peer-readacross

1# Peer read-across
2 
3When two names are linked — competitors, a supplier and its customer, two plays
4on one theme — the interesting signal is the **read-across**: a peer's print that
5resets the other's setup. `alphai_pair_analysis` is built for exactly this.
6 
7## Steps
8 
91. **Resolve both tickers.** If given company names, map them with
10   `alphai_tickers(q=...)`. Any symbol that isn't a recognized active ticker
11   comes back in `unknown_tickers` and contributes no rows — surface that.
122. **Run the comparison.** Call `alphai_pair_analysis(ticker_a, ticker_b)`. It
13   returns three things: news naming **both** companies (the shared read-across),
14   plus each ticker's **own** recent news for context.
153. **Tighten on request.** Raise `min_relevance` (default 4) for only the
16   strongest items, or `limit` for more rows per list.
17 
18## Output
19 
20- **Shared story** — the news naming both names: what links them right now and
21  which way the read-across cuts (does A's news help or hurt B?).
22- **{Ticker A}** — 2–3 of its own top stories, one-liners.
23- **{Ticker B}** — same.
24- **Net read** — one or two sentences: are they moving together or diverging, and
25  what's the single linking factor (a shared customer, a sector catalyst, a
26  head-to-head product)?
27 
28## Guardrails
29 
30- If `alphai_pair_analysis` returns no shared rows, say so — the two names may
31  simply not be in the same story flow right now; fall back to summarizing each
32  side's own news rather than forcing a connection.
33…