Write the target architecture on its own and keep today versus decided as the ranking flow plan
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
7197b993c5
commit
4565507d7a
3 files changed
+186
-74
No files matched your search
@@ -43,4 +43,4 @@ A larger rework is planned first, as a doc in `docs/` committed on main with wor
|
||||
|
||||
# Rule:
|
||||
|
||||
`docs/architecture.md` is the owner's document: the flow from board to feed and the key decisions about it, marked today, decided or open. Keep it short and update it when a key decision is made or lands. The detailed reasoning goes into `decisions.md`.
|
||||
`docs/architecture.md` is the owner's document: the target design of the flow from board to feed and its key decisions, with no description of today's code. What is built is tested against it. Change it only when the owner makes a key decision; the way there goes into a plan, the detailed reasoning into `decisions.md`.
|
||||
+72
-73
@@ -1,113 +1,112 @@
|
||||
# Architecture
|
||||
|
||||
This is the owner's document: how a role gets from a board to the Roles feed, for one search agent, and the key decisions about that flow. It is the picture any change is made against. `decisions.md` is the detailed log behind it. Each stage says what the code does **today**, what was **decided** (since 2026-10-04, not built yet) and what is still **open**.
|
||||
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. The way from today's code to here is in `plan-ranking-flow.md` while that plan is open; the detailed reasoning is in `decisions.md`.
|
||||
|
||||
## Three scores
|
||||
## Terms
|
||||
|
||||
Each agent decides about a role three times: a gate on what comes in, a gate on what the models read, and an order. Everything after that is the owner's filters, saved per agent.
|
||||
- **Fetch gate**: the agent's hard rules, a yes or no per role.
|
||||
- **Analysis score**: what decides the **cut**, the roles that get fetch text and the model pass.
|
||||
- **Final score**: the order of the feed.
|
||||
- **Fetch text**: the second HTTP read of a role's own page, without a model.
|
||||
- **Extract**, **judge**, **summarise**: the model calls (Haiku).
|
||||
- **Fetch terms**: words a big board must match to send a role. They narrow the read at the host and are not part of the fetch gate.
|
||||
- **Affinity**: an agent's setting for a company: hidden, neutral, liked or favourite.
|
||||
- **All roles**: a company switch, the same for every agent, that passes the whole company through the fetch gate.
|
||||
|
||||
- **Fetch gate**, a yes or no: the agent's hard rules. These are the required countries (Europe), the Where lines (countries, towns, remote) and the titles to leave out. A company set to **All roles** passes everything but the required countries: its roles skip the Where lines and the titles to leave out. The gate applies at every stage: at the host when the host can filter, in the cheap pass, again after extract (now with the real location and remote area), and in the feed. A role that fails it is never read by a model and never shown.
|
||||
- **Analysis score**: decides which roles that pass the fetch gate make the **cut**, the roles that get fetch text and the model pass.
|
||||
- **Final score**: orders the feed.
|
||||
|
||||
Names: **fetch text** is the second HTTP read of a role's own page, with no model (the code calls it `enrich`). **Extract**, **judge** and **summarise** are the model calls. **Fetch terms** are words a big board must match to send a role; they narrow the read at the host and are not part of the fetch gate.
