zerowidth.ai

Search ZeroWidth product documentation.

Fetch the full Markdown body of a specific docs page by its slug.

Enumerate all available docs pages, optionally filtered by product (e.

One dataset with a page of its items — read this BEFORE editing items (caliper_datasets_update_item needs the item id) and before extending coverage, so you don't add cases that already exist.

Changes a dataset's title, description, or visibility.

Deletes a dataset.

Rewrites one item's content, keeping its id (ratings and eval results keyed to it stay attached).

Drops one item.

Creates a NEW dataset of model-written items — Q&A by default, or scripted sequences / simulated people via `shape` — pass flowId and the generator reads the flow's prompt, mode, and schema to write realistic cases for THAT flow; `description` adds guidance (or stands alone when there's no flow).

Appends model-written items to an EXISTING dataset, in the style of what's already there (existing items are the few-shot examples; the output shape matches theirs unless overridden).

Lists the rubrics in the active workspace (id, name, description, criterion count).

One rubric with its criteria — each criterion's name, what the judge looks for, and the score scale.

Changes a rubric's title, description, visibility, or replaces its criteria wholesale (pass the FULL list — criteria get fresh ids).

Deletes a rubric.

One eval: what it targets (Workbench flow + stage, or external), its dataset and rubric ids, the rubric criteria it scores with (the snapshot taken at creation), schedule + runOnPublish + regression settings, run counts, latest score, and `binding` health (datasetOk / flowOk false = a run would fail at resolution — say so before proposing caliper_evals_run).

What the flow actually DID on one run item: every step in order (what it said, which tools it called with what arguments, what came back) and the final answer, plus status, duration, and cost.

Changes an eval's title, description, visibility, schedule (interval + time anchor), runOnPublish (queue a run whenever the flow publishes), or regressionThreshold (score drop vs the previous run that triggers an alert; null = off).

Deletes an eval and stops its schedule.

Stops a run that is still PENDING / RUNNING / SCORING — the brake on a run that's spending more than expected or was started by mistake.

Apps sending their agent's traces to Caliper — from their own code, OpenTelemetry, or a published Workbench flow — busiest first: name, how it sends, traces in the last 14 days (per day), and the tools its agent calls most with the share of traces using each.

One source day by day: traces, failures, tool calls, lookups that found nothing, tokens, cost, and speed (meanMs; p50/p95 as 'answered within' bucket edges); each tool with its calls and the share of each day's traces that used it; the documents lookups landed on most; models used.

The traces behind a point on a source's chart, newest first, 50 a page: the question and answer (cut short), tools called, time, tokens, cost, status.

One trace: what came in, what went out, and every step in order — model calls (model, tokens, cost, reasoning), tool calls (arguments and result), lookups (query and documents with scores), anything else — each with timing and status.

Datasets this source keeps adding to as conversations arrive: which dataset, for what (review, eval, spec), the pick it matches, sampling, how many have landed, and whether it's still running or why it stopped.

Saves the conversations behind a pick (a day, a tool, a document, failures — the same narrowing as caliper_traces_list) into a new dataset (newDatasetName) or an existing one (datasetId), newest first up to `limit`.

Stops a source from adding new conversations to a dataset.

The starter sets Caliper ships: prompt injection, system-prompt leaking, over-refusal, personal-data handling, bias under ambiguity.

Copies one starter into the workspace as a new dataset and a new rubric the user owns and can edit.

Lists datasets in the active workspace.

How a Workbench flow is ACTUALLY doing, with receipts: every Caliper eval targeting the flow, recent runs with scores, the latest run decomposed into per-criterion averages, the score delta vs the previous run, and the worst-scoring items WITH the judge's reasoning.

Recent runs for one eval, newest first: status (PENDING/RUNNING/SCORING/DONE/FAILED), overall score once DONE, label, and timestamps.

One run: status, overall score, and by default the ten lowest-scoring items with their per-criterion scores and the judge's reasoning (`items: all` for every item, `none` for totals only).

Lists evals in the active workspace with their target config (which Workbench flow, which dataset/rubric).

Queues a new run of an eval — inference over the dataset, then LLM-judge scoring.

Creates a dataset of test items — THE FIRST STEP of setting up evaluation for a flow.

Appends items to an existing dataset — use this to grow coverage (new edge cases, scenarios from a completed interview) instead of creating a parallel dataset.

Creates the scoring rubric an eval's LLM judge uses — 1-10 criteria, each scored on a numeric scale (default 1-5), judged pass/fail (kind pass_fail), or checked in code with no judge (kind check: contains, not_contains, matches a regex, valid_json, max_chars, equals_expected).

Binds a dataset + rubric to something under test as a repeatable eval — THE LAST SETUP STEP before scoring.

Lists the comment threads on one workspace entity (open first, then resolved) with authors and timestamps.

Posts a comment on a workspace entity — a new thread, or a reply when rootId is given.

Sets a comment thread's resolved state (rootId = the thread's root comment id).

Finds entities across every tool by name in one call — Workbench flows, Compass pages, Caliper datasets, evals, rubrics, reviews, specs and sources (apps sending agent traces), Ledger entries, Napkin sketches and decks.

Returns the tags on a batch of entities of one kind — the labels galleries organize by.

Without a tag: every tag in use across the workspace with how many entities carry it, most-used first — the vocabulary the team already organizes by.

Replaces the FULL tag set on one entity (an empty list clears it).

Search ZeroWidth product documentation.

Fetch the full Markdown body of a specific docs page by its slug.

Enumerate all available docs pages, optionally filtered by product (e.

Lists pages in the active workspace's Compass compendium.

Keyword search over page titles, bodies, and tags (case-insensitive substring match), paginated.

Fetches one Compass page by id, including its full Markdown body, header fields, and any attached Napkin sketches — view an attached sketch's actual drawing with `napkin_boards_view` (its boardId) before discussing it.

Creates a typed page in the workspace's Compass compendium.

Edits an existing page's title, description, body, tags, header fields, or visibility — use this to FIX what you (or an extraction) got wrong instead of creating a duplicate.

Creates a typed, directed edge between two pages — the knowledge graph's connective tissue.

All typed edges touching one page, both directions, each hydrated with the other endpoint's page summary.

Mints a stakeholder-interview invite: a no-account guest link where the person talks to an interviewer agent briefed by your focusPrompt, and the transcript flows back into Compass as reviewable draft pages.

Ranks the PEOPLE the map says know about a page (workflow, system, pain point): `owns` links first, then `involved_in`, then weaker edges.

Emails the guest link for an existing interview, framed as coming from the REQUESTING USER (their name signs it; replies go to them).

Lists the workspace's open questions — the gap registry: what the map doesn't know yet.

Records something you don't yet know — the gap registry is your working memory, so use it liberally while mapping or interviewing.

Closes a gap once you've learned the answer (ANSWERED, with the resolution) or decided it doesn't matter (DISMISSED).

The workspace's changes — fixes, chores, new steps, experiments.

File an AI-PROPOSED opportunity into the workspace's review queue — the scouting verb (the opportunity-scout routine's main move).

Record a change — a fix, a chore, a new step, or an experiment worth trying.

The honesty mechanism: write what the experiment is expected to change BEFORE evidence exists.

The measurement window's boundary: when the user says the experiment's change actually shipped / went live / rolled out, record the landing date.

