednot allowed
list_job_presetsThe Job presets — one per named research Job (positioning, pricing, jtbd_demand, ideation_hmw, ...allowednot allowednot allowed
list_lifecycle_eventsThe documented lifecycle-event catalogue the core emits (persona.created, council.record ...allowednot allowednot allowed
list_memory_anomaliesFlagged memory anomalies (contradictions / integrity issues), optionally per persona.allowednot allowednot allowed
list_methodologiesList available methodologies (built-in + user-defined) and their step keys.allowednot allowednot allowed
list_notesList a project's note nodes in creation order. Paginated per the shared convention (docs ...allowedallowedallowed
list_period_plansList a persona's period plans (optionally filtered by scope).allowednot allowednot allowed
list_persona_revisionsThe history of evidence-backed identity revisions for a persona.allowednot allowednot allowed
list_personasLean one-line overview of personas (slug/name/age/role/segment) — drill in with get_pers ...allowedallowedallowed
list_primitivesList registered Library primitives with family, icon, color and purpose metadata.allowednot allowednot allowed
list_proto_sessionsList live browser sessions.allowednot allowednot allowed
list_prototypesList registered prototype artifacts (optionally for one project).allowednot allowednot allowed
list_research_projectsList research projects (graph containers) with study/edge/theme counts.allowedallowedallowed
list_result_contractsList the output contracts declared for Jobs and methodologies.allowednot allowednot allowed
list_result_schemasList domain-neutral result schemas plus registry validation errors.allowednot allowednot allowed
list_sectionsList a project's sections (ordered).allowednot allowednot allowed
list_surveysList surveys (optionally per project), each with its live response_count.allowedallowedallowed
list_synthesesList all reports (syntheses) — id, title, scope, date — for browsing.allowedallowedallowed
list_usability_sessionsList recorded usability sessions, optionally filtered by project, persona and/or subject ...allowednot allowednot allowed
load_exampleLoad one shipped example project end-to-end (empty slug = list what's available). Idempo ...allowedallowedallowed
next_actionThe ready task FULLY loaded for a lean autonomous loop: analyze→grounding (prior synthes ...allowedallowedallowed
park_evidenceExplicitly park evidence that should remain visible but should NOT flow into a downstream ...allowednot allowednot allowed
prepare_persona_agent_contextBuild the launch context for a persona subagent (SOUL + state + recent events).allowedallowedallowed
price_ladder_analysisThe analytics shape of a recorded price ladder: acceptable-price range + cliff points, overall ...allowednot allowednot allowed
project_result_contract_stateShow which expected result schemas are recorded or still missing for a project.allowednot allowednot allowed
proto_actAct on the latest snapshot: {type: click|type|select|scroll|key|wait, ref?, text?, value?}.allowednot allowednot allowed
proto_closeClose a browser session.allowednot allowednot allowed
proto_openOpen a real running app in a headless browser session; returns {session_id, snapshot}. W ...allowednot allowednot allowed
proto_readRe-read the current snapshot of a session.allowednot allowednot allowed
put_day_planPersist the day plan you authored from brief_day.allowednot allowednot allowed
put_digestPersist + embed the digest you authored from brief_digest.allowednot allowednot allowed
put_period_planPersist a period plan (its sample_days drive which days you simulate concretely).allowednot allowednot allowed
query_councilsPaginated lean council rows; filter by project, participant, free text, `since`.allowednot allowednot allowed
query_personasPaginated lean persona rows, filterable by free text. Stable ordering + next_offset.allowedallowedallowed
query_projectsPaginated lean research-project rows; filter by status, free text, and `since` (ISO lowe ...allowednot allowednot allowed
query_synthesesPaginated lean synthesis rows (the answer/report nodes); filter by status, text, `since`.allowednot allowednot allowed
