architecture doc

This commit is contained in:
Wolf committed 2026-10-04 20:57:02 +02:00
1 parent 97c3046f53
commit 8f37f51254
1 file changed
+18 -14
+18 -14
View File
@@ -3,7 +3,7 @@
The target design of roledesk's ranking: how a role gets from a board to the Roles feed for one search agent, and the key decisions behind it. What gets built is tested against this document.
- **Fetch gate**: the agent's hard rules, a yes or no per role, in four parts: world, location, role exclusion and role fetch.
- **Analytics score** and **analytics filter**: what decides the **cut**, the roles that pass the analytics filter and get fetch text and the model pass.
- **Input analytics score** and **input analytics filter**: what decides the **cut**, the roles that pass the analytics filter and get fetch text and the `model analytics score`.
- **Feed scores**: the two orders of the feed, the want feed score and the match feed score.
- **Fetch text**: the second HTTP read of a role's own page, without a model.
- **Extract**, **judge**, **summarise**: the model calls (Haiku).
@@ -19,13 +19,13 @@ The target design of roledesk's ranking: how a role gets from a board to the Rol
search providers: their own saved query
│
▼
2 Analytics score, no tokens ─ prompt closeness, CV closeness, affinity → the cut
2 Input analytics score, no tokens ─ prompt closeness, CV closeness, affinity → the cut
│
▼
3 Fetch text ─ the role's own page, for cut roles without text
│
▼
4 Model pass ─ extract the cut → fetch gate and cut again → judge the cut
4 Model analytics score ─ extract the cut → fetch gate and cut again → judge the cut
│
▼
5 Feed ─ every role that passes the fetch gate, in two orders;
@@ -85,34 +85,38 @@ The gate rejects on evidence only. A role with an unknown location passes until
- One posting listed several times (by a search provider and by the company's board, or by one board under several ids) is one role. Two listings are one posting when they share company, title and country, and their towns overlap; a listing without a town matches any town.
- The kept copy is the company board's over a search provider's, then the one with text, then the earliest posted. Only the kept copy is scored, read by a model and shown; it lists the others.
## 2 Analytics score and filter
## 2 Input analytics score and filter
#### 2.1 Closeness
Each role is embedded and scored semantically:
- **Prompt closeness** is its level against the best of the agent's prompts.
- **CV closeness** is its level against the closest part of the CV.
Both are calibrated levels from 0 to 1, the same in every run. A liked company adds 0.05 to both levels, a favourite 0.1. The bonus counts before the count and the minimum apply.
Both are calibrated levels from 0 to 1. A liked company adds 0.05 to both levels, a favourite 0.1. The bonus counts before the count and the minimum apply.
The levels drive the `analytics filter`. A role passes it when it passes the fetch gate (1.1.1 to 1.1.3) and:
#### 2.2 Input analytics filter
- is among the best N by prompt closeness, each at least X (500 and 0.6 to start), or
- is among the best M by CV closeness that the first list leaves out, each at least Y (150 and 0.6 to start), or
- is liked or saved, whatever its levels.
The `closeness`es are the main input for the `input analytics filter`, which determines which roles get `fetch text` and the `model analytics score`. A role passes the `input analytics filter` when it:
- passes the `fetch gate` (1.1.1 to 1.1.3)
- is among the best N by `prompt closeness`, each at least X (500 and 0.6 to start), or
- is among the best M by `CV closeness` that the first list leaves out, each at least Y (150 and 0.6 to start), or
- is liked or saved not matter the `closeness`.
The two lists are kept apart because they answer different questions (what I want, what I am), and a merged number lets the stronger side crowd the other out. For a broad agent the count stops each list; for a narrow agent the minimum stops it, so roles that do not fit are not read just to fill the count.
Newness and job likes are not part of the `analytics score`. A role is read once, pulls run every few hours, and votes come after the read.
Newness and job likes are not part of the `input analytics score`. A role is read once, pulls run every few hours, and votes come after the read.
An agent without a CV has no CV list and no judge. An agent without prompts has no prompt list and no prompt closeness in the want feed score.
The `analytics filter` determines which roles get `fetch text` and the model pass.
## 3 Fetch text
Some job boards have one API for the listings and another for the job specs. `fetch text` reads the role's own page for every role in the cut that came without text. Once the full text is fetched, the role is embedded again and its levels recomputed. A role that enters the cut after this recompute gets its text on the next pull.
## 4 Model pass
## 4 Model analytics
All roles in the cut go through the detailed analysis and metadata extraction. Extract and judge are two calls: `extract` needs no CV, it is faster, and it is the final step of the ingestion, so it decides what finally passes the `analytics filter`.
@@ -154,7 +158,7 @@ The `want feed score` consists of `prompt closeness`, newness, company likes and
#### 5.1.2 Match feed score, "What fits me"
The `match feed score` orders the judged roles by `CV match`, then the rest by `CV closeness` (embedding only, as they had no model pass).
The `match feed score` orders the judged roles by `CV match`, then the rest by `CV closeness` (embedding only, as they had no `model analytics score`).
#### 5.1.3 Job likes