Renders the workspace's visual map to an image and returns it so you can SEE it the way the user does: an isometric drawing where every page is a structure whose shape is its type — people are figures, audiences are crowds, workflows are gears lying on the ground, systems are database drums, offerings are price tags, pain points are warning signs, documents are standing sheets of paper, values are shields, priorities are flags — sized by how many other pages connect to them, placed near what they link to, with pages connected to nothing parked to one side, and routes drawn between linked pages.

Moves a page to the trash (soft delete — its connections and anchored opportunities go with it, and compass_pages_restore brings the whole set back).

Puts a trashed page back on the map, together with exactly the connections and opportunities its delete took.

Edits an existing edge between two pages: its `kind` (how the two relate) and/or its `note`.

Deletes one edge from the graph (the pages stay).

Corrects an opportunity's content: label, description, priority, what done means, the 1–5 value / feasibility / risk scores, the owner (a PERSON page), notes, tags, workflow anchor, external link, visibility.

Removes an opportunity from the pipeline (soft delete).

The review verb for the Inbox: promotes an AI-PROPOSED opportunity (from compass_opportunities_propose or the opportunity scout) into the workspace's own pipeline.

Every stakeholder interview in the workspace, newest first: who was invited, status (INVITED / IN_PROGRESS / COMPLETED), focus, message count, whether the transcript was already reviewed (documentPageId set), and the invite URL while the link is still live.

One interview in full — metadata plus the transcript of what the guest actually said.

Kills an interview's invite link — the guest's next visit sees that the link is no longer active.

The Compass Inbox in one read: finished interviews awaiting review (transcript in, not yet turned into pages), AI-proposed opportunities awaiting accept / dismiss, and the caller's pending approval cards for Compass writes.

Edits an open question's wording, rationale, or suggested resolution — for sharpening a vague question or fixing one you phrased badly.

The statuses this workspace's changes move through, in board order — the names people use.

Move a change to one of the workspace's statuses, by name (compass_statuses_list has them — e.

Create or update up to 100 changes in one call, each matched by `url` — the GitHub issue, Linear or Jira ticket, PR or doc it mirrors.

Lists the comment threads on one workspace entity (open first, then resolved) with authors and timestamps.

Posts a comment on a workspace entity — a new thread, or a reply when rootId is given.

Sets a comment thread's resolved state (rootId = the thread's root comment id).

Finds entities across every tool by name in one call — Workbench flows, Compass pages, Caliper datasets, evals, rubrics, reviews, specs and sources (apps sending agent traces), Ledger entries, Napkin sketches and decks.

Returns the tags on a batch of entities of one kind — the labels galleries organize by.

Without a tag: every tag in use across the workspace with how many entities carry it, most-used first — the vocabulary the team already organizes by.

Replaces the FULL tag set on one entity (an empty list clears it).

Search ZeroWidth product documentation.

Fetch the full Markdown body of a specific docs page by its slug.

Enumerate all available docs pages, optionally filtered by product (e.

The workspace's memory: decisions (changes with pre-registered expectations), lessons (distilled beliefs), and observations (captured facts).

One entry's full anatomy — the six fields, attached evidence (Caliper runs, measurements, observations), and the supersede chain (what replaced it, or what it replaced).

Records a memory entry.

The ritual moment: evidence has landed, the expectation closes, the lesson is written.

The numbers the workspace watches — each with unit, latest reading, and how many open decisions are bound to it.

Create a metric — a number the workspace watches (triage time, weekly signups, cost per run).

Record one observation of a tracked metric.

One metric's definition (unit, kind, direction, target, cadence) plus its readings newest first and the open decisions bound to it.

Corrects an entry in place — its title (summary), body (rationale), the pre-registered prediction of an OPEN decision (null clears it), or its facet (filing category; editable even after settlement).

Takes an entry out of the curated ledger — THE remedy when you recorded something wrong (a decision that wasn't made, a duplicate, a fact the user corrects).

Records what happened against an open decision — a manual observation the user reports ('the pilot team says triage feels faster'), an implementation note, or a reference to a Caliper run.

Corrects a metric's name, unit, description, kind (measure / event), direction (which way is good), target, cadence, icon, level, or the metrics it drives (its place in the metric tree).

Takes a metric out of the gallery (`archived: true`) or puts it back (`false`).

Pass `entryId` for one decision's plan items, or `from` + `to` (YYYY-MM-DD, at most about a year apart) for the calendar: decision spans (recorded day → expectation deadline) plus every dated item inside the window, including standalone dates with no decision.

Adds a plan item to an OPEN decision (the work that carries it out: a post, a launch step, an email).

Edits one plan item while its decision is open: move it (dueOn), rename it, change the owner (null clears), attach the link, or set status (planned | done | skipped).

Removes one plan item while its decision is open, for an item added by mistake or work that's no longer planned.

Ready-made metrics a business can start tracking, each with a unit, a cadence, which direction is good, a business surface (facet), and cross-cutting tags.

Creates the named presets as real metrics the workspace owns, tagged from the catalog.

Starter trees by shape of business or team (subscription software, services firm, online store, sales team, service operation).

Creates a starter's metrics at their levels and links them.

Writes up to 50 entries as DRAFTS: proposals that stay out of the record until a person confirms each one in Ledger's Drafts view.

The connected servers this workspace exposes to you, with the id a feed needs.

The standing instructions for how metrics' numbers arrive — which tool each one calls, how often, and how the last run went.

Call a connected server's tool once and see what a mapping would pull out of the response — nothing is written and no feed is created.

Freeze a tool call as a metric's standing source: it runs on the cadence you give and records what it finds, with no model involved.

Change a feed's arguments, mapping, cadence, or pause it.

Run a feed immediately over its own window and record what it finds.

Run the same frozen instruction over a past range, so a metric has history instead of starting the day it was set up.

Remove a feed.

Lists the comment threads on one workspace entity (open first, then resolved) with authors and timestamps.

Posts a comment on a workspace entity — a new thread, or a reply when rootId is given.

Sets a comment thread's resolved state (rootId = the thread's root comment id).

Finds entities across every tool by name in one call — Workbench flows, Compass pages, Caliper datasets, evals, rubrics, reviews, specs and sources (apps sending agent traces), Ledger entries, Napkin sketches and decks.

Returns the tags on a batch of entities of one kind — the labels galleries organize by.

Without a tag: every tag in use across the workspace with how many entities carry it, most-used first — the vocabulary the team already organizes by.

Replaces the FULL tag set on one entity (an empty list clears it).

Search ZeroWidth product documentation.

Fetch the full Markdown body of a specific docs page by its slug.

Enumerate all available docs pages, optionally filtered by product (e.

Lists the comment threads on one workspace entity (open first, then resolved) with authors and timestamps.

Posts a comment on a workspace entity — a new thread, or a reply when rootId is given.

Sets a comment thread's resolved state (rootId = the thread's root comment id).

Lists sketch boards in the active workspace — name, id, kind (sketch / deck), shape count, last activity.

Returns a board's shapes as data — each with its id, kind, position, size, and text — so you can TARGET one to change or remove with napkin_draw (`updates` / `deletes` take these ids and absolute board coordinates).

Renders the sketch board to an image and returns it so you can SEE what's drawn — layout, arrows, handwriting-style strokes, sticky notes — not just data about it.