|
||||
## Flow
|
||||
|
||||
```
|
||||
company boards (ATS) search providers
|
||||
fetch gate at the host + fetch terms, their own saved query
|
||||
only boards ≥300 roles whose host filters
|
||||
boards ≥300 roles whose host filters
|
||||
│ │
|
||||
▼ ▼
|
||||
1 Fetch ─ list pages: title, place, teaser or text
|
||||
│
|
||||
▼
|
||||
2 Cheap pass, no tokens ─ prep, embed, fit to the prompts, closeness to the CV, fetch gate
|
||||
│
|
||||
▼ analysis score → the cut
|
||||
3 Fetch text ─ the role's own page, for cut roles without text → embed, rescore
|
||||
2 Fetch gate ─ required countries, Where lines, titles to leave out
|
||||
│
|
||||
▼
|
||||
4 Model pass (Haiku) ─ extract the cut → fetch gate and cut again → judge the cut
|
||||
3 Analysis score, no tokens ─ fit to the prompts, closeness to the CV, affinity → the cut
|
||||
│
|
||||
▼
|
||||
5 Feed ─ every role that passes the fetch gate, in two orders:
|
||||
"what I'm looking for" (final score) and "what fits me" (CV match);
|
||||
front-end filters and saved filters narrow it
|
||||
4 Fetch text ─ the role's own page, for cut roles without text
|
||||
│
|
||||
▼
|
||||
6 After the ranking ─ summarise the top of the feed
|
||||
5 Model pass ─ extract the cut → fetch gate and cut again → judge the cut
|
||||
│
|
||||
▼
|
||||
6 Feed ─ every role that passes the fetch gate, in two orders;
|
||||
filters and saved filters narrow it
|
||||
│
|
||||
▼
|
||||
7 After the ranking ─ summarise the top of the feed
|
||||
```
|
||||
|
||||
## 1 Fetch
|
||||
|
||||
**Today.** The Where lines become the reach: a country and remote filter the host applies. This only happens on boards with 300 or more roles whose host can filter by place. Smaller boards, and hosts that cannot filter, are read whole. Fetch terms only apply to companies set to All countries (Mistral AI and OpenAI today), and only on hosts that take a query (Workday, SuccessFactors, Oracle, Phenom, Eightfold, SmartRecruiters). Search providers send their own saved query and take neither filter.
|
||||
- On a company board with 300 or more roles, the host is asked for the fetch gate's location part (the required countries and the Where lines) and for the fetch terms, each where the host can filter on it. A smaller board, or a host that cannot filter, is read whole.
|
||||
- A company set to All roles is fetched from every required country, without fetch terms.
|
||||
- A search provider is read by its own saved query and takes neither filter.
|
||||
- A read narrowed by fetch terms is not the whole board, so it closes no role. Roles on such boards close by age. This is accepted because ranking relies on recency, not on closing.
|
||||
|
||||
**Decided.** The fetch gate's location part and the fetch terms become one block on the agent form and follow one rule: each applies to every board with 300 or more roles whose host can filter on it. Fetch terms no longer depend on All countries. Agent 2 has no fetch terms today, so nothing changes on the live server until some are set. The titles to leave out cannot be asked of a host, so that part of the fetch gate starts at the cheap pass.
|
||||
## 2 Fetch gate
|
||||
|
||||
**Consequence.** The pull never closes a role against a read narrowed by terms, because that read is not the whole board. With terms on every big board, roles there close only by age. Accepted, since Wolf ranks on recency, not on `closed_at`.
|
||||
- A role passes when it is in the required countries (Europe), matches at least one Where line (a country, a town or remote), and has no title to leave out in its title. With every Where line empty, a role can be anywhere in the required countries.
|
||||
- A role of a company set to All roles passes on the required countries alone. This is for small companies worth a speculative approach, whatever their roles' location or title.
|
||||
- The gate rejects on evidence only. A role with an unknown location passes until extract has read it.
|
||||
- A hidden company is never scored, read by a model or shown.
|
||||
- The same gate applies at every stage: at the host where it can filter, before the analysis score, again after extract with the real location and remote area, and in the feed.
|
||||
|
||||
## 2 Cheap pass
|
||||
## 3 Analysis score and the cut
|
||||
|
||||
**Today.** Every open role gets one score per agent: `(0.6 fit + 0.2 newness + 0.2 company affinity + 0.2 taste + prefer gates) / sum of the weights`. Fit is the calibrated cosine to the best of the agent's prompts. The gates (Where lines, titles to leave out) set a failing role's score to 0 with a reason. A gate rejects on evidence only, so a role with no known location still ranks until extract fills it in (323 of agent 2's 7,263 roles that pass). Closeness to the CV (`cv_fit`) is stored beside the score but is not part of it. That one score drives enrich, extract, summarise, judge and the feed order.
|
||||
- Free and local: each role is embedded once. **Fit** 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.
