> ## Documentation Index > Fetch the complete documentation index at: https://docs.parable.work/llms.txt > Use this file to discover all available pages before exploring further. # Ponder Primer > Work through a durable Problem with AI, teammates, source context, and proof in one shared Workspace conversation. # Ponder ## Sources Docs: [Pondering](/ponder/parables/purposes/pondering) Web App: Open **Ponder** from your Workspace sidebar; each Workspace has its own address. Ponder is where people and AI work through a Problem together. The Problem keeps the ordered Message thread; each ordinary response uses the Persona, profile, and Powers selected for that request. An explicit Process uses a separate Run. Another person can return to the thread without reconstructing it from a temporary chat. ## Set appearance and sound The Workspace sidebar places appearance and sound controls immediately before Parable Pets. Select the appearance icon to cycle **Auto**, **Light**, and **Dark**; a toast confirms the selected mode. Auto continues to follow the operating system. Sound effects are on by default. Select the sound icon to turn them off or back on for this browser. The choice applies across Parable and does not enable new sounds on surfaces that do not already use them. Audio assets remain unloaded until an existing interaction requests a sound. ## Start with a Problem If no active Parables are available to you and you can create one, Ponder creates and opens **Your First Parable**. Other people's private Parables do not prevent you from getting your own. Reopening Ponder uses your existing Parable. When Home is the only Page, Ponder starts at full width. The left/right arrow control restores the Page and preview alongside it; the up/down arrow control expands or restores the conversation's height. These controls work independently from every tab and remember the width choice. The composer stays centered at a comfortable width. An empty conversation shows the Ponder orb without introductory copy. Ponder expanded in both directions shows the Parable title in Editorial New, at the same size as the breadcrumb title. Side-by-side, its header says **Ponder**. The restored view keeps that title as the first breadcrumb, followed by compact uppercase Piece names. Expand and restore animate smoothly, respect reduced motion, and play transition sounds only when your sound preference is enabled. The Page's bottom editor starts closed. Choose a document tab to open it; Ponder remembers whether you left that editor open or closed. A Page without Panes shows the dotted canvas alone. Handle-display menus and package-transfer controls are temporarily hidden. The mode dropdown stays visible while your Parable is **Personal**. Choose **Publishing** there to save Versions and invite participants when you have permission to change its Collaboration Mode. A **Problem** is the shared thread for an outcome, question, risk, or decision. Give it a name that a teammate can recognize later, then keep working in the same thread as the surrounding Parable changes. To create one from the Problem picker, type its name in search and choose **Ponder Problem**. The new Problem keeps the name you typed. Use a separate Problem when the work has a different outcome, owner, or review path. Keep the same Problem when you are refining the same outcome across several messages or pieces of a Parable. ## Give Ponder the right context Ponder can work from context already available to the Problem and can use authorized tools to inspect the Workspace when a request needs more. A Problem keeps its connection to its Parable even when no specific Piece is selected. When the Parable changes, its attached context still identifies the Parable; Ponder can read current details before acting. Merely opening another Parable, change, or Piece does not silently rewrite the Problem before your next message. Each Message receives the same definition revision and Current or Report data reading used by the open Parable's React and Plots, together with the selected Changes and Piece. Queued Messages and approval continuations retain that view. This applies to every tool in chat and Processes: context links and the current view are optional. Name another Parable, Piece, or set of Changes to work there; Ponder uses that target instead of replacing it with the open view. Without a view, Ponder can discover an authorized target and asks only when the choice remains ambiguous. A target, required fields, or current revision may still be needed by the action itself. Tools that manage context links naturally need the link they act on. Context helps Ponder understand the work; it does not give Ponder new access. You and Ponder can use only the information and actions allowed by your current Workspace access. If a response seems too broad, name the relevant Piece or select a Power that knows how to inspect it. You keep the same Message history without turning browser navigation into hidden Problem setup. ## Choose how Ponder should approach the work The composer starts with **Automatic** under **Problem**, which is the current Parable's primary Problem; open the list to work in a specific Problem instead. Every response also has a **Persona**: a reusable approach such as coordinating, composing, checking, or