Edits a board's details: name, description, visibility, or `archived` (true takes it out of the gallery; false brings it back — the recovery move for a board you created by mistake or the user no longer wants).

Returns a Napkin deck as a markdown outline — one section per slide in presentation order, with slide titles, text content (bold + bullets preserved), empty layout stubs still awaiting content, and a summary of drawn marks.

Renders a single slide of a Napkin deck to an image — exactly what present mode shows, cropped to the slide.

Creates a blank Napkin board — a sketch (free canvas) or a deck (slides).

Creates a deck from a markdown outline — the SAME dialect `napkin_deck_outline` reads back, so any deck you've read shows the format.

Appends one slide to an existing deck.

Fills a slide's empty layout text areas by NAME — the names `napkin_deck_outline` surfaces as `[empty text stub: "…"]`.

Draws shapes, strokes, and labels on a board — diagram on a sketch, annotate a deck slide — and, via `updates` / `deletes`, changes or removes shapes that are already there (ids from napkin_boards_get; the fix for something you drew wrong).

Paints every slide of a deck with a theme — slide background, heading and body typefaces, and text colors — in one call, the same as picking it in the deck's theme menu.

Changes one slide as a whole: move it to another position in the deck (`moveTo`, 1-based — the other slides shift around it), hide it from the show without deleting it (`skipped`), show or hide its slide number (`pageNumber`), or replace its speaker notes (`notes`, markdown).

Lists the workspace's brand kits: id, name, description, and which one is the workspace's brand (`isDefault`).

Reads a brand kit — the workspace's brand unless you name another.

Finds words the brand says to avoid in a piece of writing, with what to say instead and why.

Restyles a piece in the brand — the workspace's brand unless you name a kit.

Creates a new brand kit, or edits one that is NOT the workspace's brand.

Gets the font files for a kit's typefaces from Google Fonts and keeps them in the kit, so decks, slide pictures and the canvas draw the brand's real typefaces instead of a stand-in.

Shows you the pictures in a kit's Examples sections — screenshots of work that gets the brand right — with each one's note on what makes it good, plus the example links.

Adds pictures to a brand kit section — logo versions, product marks, example screenshots, imagery.

Look at the pictures in a brand kit — logos, product marks, footage stills, layout references, examples — before you use them.

Exports a deck's slides as PNG files at each slide's real pixels — a square post at 1080×1080, a story at 1080×1920, a leaderboard at 728×90 — ready to upload to an ad platform or a social post.

Lists the slide layouts napkin_deck_compose can build from — the brand kit's own first, then the built-in ones — with when to use each and the slots it takes (`needs` must be filled; `takes` are optional).

Builds a designed deck: each slide is a layout with its slots filled, or HTML and CSS you write; a real browser lays it out, and it becomes an ordinary Napkin deck people can edit.

Lists the workspace's Napkin docs (quick markdown documents — drafts, notes, working text; the LINEAR surface, distinct from boards which are drawing canvases) newest first, with excerpts.

Fetch one Napkin doc's full markdown body by id (from napkin_docs_list).

Create a Napkin doc — a markdown DOCUMENT (prose, structure, code blocks), not a drawing canvas (that's napkin_boards_create) and not slides (napkin_deck_write).

Edit a Napkin doc.

Lists the workspace's Napkin sheets (multi-tab spreadsheets — the small-data surface) newest first with tab/chart counts.

Returns a sheet's tabs as SQL table definitions — CREATE TABLE scripts with row counts (each tab is a table; its header row names the columns; formula cells contribute computed values).

Runs a SQLite SELECT over a sheet's tabs-as-tables (get the table/column names from napkin_sheets_schema first).

Renders one of a sheet's pinned charts against the LIVE data and returns the image so you can SEE it — the exact chart the user sees.

Sets cells in one tab of a sheet, by A1 address — values or formulas ('=SUM(B2:B9)').

Adds a LIVE chart to a sheet — its SQL re-runs against the tabs on every view, so it never goes stale.

Creates a Napkin sheet (multi-tab spreadsheet), optionally titled.

Edits a sheet's details: title, description, visibility, or `archived` (true takes it out of the gallery; false brings it back — the recovery move for a sheet created by mistake or no longer wanted).

Lists the workspace's Napkin diagrams (interactive flowcharts — processes, decision trees, system maps) newest first.

Fetch one Napkin diagram's mermaid source by id (from napkin_diagrams_list).

Create a Napkin diagram — an interactive FLOWCHART (process, decision tree, system map), not a doc (napkin_docs_create) or drawing canvas (napkin_boards_create).

Edit a Napkin diagram: retitle, describe, REPLACE the whole mermaid source, set visibility, or `archived` (true takes it out of the gallery, false brings it back — the recovery move for a diagram created by mistake).

List the interfaces in a workspace — small self-contained screens (a custom chat, a control panel, a prototype) that run on their own origin and can call the flows they've been granted.

Read one interface: its name, the flows it may run (with the published version each is pinned to), and the contents of its files.

See what an interface LOOKS like right now: the whole page, drawn from its current files at desktop width under the same rules as the live page (no web fonts, no remote pictures).

Create an interface — a small screen of its own the user can open and send to people.

Write one file of an interface.

Save where an interface is now as a numbered version.

Set what an interface may run — flows and shims, each pinned to a published version.

Finds entities across every tool by name in one call — Workbench flows, Compass pages, Caliper datasets, evals, rubrics, reviews, specs and sources (apps sending agent traces), Ledger entries, Napkin sketches and decks.

Returns the tags on a batch of entities of one kind — the labels galleries organize by.

Without a tag: every tag in use across the workspace with how many entities carry it, most-used first — the vocabulary the team already organizes by.

Replaces the FULL tag set on one entity (an empty list clears it).

Save a picture the user attached in THIS conversation to the workspace's files, in the Home folder "From chat", and get back its file id.

Search ZeroWidth product documentation.

Fetch the full Markdown body of a specific docs page by its slug.

Enumerate all available docs pages, optionally filtered by product (e.

Lists Prism fields (idea-exploration canvases) in the active workspace: name, origin idea, node count.

One field's full tree: every node (id, parent, axis, description, pinned, color, whether it has an image / desk research) plus the AI-clustered groups.

Cross-instrument findings for one subject (today: a Prism node) — attached feedback studies with response counts + theme counts, and whether desk research exists.

Creates a field from an origin idea — the seed of an exploration canvas.

THE core Prism gesture: generate variations of a node along a named semantic axis ('more visceral', 'for the skeptic', 'stripped to essentials'…) in one of four directions.

Sets pinned state and/or the color tag on a node.

Web-sourced secondary research on a node's idea — market context with citations, stored on the node.

Feedback studies attached to one Prism node: title, question count, response count, open/closed.

One study's questions, response count, open/closed state, and the STORED analysis (summary + themes with strength; insights.

Generates a short study (5-8 questions probing the node's problem space — respondents never see the idea itself) and creates it as a DRAFT.

Generates and creates a DRAFT study that isn't tied to any canvas node — brand tracking, workspace-level research, anything you can describe in a sentence.

Qual-first design: drafts a survey GROUNDED in the study's completed interviews — the recurring claims become measurable questions, the tensions become the choices, in the interviewees' own words.

publish: true takes a draft live (one-way — the participant link starts working).