|
||||
- Affinity is a bonus on both levels, in the same proportion as in the final score: a liked company about 0.05 above neutral, a favourite about 0.1. It is a nudge, not a pass.
|
||||
- The cut holds the roles that pass the fetch gate and are:
|
||||
- among the best N by fit, each at least X (500 and 0.6 to start), or
|
||||
- among the best M by CV closeness that the first list leaves out, each at least Y (150 and 0.6 to start), or
|
||||
- liked or saved, whatever their levels.
|
||||
- Newness and taste are not part of the analysis score. A role is read once and pulls run every few hours, and votes come after the read.
|
||||
- The two lists are not merged into one number. 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.
|
||||
- The cut takes only roles that pass the fetch gate. Measured on 2026-10-04 for agent 2, without the Where lines only 118 of the 500 best by fit were roles the agent could take.
|
||||
|
||||
**Decided.** The one score is split into the analysis score (this section) and the final score (section 5). The analysis score uses fit to the prompts, closeness to the CV and company affinity. It leaves out newness (a pull runs every 6 hours and a role is read once), taste (votes come after the read) and prefer gates. Prefer gates leave the agent; hybrid becomes a feed filter.
|
||||
## 4 Fetch text
|
||||
|
||||
**Decided: the cut is two lists, joined.** One list is by prompt fit. The other is by CV closeness: the roles closest to the CV that the first list leaves out. The two are not merged into one number, because they answer different questions (what I want, what I am), and a merged number would let the stronger side crowd the other out. Each list has a count and a minimum level on the form. For a broad agent the count stops the list; for a narrow agent the minimum does, so roles that do not fit are not read just to fill the count. Starting values: 500 by prompt fit and 150 by CV closeness, each at least 0.6. The minimums are levels of plain fit and plain CV closeness, not of today's blended score. Among agent 2's roles that pass the fetch gate, 2,086 reach fit 0.6, 1,580 reach CV closeness 0.6, and 2,437 reach either, so for agent 2 the counts decide.
|
||||
- Fetch text reads the role's own page for every role in the cut that came without text. The role is embedded again and its levels recomputed.
|
||||
|
||||
**Decided: affinity is a bonus on the level, as today in spirit.** A role's level on both lists rises by the company's affinity. Today the affinity term is weighted 0.2 out of 1.25, which puts a liked company about 0.05 above a neutral one and a favourite about 0.1 above. The cut keeps those sizes. The four company settings are hidden (-1), neutral (0), liked (1) and favourite (2). A hidden company is not scored at all, so it never reaches the cut or the feed. There is no level that pushes a company down without hiding it, and none is planned. Affinity remains a nudge, not a pass: a favourite's role that matches nothing stays out of the cut. Favourite only raises the level. Today it also skips the Where lines; that moves to All roles (section 5).
|
||||
## 5 Model pass
|
||||
|
||||
**Decided: a role you like or save always makes the cut.** This is part of the analysis score, not a separate manual path: a like or a save passes the cut whatever the role's levels, so the role gets fetch text, extract and judge. It goes through on the next pull or agent save, not the moment you click.
|
||||
- One depth: the cut is the only selection, and extract and judge both read all of it.
|
||||
- **Extract** reads the cut first. It fills location, remote area, seniority, languages and deadline.
|
||||
- The fetch gate and the cut are then applied again with what extract filled. A role can drop out, such as one that turns out to be outside the agent's places, or enter, such as one that turns out to be remote. A role that enters is extracted on the next pull.
|
||||
- **Judge** reads the cut as recomputed. It reads each role against the agent's CV, languages, likes and dislikes, and gives skills, experience and career from 0 to 100, one to three strengths and gaps, and a verdict on each must-have. The **CV match** is the three numbers under the agent's weights (30/25/30 to start). Changing the weights asks the model for nothing.
|
||||
- Extract and judge are two calls. Extract needs no CV, and its location and remote answers must reach the fetch gate before judge reads anything.
|
||||
- Each role is extracted once. A judgement is redone only when its input changes. A change to the CV, a prompt, or the like or dislike text re-judges the whole cut (about an hour for 650 roles); a changed posting re-judges that role only.
