> For the complete documentation index, see [llms.txt](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/.spec_system/archive/phases/phase_29/session_14_one_to_watch_surface.md).

# Session 14: One-To-Watch Surface

**Session ID**: `phase29-session14-one-to-watch-surface` **Status**: Not Started **Estimated Tasks**: \~12-25 **Estimated Duration**: 2-4 hours

***

## Objective

Turn existing predictions, retros, and calibration into a dedicated "what to watch next cycle" surface. Maps the Tier 3 One-to-Watch prediction-framing idea.

***

## Scope

### In Scope (MVP)

* Build presentation over existing prediction, retro, and calibration records.
* Rank forward-looking watch items using existing evidence, prediction, and corroboration/reception fields where available.
* Clearly label unknown or uncalibrated accuracy; do not ship mock accuracy chips.
* Render in live Brief/Trends and static Brief as appropriate.

### Out of Scope

* Any new prediction model or invented next-cycle claim.
* Mock accuracy chips.

***

## Prerequisites

* [ ] Sessions 03 and 04 complete (reception and corroboration fields available).

***

## Deliverables

1. One-to-Watch presentation over existing prediction/retro/calibration records.
2. Forward-looking ranking using available evidence and derived fields.
3. Explicit unknown/uncalibrated accuracy labeling.
4. Unit/e2e tests for rendering and missing-calibration honesty.

***

## Success Criteria

* [ ] One-to-Watch rows render from existing prediction records.
* [ ] Missing calibration is labeled explicitly.
* [ ] No invented next-cycle claims or mock accuracy chips are published.
* [ ] Payload budget and privacy scans remain green.

***

## Key Files

* `scripts/lib/ai-runtime/predictions.ts`
* `scripts/lib/ai-runtime/retros.ts`
* `scripts/lib/ai-runtime/backtests.ts`
* `src/extensions/trend-finder/view-model.ts`
* `src/extensions/trend-finder/views/brief-view.tsx`
* `scripts/extensions/trend-finder/static-brief-renderer.ts`

***

## Comparison Notes (folded from comparison plan)

**Effort:** Low-Medium. **Boundary risk:** None. Tier 3 polish. **Depends on Sessions 03 and 04** (reception and corroboration fields feed the ranking).

**One to Watch prediction framing.** In TrendingAI six streams are ranked as next-cycle bets, but the accuracy chips are still mock. Trend Finder adoption: present existing predictions, retros, calibration, and Brier scoring as forward-looking watch rows without mock accuracy - clearly label unknown or uncalibrated accuracy and ship no mock chips.

**TrendingAI source pointers.** `scripts/classify-one-to-watch.ts`.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/.spec_system/archive/phases/phase_29/session_14_one_to_watch_surface.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.