Everything the Results tab shows, as numbers you can trust without counting raw rows: fielding funnel (opens → starts → completes, median completion time, sources, per-question drop-off), per-question aggregates (scale distributions + means + NPS on 0–10, choice/multi counts, rank first-place + mean ranks, MaxDiff set scores, word frequencies, text samples), and quality flags (speeders, duplicate participant ids).

A cross-study digest: every study with responses — title, origin (standalone / canvas node / tracker wave), response count, latest analysis summary, top themes, and which insights were kept in Ledger.

An AI research analyst writes the report's narrative layer — executive summary, key findings with their numbers, recommendations — from the study's computed record (funnel, per-question aggregates, themes, quotes).

Recurring research programs (ADR 0031): name, cadence, enabled state, next wave time, wave count, and the metric + score rule when the series posts readings.

CLOSES the current wave (no more responses; it scores and posts to Ledger if bound) and fields the next one from the series' frozen instrument, readying its participant link.

The study's one-on-one qual conversations: guest, status, focus, and — once completed — the structured memo (summary, key claims, tensions, verbatim quotes).

The stored k-means segmentation over the study's numeric answers: named segments with size, share, and the distinguishing features (segment mean vs overall).

Server-computed banner cut with significance: a target question (scale/number → group means + NPS on 0–10; choice/multi → per-option shares) split by acquisition source or by any single-choice question, each group tested against its complement at 95% (Welch t / two-proportion z).

Kicks the theme analysis (incremental — reads only responses and interviews since the last run; the previous themes carry forward).

Creates a one-on-one AI-led interview on a study and returns the invite link to forward — the guest needs no account.

Promotes an analysis theme (or, with no themeId, the analysis summary) into the workspace's Ledger as a belief, carrying the supporting verbatims as evidence with links back to the study.

Runs k-means over the study's numeric answers (silhouette-picked k) and names the discovered segments from their computed profiles.

Edits a field's name (null reverts to the origin idea), description, or visibility.

Removes a field and its whole canvas (soft delete; frees the workspace's field quota).

All studies regardless of origin — standalone, canvas-node, and series waves — newest first: title, question count, response count, draft / live / closed state, and the field / node / series it hangs off.

Permanently deletes a study with its responses, interviews, analysis, and share links.

Creates a research program that fields the SAME instrument on a schedule — brand tracking, a weekly pulse — each wave an ordinary study.

Edits a series: `enabled: false` pauses the schedule (true resumes), interval / scheduleTime / scheduleTimezone / dayOfWeek move the cadence, name and follow-up / auto-analyze settings change any time.

Lists the comment threads on one workspace entity (open first, then resolved) with authors and timestamps.

Posts a comment on a workspace entity — a new thread, or a reply when rootId is given.

Sets a comment thread's resolved state (rootId = the thread's root comment id).

Finds entities across every tool by name in one call — Workbench flows, Compass pages, Caliper datasets, evals, rubrics, reviews, specs and sources (apps sending agent traces), Ledger entries, Napkin sketches and decks.

Returns the tags on a batch of entities of one kind — the labels galleries organize by.

Without a tag: every tag in use across the workspace with how many entities carry it, most-used first — the vocabulary the team already organizes by.

Replaces the FULL tag set on one entity (an empty list clears it).

Search ZeroWidth product documentation.

Fetch the full Markdown body of a specific docs page by its slug.

Enumerate all available docs pages, optionally filtered by product (e.

The flow's revision history, newest first: published versions carry a `version` label and note; entries with version null are draft autosaves.

Changes a flow's name, description, visibility, tags, or archived state — the metadata around the flow, NOT its orchestration (prompts and nodes change through workbench_flows_edit_text).

Snapshots the flow's current DRAFT as a named published version — the version schedules (workbench_flows_schedule), guest share links (workbench_flows_share_create), public-API runs, and 'published'-stage evals execute.

Deletes a flow.

Copies a PUBLIC flow from another workspace (a template) into this one as a new draft the user owns.

Every schedule on one flow: cadence, whether it's paused (`enabled: false`), the next fire time, delivery, and the last run's status.

Changes one schedule: `enabled: false` pauses it (configuration kept), `enabled: true` resumes and recomputes the next fire time from now; `interval` / `scheduleTime` / `scheduleTimezone` / `scheduleDayOfWeek` change the cadence; `label`, `delivery`, and `input` can change too.

Removes a schedule for good.

Runs one iteration of a schedule immediately through the real scheduled pipeline (same input, same delivery — the email or channel it normally posts to) without moving its cadence.

Every guest link on one flow, newest first: label, whether it's still live, the shareUrl (live links only — dead ones have no URL), expiry, and how many guests and messages it has seen.

Kills one guest link immediately — anyone holding it gets a closed page from then on.

Execute a flow and return its outputs synchronously.

Set a specific built flow to run automatically on a cadence — the deterministic counterpart to a zv1 routine.

Lists every flow in the active workspace the caller can see.

The flow's stack traces: recent executions with per-node timelines — what each node received, produced, how long it took, and the exact error when one failed.

One flow.

READ THIS FIRST before writing or editing any raw flow orchestration JSON.

The ground truth for what nodes exist and what their ports actually are — verify against this instead of recalling.

Creates a runnable first-draft flow from a spec you author: pick the simplest pattern that fits (classifier for read-and-bucket, structurer for transform/extract/draft-for-review, agent for genuinely conversational), write a production-quality system prompt grounded in what the user told you, and mark anything stubbed with [STUB: .

Applies ONE precise text replacement to a flow's DRAFT orchestration — Edit-tool semantics: `find` must be the EXACT current text, copied character-for-character from workbench_flows_get, and must occur exactly once anywhere in the flow (system prompts, node settings, metadata, a node's type).

Creates a no-account guest link where anyone can chat with the flow's latest PUBLISHED revision at workbench's /s/<token> page — the fastest way to put a working flow in a stakeholder's hands ('here, try it').

One knowledge base: name, recipe (docs / tabular / graph), status, document and chunk counts, embedding model, and ingestion settings.

Every document ingested into the KB's current content: id, name, type, size, chunk count.

The state of one ingestion run started by workbench_kb_add_documents: PENDING / RUNNING / DONE / FAILED, chunks written, and the error when it failed.

Deletes a knowledge base and everything in it.

Removes one ingested document and all its chunks; searches stop returning it at once.

Lists every knowledge base in the active workspace the caller can see.

Retrieves the most relevant chunks from one knowledge base — the core RAG primitive.

Creates an empty knowledge base.

Adds documents to a knowledge base and starts ingestion (chunk + embed; graph KBs also extract entities; tabular KBs load CSV as tables).

Every shim the user can see: id, name, the question it answers, how many answers and examples it has, and the published version's held-out accuracy (null until something is published).

One shim in full: the question, where its inputs come from, every answer with its description and examples, what the shim still needs before it can build, and the newest build's report — held-out accuracy, recall per answer, which answers get mistaken for which, and the compiler's notes.

Creates a shim from a name, the question it answers, and its answers.

Adds one answer (a label and, optionally, when it applies).

Adds example inputs to one answer.

Lists the comment threads on one workspace entity (open first, then resolved) with authors and timestamps.

Posts a comment on a workspace entity — a new thread, or a reply when rootId is given.