|
||||
|
||||
**Decided: the cut only takes roles that pass the fetch gate, location included.** For agent 2 on 2026-10-04 (24,711 open roles):
|
||||
## 6 Feed
|
||||
|
||||
| Rules applied before the cut | Roles passing | Fit ≥ 0.6 | Inside today's Where, of the top 500 by fit | Inside today's Where, of the top 150 |
|
||||
|---|---|---|---|---|
|
||||
| Today: Europe, Where lines, titles | 7,263 | 2,086 | 500 | 150 |
|
||||
| Europe and titles, no Where lines | 14,704 | 4,855 | 118 | 28 |
|
||||
| Titles only | 22,297 | 9,161 | 66 | 18 |
|
||||
- The feed shows every role that passes the agent's fetch gate, loaded as you scroll, in every order, newest first included. No order shows a role the fetch gate rejects.
|
||||
- **What I'm looking for** orders by the final score: `(0.6 fit + 0.2 newness + 0.2 affinity + 0.2 taste) / sum of the weights`. Newness halves every 14 days. Taste is the role's closeness to the roles the agent liked, away from those it passed. The weights are set per agent.
|
||||
- **What fits me** orders the judged roles by CV match, then the rest by CV closeness.
|
||||
- Everything else (seniority, location, remote or hybrid, pay) is a filter, not a score term. Filters only narrow what the fetch gate passed.
|
||||
- The Roles page says that the feed is already filtered by the agent's fetch gate, location included.
|
||||
- **Saved filters**, per agent: the current filter settings are saved under a name, loaded with one click, and deleted. There is no editing; a change is a new saved filter.
|
||||
- The company view says what is filtered: for an All roles company, every role in the required countries; for any other company, the roles the agent's fetch gate passes. Looking up a company never silently hides roles elsewhere.
|
||||
|
||||
Without the Where lines, about four in five model reads go to roles outside DK, SE, the Skåne towns and remote, and keeping today's coverage would take a budget about four times larger.
|
||||
## 7 After the ranking
|
||||
|
||||
## 3 Fetch text
|
||||
- Summarise is not part of any score. It runs after the final score, on the top of the feed by the final score (50 to start, its own setting), and on every role liked or saved.
|
||||
|
||||
**Today.** The `enrich` stage reads the role's own page for open roles without text, on hosts that list without it. It uses its own bar from the config (`enrich.top` 500, `enrich.min_score` 0.5, at most 200 per board and 1,000 per run). Embed and score run again for the roles it filled.
|
||||
## Settings
|
||||
|
||||
**Decided.** Fetch text reads the whole analysis cut, so every role the model will read has its text first. The stage is renamed from `enrich` to fetch text so it is not mistaken for a model call.
|
||||
Per agent, on the form:
|
||||
|
||||
## 4 Model pass
|
||||
- name and prompts
|
||||
- the fetch block: required countries, Where lines, titles to leave out, fetch terms
|
||||
- CV, languages, likes and dislikes
|
||||
- the cut: count and minimum by fit, count and minimum by CV closeness
|
||||
- the final score weights, and the CV match weights
|
||||
- summarise size
|
||||
|
||||
**Today.** Extract and judge run on Haiku (summarise is in section 6). Each has a count and a minimum score on the blended score; for agent 2 the count decides every stage.
|
||||
|
||||
- **Extract** reads at most 500 roles scoring at least 0.55. It fills location, remote area, seniority, languages and deadline. A rescore follows so the gates see these columns.
|
||||
- **Judge** reads at most 150 roles scoring at least 0.55, plus the 50 closest to the CV that those leave out. It scores skills, experience and career 0 to 100, plus a verdict on each must-have. These are weighted 30/25/30 into `cv_score`.
|
||||
|
||||
**Decided.** One depth: the cut is the only selection, and both scoring model stages read all of it. A second score inside the cut would defeat its purpose. The order is:
|
||||
|
||||
1. **Extract** reads the whole cut. It is the small, fast call (about 1.5 s a role on the live backend).
