Directory / Scanning & screening
Scanning & screeningAdvanced#watchlist#weekly-review#python#hallucination-guard#data-quality

Review recent IPOs against your written base criteria for research notes

An agent checks companies that listed in the last one to three years against your liquidity filter and your written definition of a base, then returns a private weekly list of current matches with the measurements.

How it works

  1. Write {{base_rules_file}} with your liquidity minimum, minimum weeks since listing, and your own range, duration and volume rules.
  2. Build {{ipo_list_csv}} of listings from the last 1-3 years from a public IPO calendar plus price and volume data you already use.
  3. A Python script computes average traded value, weeks since listing, range, duration and volume pattern and writes those columns into the CSV.
  4. Weekly, the agent compares those columns to the rules file, applies the liquidity filter first and reports how many names it removed, then lists matches with measurements only.
  5. The agent shows a dry-run diff of the entry; you confirm before anything is written, then surviving names are appended to your private watchlist. The list stays private.

Copy-paste prompt

Check recent listings in {{ipo_list_csv}} against my base definition in {{base_rules_file}}. The CSV already includes script-computed columns: avg_dollar_volume, weeks_since_listing, range_pct, duration_weeks and volume_pattern.
1. Read only those existing columns. Do not calculate or invent price, volume or average traded value.
2. Drop names under the minimum weeks in the rules file before matching, then apply the liquidity rule first and report how many names it removed.
3. List only matches plus those measurements. No comments about future price, trading action or opportunity.

Guardrails

  • Liquidity filter first.
  • Your own written base definition.
  • No names published; private list only.
  • Dry-run diff shown and confirmed by you before writing to your journal.
  • List is for private research notes and journal only; you perform independent chart review before any discretionary decision.
  • Re-run the Python metric script if any data looks stale.

What can go wrong

Very new listings have too little history for any base definition to mean much (set a minimum number of weeks since listing). The LLM can still mis-apply ambiguous rules or overlook nuances in the written base definition even when told to use only script metrics; data in public IPO calendars can be incomplete or delayed.

Why it helps

Recent listings are easy to forget once the headlines fade. A weekly private review of measurements against your own written criteria supports research hygiene and keeps your journal up to date without any external signals or recommendations. The script output covers average traded value, weeks since listing, range, duration and volume pattern. The base definition is yours (minimum weeks, maximum depth, minimum duration, volume contraction) and is not an instruction to act.

Source and references

Original write-up by Agents for Traders. Background reading is linked below.

Spotted an error, or want your post removed? Email hello@agentsfortraders.com.

Educational content only. Not investment advice or a personal recommendation. No tickers, signals or trade alerts. Trading involves risk of loss.

Conteúdo exclusivamente educativo. Não constitui aconselhamento nem recomendação de investimento. Sem tickers, sinais ou alertas de negociação. Negociar envolve risco de perda.

Related use cases

Scanning & screening

Build a private pre-market scan digest from your own written rules

A script applies the screening rules you wrote down to your own universe and computes every number. An agent groups the results and sends you a private list with chart links to review before the open.

Advanced#pre-market#watchlist#python
Watchlists & alert hygiene

Classify your watchlist by trend stage every night

Each evening an agent applies your own numeric rules to label watchlist names by Weinstein stage (1-4) and logs only label changes that persist for your chosen minimum weeks; output goes to your journal after you review a diff.

Intermediate#end-of-day#journaling#python