Sets a comment thread's resolved state (rootId = the thread's root comment id).

One Task in full: its sentence, status, the latest saved plan (the clauses — which run flows, which zv1 handles, who decides at each gate) with the flow and people names the plan refers to, and its recent runs.

Changes a task's name — the gallery label only.

Deletes a task.

Lists the workspace's Tasks — sentence-orchestrated processes — with their sentence, status, and recent runs (id, status, who a waiting run is on).

Creates a DRAFT Task from a name + sentence.

Runs the compiler over a sentence and returns the PROPOSED plan (or repair-grade problems — fix by refining the sentence with the user, not by guessing).

Freezes a reviewed plan as the Task's next version and activates it.

Kicks off a run of a Task.

The run's current state rendered as its sentence: what ran (with timings), which path each gate took, what's waiting on whom and for how long, what's coming up.

Records THIS user's verdict on a run that is waiting on them — the labels come from the gate (workbench_tasks_run_view shows them via the plan; a wrong label errors listing the real options).

Finds entities across every tool by name in one call — Workbench flows, Compass pages, Caliper datasets, evals, rubrics, reviews, specs and sources (apps sending agent traces), Ledger entries, Napkin sketches and decks.

Returns the tags on a batch of entities of one kind — the labels galleries organize by.

Without a tag: every tag in use across the workspace with how many entities carry it, most-used first — the vocabulary the team already organizes by.

Replaces the FULL tag set on one entity (an empty list clears it).

Search ZeroWidth product documentation.

Fetch the full Markdown body of a specific docs page by its slug.

Enumerate all available docs pages, optionally filtered by product (e.

Lists ZeroWidth's published Distributed Cognition essays (newest first): title, slug, excerpt, byline, public URL.

Fetch the full Markdown body of one Distributed Cognition essay by slug (from `list_posts`).

The flow's revision history, newest first: published versions carry a `version` label and note; entries with version null are draft autosaves.

Changes a flow's name, description, visibility, tags, or archived state — the metadata around the flow, NOT its orchestration (prompts and nodes change through workbench_flows_edit_text).

Snapshots the flow's current DRAFT as a named published version — the version schedules (workbench_flows_schedule), guest share links (workbench_flows_share_create), public-API runs, and 'published'-stage evals execute.

Deletes a flow.

Copies a PUBLIC flow from another workspace (a template) into this one as a new draft the user owns.

Every schedule on one flow: cadence, whether it's paused (`enabled: false`), the next fire time, delivery, and the last run's status.

Changes one schedule: `enabled: false` pauses it (configuration kept), `enabled: true` resumes and recomputes the next fire time from now; `interval` / `scheduleTime` / `scheduleTimezone` / `scheduleDayOfWeek` change the cadence; `label`, `delivery`, and `input` can change too.

Removes a schedule for good.

Runs one iteration of a schedule immediately through the real scheduled pipeline (same input, same delivery — the email or channel it normally posts to) without moving its cadence.

Every guest link on one flow, newest first: label, whether it's still live, the shareUrl (live links only — dead ones have no URL), expiry, and how many guests and messages it has seen.

Kills one guest link immediately — anyone holding it gets a closed page from then on.

Execute a flow and return its outputs synchronously.

Set a specific built flow to run automatically on a cadence — the deterministic counterpart to a zv1 routine.

Lists every flow in the active workspace the caller can see.

The flow's stack traces: recent executions with per-node timelines — what each node received, produced, how long it took, and the exact error when one failed.

One flow.

READ THIS FIRST before writing or editing any raw flow orchestration JSON.

The ground truth for what nodes exist and what their ports actually are — verify against this instead of recalling.

Creates a runnable first-draft flow from a spec you author: pick the simplest pattern that fits (classifier for read-and-bucket, structurer for transform/extract/draft-for-review, agent for genuinely conversational), write a production-quality system prompt grounded in what the user told you, and mark anything stubbed with [STUB: .

Applies ONE precise text replacement to a flow's DRAFT orchestration — Edit-tool semantics: `find` must be the EXACT current text, copied character-for-character from workbench_flows_get, and must occur exactly once anywhere in the flow (system prompts, node settings, metadata, a node's type).

Creates a no-account guest link where anyone can chat with the flow's latest PUBLISHED revision at workbench's /s/<token> page — the fastest way to put a working flow in a stakeholder's hands ('here, try it').

One knowledge base: name, recipe (docs / tabular / graph), status, document and chunk counts, embedding model, and ingestion settings.

Every document ingested into the KB's current content: id, name, type, size, chunk count.

The state of one ingestion run started by workbench_kb_add_documents: PENDING / RUNNING / DONE / FAILED, chunks written, and the error when it failed.

Deletes a knowledge base and everything in it.

Removes one ingested document and all its chunks; searches stop returning it at once.

Lists every knowledge base in the active workspace the caller can see.

Retrieves the most relevant chunks from one knowledge base — the core RAG primitive.

Creates an empty knowledge base.

Adds documents to a knowledge base and starts ingestion (chunk + embed; graph KBs also extract entities; tabular KBs load CSV as tables).

Every shim the user can see: id, name, the question it answers, how many answers and examples it has, and the published version's held-out accuracy (null until something is published).

One shim in full: the question, where its inputs come from, every answer with its description and examples, what the shim still needs before it can build, and the newest build's report — held-out accuracy, recall per answer, which answers get mistaken for which, and the compiler's notes.

Creates a shim from a name, the question it answers, and its answers.

Adds one answer (a label and, optionally, when it applies).

Adds example inputs to one answer.

One dataset with a page of its items — read this BEFORE editing items (caliper_datasets_update_item needs the item id) and before extending coverage, so you don't add cases that already exist.

Changes a dataset's title, description, or visibility.

Deletes a dataset.

Rewrites one item's content, keeping its id (ratings and eval results keyed to it stay attached).

Drops one item.

Creates a NEW dataset of model-written items — Q&A by default, or scripted sequences / simulated people via `shape` — pass flowId and the generator reads the flow's prompt, mode, and schema to write realistic cases for THAT flow; `description` adds guidance (or stands alone when there's no flow).

Appends model-written items to an EXISTING dataset, in the style of what's already there (existing items are the few-shot examples; the output shape matches theirs unless overridden).

Lists the rubrics in the active workspace (id, name, description, criterion count).

One rubric with its criteria — each criterion's name, what the judge looks for, and the score scale.

Changes a rubric's title, description, visibility, or replaces its criteria wholesale (pass the FULL list — criteria get fresh ids).

Deletes a rubric.

One eval: what it targets (Workbench flow + stage, or external), its dataset and rubric ids, the rubric criteria it scores with (the snapshot taken at creation), schedule + runOnPublish + regression settings, run counts, latest score, and `binding` health (datasetOk / flowOk false = a run would fail at resolution — say so before proposing caliper_evals_run).

What the flow actually DID on one run item: every step in order (what it said, which tools it called with what arguments, what came back) and the final answer, plus status, duration, and cost.

Changes an eval's title, description, visibility, schedule (interval + time anchor), runOnPublish (queue a run whenever the flow publishes), or regressionThreshold (score drop vs the previous run that triggers an alert; null = off).

Deletes an eval and stops its schedule.

Stops a run that is still PENDING / RUNNING / SCORING — the brake on a run that's spending more than expected or was started by mistake.

