> ## Documentation Index > Fetch the complete documentation index at: https://docs.moda.dev/llms.txt > Use this file to discover all available pages before exploring further. # Conversations > Browse every ingested conversation, and inspect a single conversation as a full message trace or as its extracted world state. Conversations (sidebar: Observe → Conversations) lists every conversation Moda has ingested and is the entry point for inspecting a single conversation turn by turn. New conversations appear within seconds of sending data; analysis results attached to them (use case, world state, signals) fill in within minutes. ## Conversation list The list supports: * **Search** — the "Search conversations..." box filters the list. * **Filters** — environment (Production / Development / Staging) and use case. * **Time range** — All time, Last 24 hours, or Last 30 days. * **Sort** — Newest first, Oldest first, Most messages, Fewest messages. * **Pagination** — page sizes 10 / 25 / 50 / 100 with Previous / Next; the total count loads separately. The first page refetches automatically every 15 seconds while the tab is visible, so new conversations stream in without a manual refresh. Filters, sort, and page size are reflected in the URL, so a filtered view can be shared as a link. Arriving from a user's detail page pre-filters the list to that user; a chip above the table clears the filter. ### Columns The **Columns** button shows or hides columns; column widths can be dragged. Preferences are saved in your browser. | Column | Shows | Visible by default | | ------------------- | -------------------------------------------------------------------------------------------------------------------------- | ------------------ | | Conversation | Preview of the first message text. | Yes | | Processed | Whether processing has completed (Processed / Unprocessed). | Yes | | Env | Environment badge (Prod / Dev / Staging). | Yes | | Messages | Message count. | Yes | | Use case | The assigned use-case cluster. | Yes | | Last active | Time of the most recent message. | Yes | | Conversation ID | The full conversation ID. | No | | Use case confidence | Membership score for the use-case assignment. | No | | First active | Time of the first message. | No | | Indexed | When Moda first indexed the conversation. | No | | Processing | Processing status badge. | No | | World state | World-state build status: Ready when built, Stale when out of date, otherwise the in-progress status (Pending by default). | No | Clicking a row opens the conversation detail in a new tab. ## Conversation detail The header shows the conversation ID, date, duration, and turn count, plus badges when they apply: a frustration score (shown when the score is 5 or higher), the tool-failure count, and the use case with its confidence. Previous / next links step through neighboring conversations. A toggle switches between the two views: **Full Trace** and **World State**. While a conversation is still mostly unprocessed, a strip lists the pending pipeline stages (`segmentation`, `world-state`, `cluster`, `frustration`); it disappears once most stages have completed. ### Full Trace Full Trace is the raw timeline: every message and content block in order. Each row shows content appropriate to its type: * **User messages** — the message content, rendered as markdown. * **Agent responses** — the model and provider above the response text. * **Thinking** — collapsed to a single expandable line. * **Tool calls** — expandable input and result; failed calls are highlighted. Every message has a copy button on hover. Messages that changed the tracked world state carry event chips; selecting a turn opens an inspector for that turn's state changes. A filter rail on the left toggles block categories — Prompts, Agent Responses, Thinking, Tool Calls (with per-tool sub-filters), Images, Email, Call Transcripts — each with a count, plus **Clear Filters**. When the conversation carries signals, context banners appear above the timeline: * **Tool Call Failure** — the tool name and error, with **Jump to failure**. * **User Frustration Detected** — the score, trajectory, and primary cause, with clickable quotes that jump to the quoted turn. Evidence links from [Signals](/dashboard/signals) and [Problems](/dashboard/problems) open Full Trace scrolled to the relevant turn or failed tool call. ### World State World State shows what Moda extracted from the conversation: the tasks the user pursued and the facts established along the way. It has two tabs. **Tasks** lists the conversation's task threads with a resizable detail pane. Each thread has a status (Open / Resolved / Cancelled) and can contain subtasks (Open / Done / Blocked / Cancelled). The detail pane shows a progression timeline of actions — Message, Tool call, Correction, Subtask opened, Subtask completed, Failure, Retry — and each step can jump back to the matching turn in Full Trace. **Add to eval set** saves a task as a replay case for [Replays and Playground](/dashboard/evaluate). **Facts** lists the facts extracted from the conversation; when the position is known, each fact is tagged with the turn where it was established. Both tabs are searchable ("Search threads" / "Search facts"); Tasks additionally supports filtering by thread status, subtask status, and action type, and sorting by Most recent turn, Status, or Title (A→Z). While the build is in progress, a "Still building world state" banner shows partial results and updates live. ### User memory panel At the top of the World State view, a collapsible **User memory** panel shows a persona document built from the user's messages — voice, decision style, and constraints — used to simulate this user in replays. The panel header shows how many user messages have been folded in, and each observed trait carries a chip with its occurrence count and the last message where it appeared. ## Trace viewer A standalone trace viewer exists at `https://moda.dev/trace/`. It renders a span tree for one trace with a span detail pane, and supports a `?span=` parameter to deep-link a specific span. It is auth-gated and not linked from the sidebar — open it by URL when you have a trace ID. ## Next steps * [Signals](/dashboard/signals) — the detections that produce the banners and badges on conversation pages. * [Use Cases](/dashboard/use-cases) — the clusters behind the Use case column. * [Replays and Playground](/dashboard/evaluate) — where tasks added to an eval set are run. * [Data API: conversations](/data-api/conversations) — fetch conversations and world state programmatically.