recall_memoryHybrid (semantic + keyword/entity + recency + importance) recall over episodes, facts, d ...allowednot allowednot allowed
record_actuation_gateThe fidelity-vs-theater head-to-head: compare a rung-1 artifact walkthrough against a ru ...allowednot allowednot allowed
record_calibration_roundStamp one authored correction round ({persona_id, text, refs?} each) and snapshot a fres ...allowednot allowednot allowed
record_chat_turnPersist one authored chat exchange (the durable, queryable artifact). Emits the `chat.re ...allowedallowedallowed
record_cohort_criticPersist the host-authored cohort critique (outliers + cohort_note) as an eval report + a ...allowednot allowednot allowed
record_completeness_criticPersist the independent critic verdict {scores, passed, missing[{kind,what,why, suggeste ...allowednot allowednot allowed
record_councilPersist a host-authored council. Shape it by what you pass (the UI derives the mode): DI ...allowedallowedallowed
record_critic_roundLog one completeness-critic round on the run (loop-until-dry observability).allowednot allowednot allowed
record_dayPersist a host-authored SINGLE day end-to-end (put_day_plan -> simulate the authored blo ...allowednot allowednot allowed
record_decisionPersist a host-authored decision record — "we decided X, based on syntheses A and B, rej ...allowedallowedallowed
record_eval_criticPersist the host-authored critic verdict; flags low dimensions + items as anomalies.allowednot allowednot allowed
record_evidence_checkPersist provenance verdict: confirmed/contradicted/unsupported; flags contradictions.allowednot allowednot allowed
record_frameDischarge an ANALYZE frame task: author research questions + hypotheses grounded in cited ...allowednot allowednot allowed
record_groundingPersist authored grounding: optional profile patch + the provenance map (claim → chunk i ...allowednot allowednot allowed
record_head_to_headPersist a host-authored HEAD-TO-HEAD (stored as a CouncilSession with a `head_to_head` block). ...allowedallowedallowed
record_hmw_reframeREFRAME (ideation_hmw protocol step 1): persist your How-Might-We reframe of a raw problem — ...allowednot allowednot allowed
record_hypothesisPersist a host-authored hypothesis with status=open — the bet stamped BEFORE reality ans ...allowedallowedallowed
record_hypothesis_resultAttach the REAL-WORLD observation and flip the status. `source` is a Ref that must RESOL ...allowedallowedallowed
record_ideasDIVERGE (step 2): persist council-generated ideas as first-class, queryable idea records. ...allowednot allowednot allowed
record_ideation_summaryCONVERGE (step 3): persist the FORCED ranking as an ideation summary. `shortlist` is your ...allowednot allowednot allowed
record_job_outcomePersist one project-owned schema outcome as a job completion milestone.allowednot allowednot allowed
record_judgmentRecord an evidence-backed LLM gate judgment on a plan TASK (usually a verify task). `gate_tag` ...allowednot allowednot allowed
record_memory_deltasPersist host-authored memory deltas: resolves/dedupes entities, writes bi-temporal facts ...allowednot allowednot allowed
record_month_bundlePersist a host-authored month bundle through the full loop (plan->sample days-> simulate ...allowednot allowednot allowed
record_open_questionsPromote open questions raised by a study into first-class graph nodes.allowednot allowednot allowed
record_personaValidate + persist the persona profile you authored from brief_persona. This is the crea ...allowedallowedallowed
record_persona_revisionPersist evidence-backed identity drift (re-renders SOUL); source identity preserved.allowednot allowednot allowed
record_prediction_outcomeMatch ONE real outcome to one predicted behavior and score it. prediction_ref: {kind: se ...allowednot allowednot allowed
record_price_ladderPersist a host-authored PRICE LADDER (stored as a CouncilSession with a `price_ladder` block). ...allowednot allowednot allowed
record_prototype_sessionPersist a persona's grounded prototype use as an experience + memory + artifact; rejects ...allowednot allowednot allowed