Apps sending their agent's traces to Caliper — from their own code, OpenTelemetry, or a published Workbench flow — busiest first: name, how it sends, traces in the last 14 days (per day), and the tools its agent calls most with the share of traces using each.

One source day by day: traces, failures, tool calls, lookups that found nothing, tokens, cost, and speed (meanMs; p50/p95 as 'answered within' bucket edges); each tool with its calls and the share of each day's traces that used it; the documents lookups landed on most; models used.

The traces behind a point on a source's chart, newest first, 50 a page: the question and answer (cut short), tools called, time, tokens, cost, status.

One trace: what came in, what went out, and every step in order — model calls (model, tokens, cost, reasoning), tool calls (arguments and result), lookups (query and documents with scores), anything else — each with timing and status.

Datasets this source keeps adding to as conversations arrive: which dataset, for what (review, eval, spec), the pick it matches, sampling, how many have landed, and whether it's still running or why it stopped.

Saves the conversations behind a pick (a day, a tool, a document, failures — the same narrowing as caliper_traces_list) into a new dataset (newDatasetName) or an existing one (datasetId), newest first up to `limit`.

Stops a source from adding new conversations to a dataset.

The starter sets Caliper ships: prompt injection, system-prompt leaking, over-refusal, personal-data handling, bias under ambiguity.

Copies one starter into the workspace as a new dataset and a new rubric the user owns and can edit.

Lists datasets in the active workspace.

How a Workbench flow is ACTUALLY doing, with receipts: every Caliper eval targeting the flow, recent runs with scores, the latest run decomposed into per-criterion averages, the score delta vs the previous run, and the worst-scoring items WITH the judge's reasoning.

Recent runs for one eval, newest first: status (PENDING/RUNNING/SCORING/DONE/FAILED), overall score once DONE, label, and timestamps.

One run: status, overall score, and by default the ten lowest-scoring items with their per-criterion scores and the judge's reasoning (`items: all` for every item, `none` for totals only).

Lists evals in the active workspace with their target config (which Workbench flow, which dataset/rubric).

Queues a new run of an eval — inference over the dataset, then LLM-judge scoring.

Creates a dataset of test items — THE FIRST STEP of setting up evaluation for a flow.

Appends items to an existing dataset — use this to grow coverage (new edge cases, scenarios from a completed interview) instead of creating a parallel dataset.

Creates the scoring rubric an eval's LLM judge uses — 1-10 criteria, each scored on a numeric scale (default 1-5), judged pass/fail (kind pass_fail), or checked in code with no judge (kind check: contains, not_contains, matches a regex, valid_json, max_chars, equals_expected).

Binds a dataset + rubric to something under test as a repeatable eval — THE LAST SETUP STEP before scoring.

Lists pages in the active workspace's Compass compendium.

Keyword search over page titles, bodies, and tags (case-insensitive substring match), paginated.

Fetches one Compass page by id, including its full Markdown body, header fields, and any attached Napkin sketches — view an attached sketch's actual drawing with `napkin_boards_view` (its boardId) before discussing it.

Creates a typed page in the workspace's Compass compendium.

Edits an existing page's title, description, body, tags, header fields, or visibility — use this to FIX what you (or an extraction) got wrong instead of creating a duplicate.

Creates a typed, directed edge between two pages — the knowledge graph's connective tissue.

All typed edges touching one page, both directions, each hydrated with the other endpoint's page summary.

Mints a stakeholder-interview invite: a no-account guest link where the person talks to an interviewer agent briefed by your focusPrompt, and the transcript flows back into Compass as reviewable draft pages.

Ranks the PEOPLE the map says know about a page (workflow, system, pain point): `owns` links first, then `involved_in`, then weaker edges.

Emails the guest link for an existing interview, framed as coming from the REQUESTING USER (their name signs it; replies go to them).

Lists the workspace's open questions — the gap registry: what the map doesn't know yet.

Records something you don't yet know — the gap registry is your working memory, so use it liberally while mapping or interviewing.

Closes a gap once you've learned the answer (ANSWERED, with the resolution) or decided it doesn't matter (DISMISSED).

The workspace's changes — fixes, chores, new steps, experiments.

File an AI-PROPOSED opportunity into the workspace's review queue — the scouting verb (the opportunity-scout routine's main move).

Record a change — a fix, a chore, a new step, or an experiment worth trying.

The honesty mechanism: write what the experiment is expected to change BEFORE evidence exists.

The measurement window's boundary: when the user says the experiment's change actually shipped / went live / rolled out, record the landing date.

Renders the workspace's visual map to an image and returns it so you can SEE it the way the user does: an isometric drawing where every page is a structure whose shape is its type — people are figures, audiences are crowds, workflows are gears lying on the ground, systems are database drums, offerings are price tags, pain points are warning signs, documents are standing sheets of paper, values are shields, priorities are flags — sized by how many other pages connect to them, placed near what they link to, with pages connected to nothing parked to one side, and routes drawn between linked pages.

Moves a page to the trash (soft delete — its connections and anchored opportunities go with it, and compass_pages_restore brings the whole set back).

Puts a trashed page back on the map, together with exactly the connections and opportunities its delete took.

Edits an existing edge between two pages: its `kind` (how the two relate) and/or its `note`.

Deletes one edge from the graph (the pages stay).

Corrects an opportunity's content: label, description, priority, what done means, the 1–5 value / feasibility / risk scores, the owner (a PERSON page), notes, tags, workflow anchor, external link, visibility.

Removes an opportunity from the pipeline (soft delete).

The review verb for the Inbox: promotes an AI-PROPOSED opportunity (from compass_opportunities_propose or the opportunity scout) into the workspace's own pipeline.

Every stakeholder interview in the workspace, newest first: who was invited, status (INVITED / IN_PROGRESS / COMPLETED), focus, message count, whether the transcript was already reviewed (documentPageId set), and the invite URL while the link is still live.

One interview in full — metadata plus the transcript of what the guest actually said.

Kills an interview's invite link — the guest's next visit sees that the link is no longer active.

The Compass Inbox in one read: finished interviews awaiting review (transcript in, not yet turned into pages), AI-proposed opportunities awaiting accept / dismiss, and the caller's pending approval cards for Compass writes.

Edits an open question's wording, rationale, or suggested resolution — for sharpening a vague question or fixing one you phrased badly.

The statuses this workspace's changes move through, in board order — the names people use.

Move a change to one of the workspace's statuses, by name (compass_statuses_list has them — e.

Create or update up to 100 changes in one call, each matched by `url` — the GitHub issue, Linear or Jira ticket, PR or doc it mirrors.

Lists Prism fields (idea-exploration canvases) in the active workspace: name, origin idea, node count.

One field's full tree: every node (id, parent, axis, description, pinned, color, whether it has an image / desk research) plus the AI-clustered groups.

Cross-instrument findings for one subject (today: a Prism node) — attached feedback studies with response counts + theme counts, and whether desk research exists.

Creates a field from an origin idea — the seed of an exploration canvas.

THE core Prism gesture: generate variations of a node along a named semantic axis ('more visceral', 'for the skeptic', 'stripped to essentials'…) in one of four directions.

Sets pinned state and/or the color tag on a node.

Web-sourced secondary research on a node's idea — market context with citations, stored on the node.