|
||||
2. The fetch gate and the cut are applied again with what extract filled, now knowing which roles are really remote and where the rest are. Some roles drop out; some enter, such as roles that turn out to be remote. A role that enters is extracted on the next pull.
|
||||
3. **Judge** reads the cut as recomputed (about 6 s a role).
|
||||
|
||||
**Decided: extract and judge stay two calls.** Extract needs no CV and its location and remote answers feed the fetch gate before judge reads anything. Judge works per agent and role, with the CV in the system prompt.
|
||||
|
||||
**Cost.** Every model read happens once per role (judge once per role and CV), so a larger cut costs mostly a one-off catch-up. With a cut of about 650 roles, that catch-up is about 16 minutes of extract and about an hour of judge on the live backend (`claude_code`, the subscription, so no per-token bill). After it, each pull reads only the roles new to the cut. The recurring cost is a re-judge: changing the CV, a prompt, or the like or dislike text changes every judgement's input, so the whole cut is judged again, about an hour for 650 roles. A changed posting text re-judges that role only. Accepted: the re-judge takes a while but is correct, since the old judgements were made against the old text.
|
||||
|
||||
## 5 Feed
|
||||
|
||||
**Today.** There are two orders. **Score** uses the same score as section 2. **CV match** shows the judged roles first by `cv_score`, then the unjudged ones by CV closeness. Roles that fail the gates are hidden unless Show gated is ticked, so the front-end place filter can only narrow inside the Where lines. A favourite company (affinity 2) skips the Where lines but also gains in the score; that is why OpenAI's London roles rank. All countries and All roles are separate company flags that only change what is fetched.
|
||||
|
||||
**Decided.**
|
||||
|
||||
- The feed shows every role that passes the fetch gate, loaded as you scroll, not only the cut. Newest first stays inside the fetch gate as well, so no order shows roles outside the agent's places.
|
||||
- There are two orders: "what I'm looking for" (final score) and "what fits me" (CV match). The final score includes newness and likes. It is not one blended number.
|
||||
- Front-end filters only narrow further. The Roles page says that the feed is already filtered by the agent's fetch gate, location included.
|
||||
- **All roles**, one company switch in place of today's All countries and All roles. It is for small companies worth a speculative approach ("have you thought about hiring in Denmark?"). The company is fetched from every country inside the required countries (Europe) and without fetch terms, and its roles pass the fetch gate whatever the Where lines and the titles to leave out say. It changes nothing in any score: its roles enter the cut only by their levels, and favourite is what pushes them up. It applies to every agent, as the two switches do today.
|
||||
- The company view says plainly what is filtered: for an All roles company, "every role in Europe, not filtered by country or title"; for any other company, that it shows the roles the agent's fetch gate passes. Looking up a company must not silently hide roles in other countries.
|
||||
- **Saved filters**, per agent. The current filter settings can be saved under a name, loaded with one click and deleted. There is no editing: to change one, save a new one and delete the old.
|
||||
|
||||
**Decided: the final score** is today's formula without the prefer gates: 0.6 fit to the prompts, 0.2 newness, 0.2 company affinity, 0.2 roles you liked, over the sum of the weights. Everything else, such as seniority, location and pay, is a filter, not a score term, so a role is never judged twice by the score and by a filter.
|
||||
|
||||
## 6 After the ranking
|
||||
|
||||
**Today.** Summarise reads at most 30 roles scoring at least 0.65, plus the roles you saved or liked. It runs inside the model pass, on the same score.
|
||||
|
||||
**Decided.** Summarise is not part of the preparation or the scoring. It runs once the final scores are set, on the top of the feed by the final score, with its own size on the form (50 to start, as a slider). Roles you saved or liked are summarised too, as today.
|
||||
Per agent, per company: affinity (hidden, neutral, liked, favourite). Per company, for every agent: All roles.
|
||||
@@ -0,0 +1,113 @@
|
||||
# Plan: ranking flow
|
||||
|
||||
This plan takes the code from what it does **today** to the target in `architecture.md`. Each stage gives today's behaviour, what was **decided** on 2026-10-04 and the measurements behind it. Work packages follow once it is cut into them. When the work lands, the reasoning is folded into `decisions.md` and this file is deleted.