bringing several perspectives together. **Automatic** under **Persona** is the Coordinator; Ponder resolves an active Persona before each response. Choose **Simple**, **Standard**, or **Strong** in the input footer. Each is a saved ranked-provider configuration; new Personas start with Portal in all three. The names do not add hidden prompts or change model effort by themselves. The **Profile settings** gear beside these choices opens the current profile's ranked models in a dialog. **Save for Me** keeps your edits as a private copy that applies only to you; **Update Persona** shares them with everyone who uses the Persona, after a permission- and revision-checked save; **Reset** discards a private copy. See [Personas](/ponder/personas) for ranking and native configuration. Problem, Persona, and Powers keep a small uppercase label inside each picker, before the icon and selected value, including when that value is Automatic. Automatic values use the same muted text treatment. Presence avatars sit at the right end of the Problem row, vertically centered with its controls. The input footer also holds attachments and Send. Persona and Powers sit below the input, and Problem stays above it. Selected choices show names only. Expand a ranked model row to open its complete **Configuration**, including structured output and other native operation settings. Unset values are shown as placeholders and do not change the saved settings. Saving those settings does not establish that the selected provider can execute every operation; unavailable adapters and privacy requirements still apply. You can also select one or more **Powers** when the work needs a reusable set of instructions. The **Powers** control opens a searchable list; each row carries a checkbox on the left that reflects whether the Power is selected, and choosing the row toggles it. Hover a row to reveal its Edit pencil. Personas and Powers guide the approach; neither can expand your permissions. Each Message captures your open Parable, Changes, version, and Piece even when none is attached to the Problem. Queued Messages and approval continuations keep that view. Context links are optional reference material, not permission to use a tool; Ponder can discover or ask for a target when no view is selected. ## Send one clear request Write what you want to achieve, what a good result looks like, and any boundary that must remain true. Use the arrow to send the message and begin the work. While Ponder is answering, the composer stays open. Sending again queues the Message: it waits in a stack above the composer with your portrait and its place in line, and goes out on its own when the current response settles. Remove a queued Message from the stack if you change your mind; **Stop**, beside the attachment control, ends the current response. Only your own queue is shown; other people's queued Messages are not yet visible. Problem, Persona, and Powers remain available while Ponder answers. A queued Message keeps the Persona, Powers, attachments, and context selected when you sent it; later changes apply to later Messages. Switching Problems leaves the other response running. After Stop or a failed response, use **Resume** to continue a held queue. The thread follows new content smoothly while you are at the bottom. Scrolling up keeps your reading position until you return to the latest Message; reduced motion uses immediate scrolling. Ordinary responses stream into the thread as the model writes. Each reply is signed **Ponder** followed by the Persona that answered, for example **Ponder Coordinator**. An OpenRouter-backed reply shows its reported **AI usage** beside the time. A tool loop updates that amount after each model step whose charge is known, marked **so far**, and settles on the response total when the reply finishes. A partial receipt is marked **recorded**; a finished reply whose provider did not report a charge says **AI usage unavailable** instead of showing zero. Before the first words arrive, the Ponder glyph at the head of the reply is the thinking state: it breathes beside **Thinking…**, or beside the name of the tool being run. When the answer lands the same row settles into **Thought for 4 seconds** and stays shut; a reply opened later counts its steps instead. Open the row to see the trace: each tool step with its outcome (failed and disallowed steps are marked), opening again to its parameters and result, and the model's reasoning in the muted voice. A reply with nothing to trace shows no row. A Pane preview or a Ping question a tool produces stays in the answer, not behind the trace. An Ask policy can pause an ordinary chat tool call for **Deny once** or **Allow once**; approving authorizes only that presented action, and the row reads **Waiting for you…** until you decide. The pending request is saved with that Message; your decision continues the same tool call. Authorized tool calls, including creating a Package, run in ordinary chat. Ponder asks for a Process only when you want separately managed work. A Question appears in the reply and waits for your answer; saving the answer continues the same Problem. If the connection fails before continuation starts, the answer stays queued for retry. If the Message was saved but the response could