Feedback studies attached to one Prism node: title, question count, response count, open/closed.

One study's questions, response count, open/closed state, and the STORED analysis (summary + themes with strength; insights.

Generates a short study (5-8 questions probing the node's problem space — respondents never see the idea itself) and creates it as a DRAFT.

Generates and creates a DRAFT study that isn't tied to any canvas node — brand tracking, workspace-level research, anything you can describe in a sentence.

Qual-first design: drafts a survey GROUNDED in the study's completed interviews — the recurring claims become measurable questions, the tensions become the choices, in the interviewees' own words.

publish: true takes a draft live (one-way — the participant link starts working).

Everything the Results tab shows, as numbers you can trust without counting raw rows: fielding funnel (opens → starts → completes, median completion time, sources, per-question drop-off), per-question aggregates (scale distributions + means + NPS on 0–10, choice/multi counts, rank first-place + mean ranks, MaxDiff set scores, word frequencies, text samples), and quality flags (speeders, duplicate participant ids).

A cross-study digest: every study with responses — title, origin (standalone / canvas node / tracker wave), response count, latest analysis summary, top themes, and which insights were kept in Ledger.

An AI research analyst writes the report's narrative layer — executive summary, key findings with their numbers, recommendations — from the study's computed record (funnel, per-question aggregates, themes, quotes).

Recurring research programs (ADR 0031): name, cadence, enabled state, next wave time, wave count, and the metric + score rule when the series posts readings.

CLOSES the current wave (no more responses; it scores and posts to Ledger if bound) and fields the next one from the series' frozen instrument, readying its participant link.

The study's one-on-one qual conversations: guest, status, focus, and — once completed — the structured memo (summary, key claims, tensions, verbatim quotes).

The stored k-means segmentation over the study's numeric answers: named segments with size, share, and the distinguishing features (segment mean vs overall).

Server-computed banner cut with significance: a target question (scale/number → group means + NPS on 0–10; choice/multi → per-option shares) split by acquisition source or by any single-choice question, each group tested against its complement at 95% (Welch t / two-proportion z).

Kicks the theme analysis (incremental — reads only responses and interviews since the last run; the previous themes carry forward).

Creates a one-on-one AI-led interview on a study and returns the invite link to forward — the guest needs no account.

Promotes an analysis theme (or, with no themeId, the analysis summary) into the workspace's Ledger as a belief, carrying the supporting verbatims as evidence with links back to the study.

Runs k-means over the study's numeric answers (silhouette-picked k) and names the discovered segments from their computed profiles.

Edits a field's name (null reverts to the origin idea), description, or visibility.

Removes a field and its whole canvas (soft delete; frees the workspace's field quota).

All studies regardless of origin — standalone, canvas-node, and series waves — newest first: title, question count, response count, draft / live / closed state, and the field / node / series it hangs off.

Permanently deletes a study with its responses, interviews, analysis, and share links.

Creates a research program that fields the SAME instrument on a schedule — brand tracking, a weekly pulse — each wave an ordinary study.

Edits a series: `enabled: false` pauses the schedule (true resumes), interval / scheduleTime / scheduleTimezone / dayOfWeek move the cadence, name and follow-up / auto-analyze settings change any time.

The workspace's memory: decisions (changes with pre-registered expectations), lessons (distilled beliefs), and observations (captured facts).

One entry's full anatomy — the six fields, attached evidence (Caliper runs, measurements, observations), and the supersede chain (what replaced it, or what it replaced).

Records a memory entry.

The ritual moment: evidence has landed, the expectation closes, the lesson is written.

The numbers the workspace watches — each with unit, latest reading, and how many open decisions are bound to it.

Create a metric — a number the workspace watches (triage time, weekly signups, cost per run).

Record one observation of a tracked metric.

One metric's definition (unit, kind, direction, target, cadence) plus its readings newest first and the open decisions bound to it.

Corrects an entry in place — its title (summary), body (rationale), the pre-registered prediction of an OPEN decision (null clears it), or its facet (filing category; editable even after settlement).

Takes an entry out of the curated ledger — THE remedy when you recorded something wrong (a decision that wasn't made, a duplicate, a fact the user corrects).

Records what happened against an open decision — a manual observation the user reports ('the pilot team says triage feels faster'), an implementation note, or a reference to a Caliper run.

Corrects a metric's name, unit, description, kind (measure / event), direction (which way is good), target, cadence, icon, level, or the metrics it drives (its place in the metric tree).

Takes a metric out of the gallery (`archived: true`) or puts it back (`false`).

Pass `entryId` for one decision's plan items, or `from` + `to` (YYYY-MM-DD, at most about a year apart) for the calendar: decision spans (recorded day → expectation deadline) plus every dated item inside the window, including standalone dates with no decision.

Adds a plan item to an OPEN decision (the work that carries it out: a post, a launch step, an email).

Edits one plan item while its decision is open: move it (dueOn), rename it, change the owner (null clears), attach the link, or set status (planned | done | skipped).

Removes one plan item while its decision is open, for an item added by mistake or work that's no longer planned.

Ready-made metrics a business can start tracking, each with a unit, a cadence, which direction is good, a business surface (facet), and cross-cutting tags.

Creates the named presets as real metrics the workspace owns, tagged from the catalog.

Starter trees by shape of business or team (subscription software, services firm, online store, sales team, service operation).

Creates a starter's metrics at their levels and links them.

Writes up to 50 entries as DRAFTS: proposals that stay out of the record until a person confirms each one in Ledger's Drafts view.

The connected servers this workspace exposes to you, with the id a feed needs.

The standing instructions for how metrics' numbers arrive — which tool each one calls, how often, and how the last run went.

Call a connected server's tool once and see what a mapping would pull out of the response — nothing is written and no feed is created.

Freeze a tool call as a metric's standing source: it runs on the cadence you give and records what it finds, with no model involved.

Change a feed's arguments, mapping, cadence, or pause it.

Run a feed immediately over its own window and record what it finds.

Run the same frozen instruction over a past range, so a metric has history instead of starting the day it was set up.

Remove a feed.

Lists the comment threads on one workspace entity (open first, then resolved) with authors and timestamps.

Posts a comment on a workspace entity — a new thread, or a reply when rootId is given.

Sets a comment thread's resolved state (rootId = the thread's root comment id).

Lists sketch boards in the active workspace — name, id, kind (sketch / deck), shape count, last activity.

Returns a board's shapes as data — each with its id, kind, position, size, and text — so you can TARGET one to change or remove with napkin_draw (`updates` / `deletes` take these ids and absolute board coordinates).

Renders the sketch board to an image and returns it so you can SEE what's drawn — layout, arrows, handwriting-style strokes, sticky notes — not just data about it.

Edits a board's details: name, description, visibility, or `archived` (true takes it out of the gallery; false brings it back — the recovery move for a board you created by mistake or the user no longer wants).

Returns a Napkin deck as a markdown outline — one section per slide in presentation order, with slide titles, text content (bold + bullets preserved), empty layout stubs still awaiting content, and a summary of drawn marks.

Renders a single slide of a Napkin deck to an image — exactly what present mode shows, cropped to the slide.

Creates a blank Napkin board — a sketch (free canvas) or a deck (slides).

Creates a deck from a markdown outline — the SAME dialect `napkin_deck_outline` reads back, so any deck you've read shows the format.

