I am not following, can you give a concrete example of your workflow?

In my agent file I explain that I have a static analyzer which generates a callgraph. On starting the agent runs ~/.agent/tools/__callgraph__/generate_callgraph.py

It then gets to see callgraph.current.md and upon subsequent sessions callgraph.diff.md.

Here is an example of some output that I currently have in callgraph.current.md

  ## src/components/Header.tsx

  - **export Header({ ... }: Props)** (start 9, end 54) → `useAuth`

  ## src/components/HelpTooltip.tsx

  - **export HelpTooltip({ ... }: Props)** (start 15, end 42) → (none)

  ## src/components/ResultsTable.tsx

  - **getHeaderLabel(col: { id: string; columnDef: { header?: unknown } }): string** (start 45, end 51) → (none)
  - **getCellValue(colId: string, original: KeywordResult): string** (start 53, end 74) → (none)
  - **export ResultsTable({ ... }: Props)** (start 76, end 406) → `getCellValue`

  ## src/components/SettingsDrawer.tsx

  - **export SettingsDrawer({ ... }: Props)** (start 158, end 336) → (none)

For example:

ResultsTable calls getCellValue.

In these cases it's just one function but you also have stuff like

  **export Dashboard()** (start 36, end 635) → `getTopKeywords`, `normalizeText`, `searchKeywords`, `searchKeywordsMulti`, `searchSemantic`, `searchSemanticMulti`

For the Python version it also gives the parameters and types along with it. I think the next thing I'd need to do is give self-defined type definitions. Doing things this way allows an LLM to not read all that much but to be able to reason relatively well over what the code does. The caveat is that you abstracted your code well. If you didn't, the LLM doesn't know your implementation.

I probably should also add return types.

Can you share details about this? Do you have a repo?

How do you find jobs to post? Mostly from the same sources or from everywhere? How long until you got 100 visits per day? How many jobs do you add per day? Why not build more in adjacent industries?

The jobs come about 70% from the feeds with the paying parters. I pull about 20k jobs their feed, then run my script to select about 100 relevant jobs. The other 30% I get them manually from Linkedin, Indeed, etc. I have alerts on all big sites with some deep filtering.

It took about 2 months to get a constant 100/day average visits, but I had ~5000 connections on Linkedin in the HR space (I work in HR Tech). I also got to 2000 newsletter subs in about 2 months.

My advantage was that I was already active in the HR community, I would need another “me” to build in more industries.

AI?

Yes

Give it for free to the 10 first people to show up.

Can you share more regarding the first point?

What are the features? What do you like about it?

This is the reason I have not gone the jj way.

Can you elaborate?

Are you switching?

This is not a bad idea but the payment was done through Revolut.

I tried, we'll see what happens.