record_red_teamPersist a host-authored RED-TEAM (stored as a CouncilSession with a `red_team` block). Pass the ...allowedallowedallowed
record_surveyPersist a host-authored survey. `questions` = [{id?, text, kind: single|multi|scale|text, ...allowedallowedallowed
record_synthesisPersist/UPDATE a host-authored synthesis. A synthesis is DECOUPLED from councils: `counc ...allowedallowedallowed
record_synthesis_outlinePersist the host-authored report outline (sections derived from the graph).allowedallowedallowed
record_synthesis_sectionPersist one authored report section. `content`: {markdown, citations:[{study_id|council_id}], ...allowedallowedallowed
record_usability_sessionPersist a host-authored usability session — the durable, REPLAYABLE trace (the session is ...allowednot allowednot allowed
refresh_persona_from_sourceRefresh a persona from where it came from. Catalog-pulled personas re-pull from their re ...allowedallowedallowed
register_hookSubscribe a durable hook to a lifecycle event. `event` is an exact name, 'domain.*', or ...allowednot allowednot allowed
register_methodologyRegister a USER-DEFINED methodology — author your own constellation and it becomes a Fra ...allowednot allowednot allowed
register_prototypeRegister a hand-authored app under prototypes/ as a runnable artifact (fidelity tag, e.g. lofi|m ...allowednot allowednot allowed
remove_assetDetach an asset from a project (by id or filename).allowednot allowednot allowed
remove_exampleRemove ONE example project's entities — and nothing else. Every id is re-derived from th ...allowednot allowednot allowed
remove_from_sectionRemove node ids from a section's membership (nodes themselves are untouched).allowednot allowednot allowed
reorder_sectionsSet the display/outline order of a project's sections.allowednot allowednot allowed
resolve_entityResolve a free-text mention to an existing entity (dedup), or null if new.allowednot allowednot allowed
result_contract_for_jobThe expected result schemas for one Job.allowednot allowednot allowed
result_contract_for_methodologyThe expected result schemas a methodology usually produces.allowednot allowednot allowed
run_journalThe run's journal (steps + critic rounds + cursor + status) — the source of truth for resume.allowednot allowednot allowed
run_prototypeStart the app on an ephemeral localhost port; returns {url, pid}. Local-only.allowednot allowednot allowed
run_stepThe ESV driver's brain (deterministic). Returns the next dispatch to execute: {kind: ana ...allowedallowedallowed
scaffold_prototypeGenerate a real, minimal, runnable web app from a host-authored concept and register it. ...allowednot allowednot allowed
scaffold_synthesisSeed a project REPORT outline from the project's phases so the conclusion hand-off is one author ...allowedallowedallowed
score_runPersist a RunScore (critic rubric scores + finish + novelty + groundedness + memory depth) so ...allowednot allowednot allowed
searchFind the workspace's research records (projects, councils, syntheses, hypotheses, person ...allowedallowedallowed
search_corpusKeyword search over corpus chunks — pull the real signal relevant to a task (determinist ...allowednot allowednot allowed
search_entitiesFind a persona's memory entities by kind and/or name substring.allowednot allowednot allowed
set_languageSet the content language (de|en) for generated text and/or the web UI language. By defau ...allowedallowedallowed
set_note_dataMerge keys into a note's `data` — e.g. set a concept note's `prototype_id` once you build it, ...allowednot allowednot allowed
set_project_iconReplace a Project/Job icon. Use `icon=<existing name>`, `randomize=True`, or pass a cust ...allowednot allowednot allowed
set_project_methodologyBind an existing research project to a methodology by (re)seeding its plan from the cons ...allowednot allowednot allowed
set_project_result_schemasSet the project-owned result schema contract that must be satisfied before the job is done.allowednot allowednot allowed
set_section_membersBulk-set a section's membership — the 'promote this cluster into a named section' move.allowednot allowednot allowed