|
||||
|
||||
## Three scores
|
||||
|
||||
Each agent decides about a role three times: a gate on what comes in, a gate on what the models read, and an order. Everything after that is the owner's filters, saved per agent.
|
||||
|
||||
- **Fetch gate**, a yes or no: the agent's hard rules. These are the required countries (Europe), the Where lines (countries, towns, remote) and the titles to leave out. A company set to **All roles** passes everything but the required countries: its roles skip the Where lines and the titles to leave out. The gate applies at every stage: at the host when the host can filter, in the cheap pass, again after extract (now with the real location and remote area), and in the feed. A role that fails it is never read by a model and never shown.
|
||||
- **Analysis score**: decides which roles that pass the fetch gate make the **cut**, the roles that get fetch text and the model pass.
|
||||
- **Final score**: orders the feed.
|
||||
|
||||
Names: **fetch text** is the second HTTP read of a role's own page, with no model (the code calls it `enrich`). **Extract**, **judge** and **summarise** are the model calls. **Fetch terms** are words a big board must match to send a role; they narrow the read at the host and are not part of the fetch gate.
|
||||
|
||||
```
|
||||
company boards (ATS) search providers
|
||||
fetch gate at the host + fetch terms, their own saved query
|
||||
only boards ≥300 roles whose host filters
|
||||
│ │
|
||||
▼ ▼
|
||||
1 Fetch ─ list pages: title, place, teaser or text
|
||||
│
|
||||
▼
|
||||
2 Cheap pass, no tokens ─ prep, embed, fit to the prompts, closeness to the CV, fetch gate
|
||||
│
|
||||
▼ analysis score → the cut
|
||||
3 Fetch text ─ the role's own page, for cut roles without text → embed, rescore
|
||||
│
|
||||
▼
|
||||
4 Model pass (Haiku) ─ extract the cut → fetch gate and cut again → judge the cut
|
||||
│
|
||||
▼
|
||||
5 Feed ─ every role that passes the fetch gate, in two orders:
|
||||
"what I'm looking for" (final score) and "what fits me" (CV match);
|
||||
front-end filters and saved filters narrow it
|
||||
│
|
||||
▼
|
||||
6 After the ranking ─ summarise the top of the feed
|
||||
```
|
||||
|
||||
## 1 Fetch
|
||||
|
||||
**Today.** The Where lines become the reach: a country and remote filter the host applies. This only happens on boards with 300 or more roles whose host can filter by place. Smaller boards, and hosts that cannot filter, are read whole. Fetch terms only apply to companies set to All countries (Mistral AI and OpenAI today), and only on hosts that take a query (Workday, SuccessFactors, Oracle, Phenom, Eightfold, SmartRecruiters). Search providers send their own saved query and take neither filter.
|
||||
|
||||
**Decided.** The fetch gate's location part and the fetch terms become one block on the agent form and follow one rule: each applies to every board with 300 or more roles whose host can filter on it. Fetch terms no longer depend on All countries. Agent 2 has no fetch terms today, so nothing changes on the live server until some are set. The titles to leave out cannot be asked of a host, so that part of the fetch gate starts at the cheap pass.
|
||||
|
||||
**Consequence.** The pull never closes a role against a read narrowed by terms, because that read is not the whole board. With terms on every big board, roles there close only by age. Accepted, since Wolf ranks on recency, not on `closed_at`.
|
||||
|
||||
## 2 Cheap pass
|
||||
|
||||
**Today.** Every open role gets one score per agent: `(0.6 fit + 0.2 newness + 0.2 company affinity + 0.2 taste + prefer gates) / sum of the weights`. Fit is the calibrated cosine to the best of the agent's prompts. The gates (Where lines, titles to leave out) set a failing role's score to 0 with a reason. A gate rejects on evidence only, so a role with no known location still ranks until extract fills it in (323 of agent 2's 7,263 roles that pass). Closeness to the CV (`cv_fit`) is stored beside the score but is not part of it. That one score drives enrich, extract, summarise, judge and the feed order.