not start, the thread reports that failure; send a new Message to continue. Tool steps distinguish a rejected action from an unconfirmed result. A rejection can be corrected. An unconfirmed write asks you to verify the saved state before continuing, so a retry cannot silently repeat the change. Pane previews report access or rendering failures directly instead of treating an error page as a finished preview. A Pane preview follows your selected Changes or version and data reading when no target is specified. Naming another authorized Parable previews that target without inheriting the previous Parable's draft, Report, or Piece. The camera uses captured code and authorized Preferences. Live SQL and Plot requests are not executed inside the captured preview, so a Pane that needs those requests can show its data-host error. If a model sends an invalid tool response, Ponder stops that response and keeps completed actions. Send another Message to continue. The failed step's speculative text is excluded from the next attempt's context. Select an existing Problem or create one with a title a teammate can scan. Navigate to the Parable or Piece Ponder should consider. Match the approach and depth to the work in front of you. State the desired result, important constraints, and how you will judge it. Check sources, proposed changes, requested approvals, and available proof before you publish or rely on the outcome. ## Move between conversation and work Ponder opens conversation-first, filling the height of its column immediately. On desktop, a Parable with additional Pages starts with Ponder at half the available width beside the working surface. Use the left/right arrow to switch between full width and the split; that choice is remembered for the Parable. You can also drag the split. Narrow screens keep the stacked layout. The compact views in its header keep the rest of the work close: * **Pieces** shows Pages and Packages together, including Home and each Package's Panes and Plots. Search covers the complete hierarchy. The **Add Package** icon sits beside the search field and creates a root Package. Existing Page and Package links continue to open this unified view. * **Collaboration** contains **Deployments**, **Participants**, and **Publishing**. Deployments searches and lists Workspace targets; Participants uses the RACI actor picker and assignment rows; Publishing keeps publish actions and patch history. Problems, Proofs, and Pings remain reachable through existing links but are temporarily absent from the header while those surfaces are unfinished. Select a view to reveal its tree or publishing details above the conversation. Select the Ponder header or diagonal arrow to expand fully up and right; select it again to restore the split width and conversation height. The vertical and horizontal arrows control each direction independently. All three arrows point toward their next action, and behave the same in Pieces and every Collaboration section. Your Problem remains the thread across both layouts. Deployment, Version, State, and Changes stay above the expanded Ponder conversation when those controls are shown. The first breadcrumb uses the Parable's Editorial title; later Pieces use smaller, muted uppercase Fraktion labels. The connected context group below the Ponder header contains Search, the Workspace icon, Version, State, Changes, Reports, and Reporting Actions. Changes keeps its space; the other controls compact, and field labels appear when the panel has room. The live Report reading shows **No Reports** without repeating a Reports caption. Your own Changes are **My Changes** in both the group and menu, with their last-change age beside the name. This applies to your Pending, Proposed, and historical Changes. Collapsed Version, State, Changes, and Report selectors use text. The Version control always shows its number; the **Latest** badge appears on eligible rows inside the Version dropdown, including v0. Dogfood uses the Parable mark as its Workspace icon. Only Search, Workspace, and Reporting Actions use icons in the closed group. Search opens a cascader across every available context choice and Report action. Search for a Workspace, Version, State, author’s Changes, Report, Provider, or action. Choosing Changes also selects their Version and State. Searching alone changes nothing. A Parable Version and a Report reading are different choices. The Version identifies the Parable's published structure and behavior. **No Reports** means live Provider data without a stored Report; dated Report runs identify saved readings. Selecting a Report does not select a different Parable Version. Reports on the same day include a time so they remain distinguishable. The Report cascader also lets you inspect the Providers behind a reading. An unavailable live reading explains why. The clipboard-check icon at the right of the group opens **Reporting Actions**, including **Plan Reports** for scheduling. It offers the actions supported by the current surface, participation mode, and responsibility. Pinging and Peeping show only Search, Reports, and Reporting Actions in the group; Search still reaches permitted Version and Changes selections. Refused actions retain their explanation. **Prove Report** currently explains that its runner