set_world_contextSet exogenous backdrop facts (season, regulation, market...). Not shared persona knowledge.allowedallowedallowed
sharpen_questionTurn a FUZZY goal into a well-formed study — deterministically (no server-side text-LLM). ...allowednot allowednot allowed
start_job_studyStart a study FROM a Job preset: seeds the plan through the preset's default Framework (or any ...allowednot allowednot allowed
start_projectTHE ENTRY POINT. Create a project + seed its research plan (methodology -> analyze/act/verify ...allowedallowedallowed
start_runCreate (or resume) the run object — the SINGLE entry to the governed loop. Returns the run + ...allowedallowedallowed
stop_prototypeStop a running prototype.allowednot allowednot allowed
substrate_schemaThe versioned substrate contract (envelope, row schemas, filters, the chat flow, the acc ...allowednot allowednot allowed
suggest_artifact_typesSUGGESTED artifact-type tags for produces.artifact_type / requires.*_tags (matched by ta ...allowednot allowednot allowed
suggest_capabilitiesSUGGESTED capability tags (explore/cluster/decide/build/test/synthesize, …) for a step's ...allowednot allowednot allowed
suggest_chart_kindsWhich report CHART to use when (bar, pie, stacked_bar, diverging_bar, gauge, dot_plot, h ...allowednot allowednot allowed
suggest_finding_kindsSUGGESTED Finding kinds (summary/key_problem/pain_solver/open_question/recommendation/ c ...allowednot allowednot allowed
suggest_formsShow the registered forms, schemas, renderers, aggregators and alias policy for one primitive.allowednot allowednot allowed
suggest_friction_levelsThe CANONICAL per-step friction vocabulary for usability sessions — call this before aut ...allowednot allowednot allowed
suggest_likelihood_levelsThe CANONICAL likelihood vocabulary for predicted behaviors (rare → certain, each with t ...allowednot allowednot allowed
suggest_methodologiesSUGGESTED whole-constellation templates to copy and adapt (the registered methodologies ...allowednot allowednot allowed
suggest_rolesSUGGESTED role tags for a step's produces.role. Recommendations only.allowednot allowednot allowed
suggest_section_kindsSuggested section kinds + presentation (data-driven; adopt/tweak/invent).allowednot allowednot allowed
suggest_stancesThe CANONICAL stance vocabulary — call this before authoring statement stances, votes, or ...allowednot allowednot allowed
suggest_tech_comfortThe CANONICAL tech-comfort vocabulary for a persona's capability profile (capabilities.t ...allowednot allowednot allowed
summarize_persona_periodGather a persona's experience over a date range (optional lens) for summarisation.allowednot allowednot allowed
survey_resultsPer-question aggregates of the imported responses — and for stance_mapped questions the ...allowedallowedallowed
test_hookFire a sample envelope through one registered hook and report delivery success — the ver ...allowednot allowednot allowed
trace_evidenceResolve a cited evidence chunk id back to its source: the chunk text, its corpus, and ev ...allowednot allowednot allowed
unregister_hookRemove one durable hook registration by id.allowednot allowednot allowed
update_decisionFlip a decision's status (proposed|adopted) — or supersede it: `superseded_by` names the ...allowednot allowednot allowed
update_personaApply a host-authored patch to a persona's profile; records a revision with the reason. ...allowedallowedallowed
update_sectionUpdate a section (title/kind/parent_id/order/presentation/note/member_ids).allowednot allowednot allowed
view_assetLOOK at an asset. For an image/screenshot this returns the actual image — view it before ...allowednot allowednot allowed
walk_openOpen a LIVE walkthrough session on a real SaaS URL under the WalkPolicy safety contract ...allowednot allowednot allowed
walk_ownRung 2 — drive a live surface WE OWN: pass `prototype_id` (the scaffolded app is started ...allowednot allowednot allowed
walk_policy_defaultsThe safe default WalkPolicy walk_open applies when none is passed — origin-locked to the ...allowednot allowednot allowed
open

Feedback

Sent along, transparently: Page · Version 0.2.0

Or open a GitHub issue ↗