|
||||
|
||||
**Decided.** The one score is split into the analysis score (this section) and the final score (section 5). The analysis score uses fit to the prompts, closeness to the CV and company affinity. It leaves out newness (a pull runs every 6 hours and a role is read once), taste (votes come after the read) and prefer gates. Prefer gates leave the agent; hybrid becomes a feed filter.
|
||||
|
||||
**Decided: the cut is two lists, joined.** One list is by prompt fit. The other is by CV closeness: the roles closest to the CV that the first list leaves out. The two are not merged into one number, because they answer different questions (what I want, what I am), and a merged number would let the stronger side crowd the other out. Each list has a count and a minimum level on the form. For a broad agent the count stops the list; for a narrow agent the minimum does, so roles that do not fit are not read just to fill the count. Starting values: 500 by prompt fit and 150 by CV closeness, each at least 0.6. The minimums are levels of plain fit and plain CV closeness, not of today's blended score. Among agent 2's roles that pass the fetch gate, 2,086 reach fit 0.6, 1,580 reach CV closeness 0.6, and 2,437 reach either, so for agent 2 the counts decide.
|
||||
|
||||
**Decided: affinity is a bonus on the level, as today in spirit.** A role's level on both lists rises by the company's affinity. Today the affinity term is weighted 0.2 out of 1.25, which puts a liked company about 0.05 above a neutral one and a favourite about 0.1 above. The cut keeps those sizes. The four company settings are hidden (-1), neutral (0), liked (1) and favourite (2). A hidden company is not scored at all, so it never reaches the cut or the feed. There is no level that pushes a company down without hiding it, and none is planned. Affinity remains a nudge, not a pass: a favourite's role that matches nothing stays out of the cut. Favourite only raises the level. Today it also skips the Where lines; that moves to All roles (section 5).
|
||||
|
||||
**Decided: a role you like or save always makes the cut.** This is part of the analysis score, not a separate manual path: a like or a save passes the cut whatever the role's levels, so the role gets fetch text, extract and judge. It goes through on the next pull or agent save, not the moment you click.
|
||||
|
||||
**Decided: the cut only takes roles that pass the fetch gate, location included.** For agent 2 on 2026-10-04 (24,711 open roles):
|
||||
|
||||
| Rules applied before the cut | Roles passing | Fit ≥ 0.6 | Inside today's Where, of the top 500 by fit | Inside today's Where, of the top 150 |
|
||||
|---|---|---|---|---|
|
||||
| Today: Europe, Where lines, titles | 7,263 | 2,086 | 500 | 150 |
|
||||
| Europe and titles, no Where lines | 14,704 | 4,855 | 118 | 28 |
|
||||
| Titles only | 22,297 | 9,161 | 66 | 18 |
|
||||
|
||||
Without the Where lines, about four in five model reads go to roles outside DK, SE, the Skåne towns and remote, and keeping today's coverage would take a budget about four times larger.
|
||||
|
||||
## 3 Fetch text
|
||||
|
||||
**Today.** The `enrich` stage reads the role's own page for open roles without text, on hosts that list without it. It uses its own bar from the config (`enrich.top` 500, `enrich.min_score` 0.5, at most 200 per board and 1,000 per run). Embed and score run again for the roles it filled.
|
||||
|
||||
**Decided.** Fetch text reads the whole analysis cut, so every role the model will read has its text first. The stage is renamed from `enrich` to fetch text so it is not mistaken for a model call.
|
||||
|
||||
## 4 Model pass
|
||||
|
||||
**Today.** Extract and judge run on Haiku (summarise is in section 6). Each has a count and a minimum score on the blended score; for agent 2 the count decides every stage.
|
||||
|
||||
- **Extract** reads at most 500 roles scoring at least 0.55. It fills location, remote area, seniority, languages and deadline. A rescore follows so the gates see these columns.
|
||||
- **Judge** reads at most 150 roles scoring at least 0.55, plus the 50 closest to the CV that those leave out. It scores skills, experience and career 0 to 100, plus a verdict on each must-have. These are weighted 30/25/30 into `cv_score`.