is unavailable. Use the **Active Participation Mode** control beside **Problem** in Ponder chat when the Parable surface should match what you are doing now. **Publishing** keeps the authoring surface available, **Pinging** emphasizes clarification and collaboration, and **Peeping** keeps a reading-focused view. A mode can hide controls but cannot widen your current Workspace access or Parable responsibility. See [Collaboration Modes](/ponder/parables/permissions/collaboration-modes). Personal Parables save edits directly to main; their dropdown shows **Personal** and offers **Publishing** through the saved Collaboration Mode action. The Collaboration panel also offers **Enable Publishing & Pinging**. Presence sits to the left of Problem. The Report cascader drills from readings into their Providers. The presence roster opens toward the chat content. Report actions are hidden in Personal mode and remain visible in every participation mode when versioning is enabled, with a reason on restricted actions. Plan Reports opens the scheduling dialog. Deployment, Version, State, and Changes sit below the Ponder header and above the conversation, with a matching background and a bottom divider. ## Collaborate without losing the thread When a connection resumes, Ponder continues after the updates this tab has already received. Delayed live updates do not replay those acknowledged changes. Current access still governs every update; losing access removes the reader from the affected conversation. The presence portraits in the Parable header show who is here. Hover or focus a portrait or the overflow count to reveal one roster of names, recent activity, and locations. The roster stays separate from the neighboring action controls. Messages remain in the Problem after you navigate away. Copy a link when a teammate should review a particular message. Use a Ping when you need a person to answer a question or be informed, and use Proofs when the result must be supported by evidence rather than agreement alone. Each of those is a Workspace API operation you can call yourself: a send is [Send a Message to Ponder](/protocols/reference/web-api/parable-problem-stream-ponder-parable), ending a reply on purpose is [Stop a Ponder reply](/protocols/reference/web-api/parable-problem-stop-ponder-parable-message), and a Ping answer is [Answer a Problem Ping](/protocols/reference/web-api/parable-problem-answer-parable-problem-ping). The send streams the reply back as it is written, so it is reached through the app's own server rather than the generated SDKs. Long Problems open at their newest Messages so the conversation is ready quickly. Choose **Load earlier Messages** at the top of the thread when you need older history; loading a page does not change or summarize the durable Messages. Ponder may propose changes or ask to use an action. Review the target and the effect before approving. A successful response is not the same as a published change: use **Publish** to inspect audience, responsibility, and readiness. ## What changes and what stays with the Problem | When you change | What Ponder preserves | | ----------------- | ---------------------------------------------------------------------------------------------------------------------- | | The open Piece | Earlier Messages keep the context they used; the next Message can use the new Piece. | | Persona | The Problem's assigned Persona changes for future Messages; active and queued responses keep their accepted selection. | | Selected Powers | The next response uses the new selection; earlier responses retain their instructions. | | Collaborators | Each person can review only the Problem and context their Workspace access permits. | | Browser location | The durable Problem, Messages, and review history remain available when you return. | | A proposed action | Declining performs nothing; approving authorizes only the presented target and effect. | ## When something does not work | What you see | What to do | | --------------------------------- | --------------------------------------------------------------------------------------------------------------------- | | Ponder lacks useful context | Name the target and intended action; Ponder can inspect available resources or ask when the target remains ambiguous. | | A Power or Persona is unavailable | Ask a Workspace manager whether it is available for new work. Existing history remains readable. | | An action asks for approval | Check the exact target and effect. Approve only if it matches your intent. | | A response stops or fails | Read the actionable error, keep the same Problem, and send the missing information or try again. | | You cannot see a Problem or Piece | Confirm you are in the correct Workspace and ask its owner about access. Ponder does not bypass protection rules. | ## Next Choose whether a Parable supports active Ponder work or a repeatable Playbook. Choose and manage reusable approaches for different kinds of work. Apply reusable instructions to a particular Ponder response. Match the Parable surface to authoring, clarifying, or reading. Adopt and place a visual companion without changing how Ponder works. Appearance changes synchronize between open app tabs so the theme icon and the next toggle agree with the rendered colors.