Appends one slide to an existing deck.

Fills a slide's empty layout text areas by NAME — the names `napkin_deck_outline` surfaces as `[empty text stub: "…"]`.

Draws shapes, strokes, and labels on a board — diagram on a sketch, annotate a deck slide — and, via `updates` / `deletes`, changes or removes shapes that are already there (ids from napkin_boards_get; the fix for something you drew wrong).

Paints every slide of a deck with a theme — slide background, heading and body typefaces, and text colors — in one call, the same as picking it in the deck's theme menu.

Changes one slide as a whole: move it to another position in the deck (`moveTo`, 1-based — the other slides shift around it), hide it from the show without deleting it (`skipped`), show or hide its slide number (`pageNumber`), or replace its speaker notes (`notes`, markdown).

Lists the workspace's brand kits: id, name, description, and which one is the workspace's brand (`isDefault`).

Reads a brand kit — the workspace's brand unless you name another.

Finds words the brand says to avoid in a piece of writing, with what to say instead and why.

Restyles a piece in the brand — the workspace's brand unless you name a kit.

Creates a new brand kit, or edits one that is NOT the workspace's brand.

Gets the font files for a kit's typefaces from Google Fonts and keeps them in the kit, so decks, slide pictures and the canvas draw the brand's real typefaces instead of a stand-in.

Shows you the pictures in a kit's Examples sections — screenshots of work that gets the brand right — with each one's note on what makes it good, plus the example links.

Adds pictures to a brand kit section — logo versions, product marks, example screenshots, imagery.

Look at the pictures in a brand kit — logos, product marks, footage stills, layout references, examples — before you use them.

Exports a deck's slides as PNG files at each slide's real pixels — a square post at 1080×1080, a story at 1080×1920, a leaderboard at 728×90 — ready to upload to an ad platform or a social post.

Lists the slide layouts napkin_deck_compose can build from — the brand kit's own first, then the built-in ones — with when to use each and the slots it takes (`needs` must be filled; `takes` are optional).

Builds a designed deck: each slide is a layout with its slots filled, or HTML and CSS you write; a real browser lays it out, and it becomes an ordinary Napkin deck people can edit.

Lists the workspace's Napkin docs (quick markdown documents — drafts, notes, working text; the LINEAR surface, distinct from boards which are drawing canvases) newest first, with excerpts.

Fetch one Napkin doc's full markdown body by id (from napkin_docs_list).

Create a Napkin doc — a markdown DOCUMENT (prose, structure, code blocks), not a drawing canvas (that's napkin_boards_create) and not slides (napkin_deck_write).

Edit a Napkin doc.

Lists the workspace's Napkin sheets (multi-tab spreadsheets — the small-data surface) newest first with tab/chart counts.

Returns a sheet's tabs as SQL table definitions — CREATE TABLE scripts with row counts (each tab is a table; its header row names the columns; formula cells contribute computed values).

Runs a SQLite SELECT over a sheet's tabs-as-tables (get the table/column names from napkin_sheets_schema first).

Renders one of a sheet's pinned charts against the LIVE data and returns the image so you can SEE it — the exact chart the user sees.

Sets cells in one tab of a sheet, by A1 address — values or formulas ('=SUM(B2:B9)').

Adds a LIVE chart to a sheet — its SQL re-runs against the tabs on every view, so it never goes stale.

Creates a Napkin sheet (multi-tab spreadsheet), optionally titled.

Edits a sheet's details: title, description, visibility, or `archived` (true takes it out of the gallery; false brings it back — the recovery move for a sheet created by mistake or no longer wanted).

Lists the workspace's Napkin diagrams (interactive flowcharts — processes, decision trees, system maps) newest first.

Fetch one Napkin diagram's mermaid source by id (from napkin_diagrams_list).

Create a Napkin diagram — an interactive FLOWCHART (process, decision tree, system map), not a doc (napkin_docs_create) or drawing canvas (napkin_boards_create).

Edit a Napkin diagram: retitle, describe, REPLACE the whole mermaid source, set visibility, or `archived` (true takes it out of the gallery, false brings it back — the recovery move for a diagram created by mistake).

List the interfaces in a workspace — small self-contained screens (a custom chat, a control panel, a prototype) that run on their own origin and can call the flows they've been granted.

Read one interface: its name, the flows it may run (with the published version each is pinned to), and the contents of its files.

See what an interface LOOKS like right now: the whole page, drawn from its current files at desktop width under the same rules as the live page (no web fonts, no remote pictures).

Create an interface — a small screen of its own the user can open and send to people.

Write one file of an interface.

Save where an interface is now as a numbered version.

Set what an interface may run — flows and shims, each pinned to a published version.

One Task in full: its sentence, status, the latest saved plan (the clauses — which run flows, which zv1 handles, who decides at each gate) with the flow and people names the plan refers to, and its recent runs.

Changes a task's name — the gallery label only.

Deletes a task.

Lists the workspace's Tasks — sentence-orchestrated processes — with their sentence, status, and recent runs (id, status, who a waiting run is on).

Creates a DRAFT Task from a name + sentence.

Runs the compiler over a sentence and returns the PROPOSED plan (or repair-grade problems — fix by refining the sentence with the user, not by guessing).

Freezes a reviewed plan as the Task's next version and activates it.

Kicks off a run of a Task.

The run's current state rendered as its sentence: what ran (with timings), which path each gate took, what's waiting on whom and for how long, what's coming up.

Records THIS user's verdict on a run that is waiting on them — the labels come from the gate (workbench_tasks_run_view shows them via the plan; a wrong label errors listing the real options).

List zv1 routines — scheduled natural-language instructions run by zv1.

Create a zv1 routine: a natural-language instruction run on a schedule ("scan for new competitors and propose a Compass page for each").

Update a routine's instruction, cadence, delivery, or enabled switch (pause/resume).

The workspace's rooms: where groups of people work together with zv1 and flows.

What a room has been saying: its catch-up summary (and whether messages have landed since), its sidebars with their outcomes, and the most recent messages as plain lines with who said them.

Posts a message into a room's stream as zv1, where everyone in the room will see it.

Adds a Workbench flow to a room as a member, so people can @mention it and it can work on things with you there.

Starts zv1 and flows in a room working on something together in a sidebar: they take turns without a person between each, and the result comes back to the room's stream.

The workspace's inference-credit position: plan, this month's grant and how much of it is spent, and the purchased balance runs draw on past the grant.

Finds entities across every tool by name in one call — Workbench flows, Compass pages, Caliper datasets, evals, rubrics, reviews, specs and sources (apps sending agent traces), Ledger entries, Napkin sketches and decks.

Returns the tags on a batch of entities of one kind — the labels galleries organize by.

Without a tag: every tag in use across the workspace with how many entities carry it, most-used first — the vocabulary the team already organizes by.

Without a folder: every folder in the workspace as a tree, each with its id, full path, and how many things are filed directly in it.

Replaces the FULL tag set on one entity (an empty list clears it).

Save a picture the user attached in THIS conversation to the workspace's files, in the Home folder "From chat", and get back its file id.

Read an uploaded file (PDF, Word, PowerPoint, spreadsheet, text) as markdown.

Creates folders for the work someone described, rooms linked to those folders (with your first message in each, the concrete next step), and starting pieces filed inside.