|
||||
|
||||
**Decided.** One depth: the cut is the only selection, and both scoring model stages read all of it. A second score inside the cut would defeat its purpose. The order is:
|
||||
|
||||
1. **Extract** reads the whole cut. It is the small, fast call (about 1.5 s a role on the live backend).
|
||||
2. The fetch gate and the cut are applied again with what extract filled, now knowing which roles are really remote and where the rest are. Some roles drop out; some enter, such as roles that turn out to be remote. A role that enters is extracted on the next pull.
|
||||
3. **Judge** reads the cut as recomputed (about 6 s a role).
|
||||
|
||||
**Decided: extract and judge stay two calls.** Extract needs no CV and its location and remote answers feed the fetch gate before judge reads anything. Judge works per agent and role, with the CV in the system prompt.
|
||||
|
||||
**Cost.** Every model read happens once per role (judge once per role and CV), so a larger cut costs mostly a one-off catch-up. With a cut of about 650 roles, that catch-up is about 16 minutes of extract and about an hour of judge on the live backend (`claude_code`, the subscription, so no per-token bill). After it, each pull reads only the roles new to the cut. The recurring cost is a re-judge: changing the CV, a prompt, or the like or dislike text changes every judgement's input, so the whole cut is judged again, about an hour for 650 roles. A changed posting text re-judges that role only. Accepted: the re-judge takes a while but is correct, since the old judgements were made against the old text.
|
||||
|
||||
## 5 Feed
|
||||
|
||||
**Today.** There are two orders. **Score** uses the same score as section 2. **CV match** shows the judged roles first by `cv_score`, then the unjudged ones by CV closeness. Roles that fail the gates are hidden unless Show gated is ticked, so the front-end place filter can only narrow inside the Where lines. A favourite company (affinity 2) skips the Where lines but also gains in the score; that is why OpenAI's London roles rank. All countries and All roles are separate company flags that only change what is fetched.
|
||||
|
||||
**Decided.**
|
||||
|
||||
- The feed shows every role that passes the fetch gate, loaded as you scroll, not only the cut. Newest first stays inside the fetch gate as well, so no order shows roles outside the agent's places.
|
||||
- There are two orders: "what I'm looking for" (final score) and "what fits me" (CV match). The final score includes newness and likes. It is not one blended number.
|
||||
- Front-end filters only narrow further. The Roles page says that the feed is already filtered by the agent's fetch gate, location included.
|
||||
- **All roles**, one company switch in place of today's All countries and All roles. It is for small companies worth a speculative approach ("have you thought about hiring in Denmark?"). The company is fetched from every country inside the required countries (Europe) and without fetch terms, and its roles pass the fetch gate whatever the Where lines and the titles to leave out say. It changes nothing in any score: its roles enter the cut only by their levels, and favourite is what pushes them up. It applies to every agent, as the two switches do today.
|
||||
- The company view says plainly what is filtered: for an All roles company, "every role in Europe, not filtered by country or title"; for any other company, that it shows the roles the agent's fetch gate passes. Looking up a company must not silently hide roles in other countries.
|
||||
- **Saved filters**, per agent. The current filter settings can be saved under a name, loaded with one click and deleted. There is no editing: to change one, save a new one and delete the old.
|
||||
|
||||
**Decided: the final score** is today's formula without the prefer gates: 0.6 fit to the prompts, 0.2 newness, 0.2 company affinity, 0.2 roles you liked, over the sum of the weights. Everything else, such as seniority, location and pay, is a filter, not a score term, so a role is never judged twice by the score and by a filter.
|
||||
|
||||
## 6 After the ranking
|
||||
|
||||
**Today.** Summarise reads at most 30 roles scoring at least 0.65, plus the roles you saved or liked. It runs inside the model pass, on the same score.
|
||||
|
||||
**Decided.** Summarise is not part of the preparation or the scoring. It runs once the final scores are set, on the top of the feed by the final score, with its own size on the form (50 to start, as a slider). Roles you saved or liked are summarised too, as today.
|
||||
Reference in new issue
Block a user