Skip to main content
A Noonum thematic strategy is a thematic investment definition: a basket of ranked companies assembled around an objective, with evidence-backed metadata for every holding. Each company’s inclusion is grounded in textual evidence, so you can analyze and report on a strategy from the evidence rather than by guessing. The workflows below run against existing strategies through the REST API or the MCP server: viewing holdings, finding outliers, analyzing composition, comparing two strategies, exporting CSV, pulling a factsheet, and archiving.
To create or submit a strategy, see Build a strategy. To run the full refinement loop, see Iterate on a strategy.
Every request needs an Authorization: Bearer <token> header. See Authentication for tokens and API keys.

​
The three signals

Each holding carries three scores: conviction, linguistic beta, and market buzz. Signals and scores defines each one, its range, and how to read it. This guide assumes that and focuses on which one to lead with for a given question:
  • Conviction for ranking holdings, summarizing a company, or comparing strategies. It is the default ranking metric and headline number.
  • Linguistic beta when you need to defend why a company belongs in the theme, judge how tightly a cluster ties to the thesis, or flag outliers.
  • Market buzz to see which holdings are currently active in the theme versus historically connected but quiet.
Holdings tables include both conviction and linguistic beta as columns, sorted by conviction by default.

​
Resolve a strategy

Most operations take a strategy ID. To find one:
  • List your strategies with GET /strategies (MCP: list_strategies).
  • Fetch a specific strategy with GET /strategies/{strategyId} (MCP: get_strategy).
To browse the public catalog of completed, non-archived strategies, pass scope=public to GET /strategies. Use scope=all to return your own strategies plus the catalog, deduplicated.

​
Endpoint quick reference

All REST paths are relative to https://api.noonum.ai/v2. The MCP server exposes the same endpoints as named tools.

​
View holdings

Fetch a strategy’s companies with GET /strategies/{strategyId}/companies. The endpoint reads the active version’s latest completed run by default; pass asOfDate and/or versionId to select a different run. Set includeReasoning=true to add a per-company justification column. Use scoringMinMarketCap to set the minimum market cap (USD) for conviction scoring; companies below the threshold receive a convictionScore of 0.

​
Table columns

The companies endpoint returns these columns: With includeReasoning=true, a Reasoning column is appended. An internal ID column is used for per-company queries such as GET /strategies/{strategyId}/companies/{companyId}. You typically won’t surface that ID to end users.

​
Sparse data

Some companies have incomplete metadata. When a field is missing:
  • Show an em dash (—) in the cell rather than leaving it blank.
  • Keep the company in the table; don’t drop it.
  • Note the count at the bottom (e.g. “N companies with incomplete data”).

​
Understand why a company is included

Use GET /strategies/{strategyId}/companies/{companyId} for a single company’s scores, and GET /strategies/{strategyId}/evidences for the underlying evidence. Lead with the linguistic beta score, then read the evidence the API returns. If you only have a name, resolve the company first with POST /helper/companies/search.

​
Find outliers

Fetch holdings with includeReasoning=true and flag companies that show:
  • Low conviction or low linguistic beta, signaling a tangential connection to the theme.
  • A sector that’s unexpected relative to the thesis.
  • Thin or indirect reasoning.
These are candidates for exclusion. See Iterate on a strategy for how to act on them.

​
Analyze composition

Profile a strategy from its holdings data:
  • Sector / industry breakdown: a frequency table with average linguistic beta per sector shows which sectors are core to the theme versus peripheral. Watch for any single sector dominating the basket, which can mean the strategy is really a sector bet, and for notable absences.
  • Market-cap distribution: the large-cap, mid-cap, and small-cap mix.
  • Geographic exposure: country distribution.
  • Thematic coherence: the spread of linguistic beta scores tells you whether the strategy is tightly focused or broad.
Signals and scores explains how to interpret each value.

​
Compare two strategies

Fetch holdings for both strategies, then compute the overlap and differences. A clear layout:

​
Overlap (N companies, X%)

​
Unique to Strategy A (N companies)

​
Unique to Strategy B (N companies)

​
Summary

  • Overlap: N companies (X% of A, Y% of B).
  • Sector distribution comparison: call out the largest differences.
  • Average conviction comparison. Also note any linguistic beta divergence when thematic coherence is in question.

​
Export holdings

Request the companies endpoint in CSV form (MCP: download_strategy_companies) to get all holdings as a CSV string you can save to disk or load into a spreadsheet.

​
Get a factsheet

The factsheet is generated on demand. Request (re)generation with POST /strategies/{strategyId}/factsheet, then read it with GET /strategies/{strategyId}/factsheet:
  • When the PDF is ready, the GET returns 302 Found with a short-lived presigned URL in the Location header.
  • While generation is in flight or none has been requested, the GET returns 200 OK with a FactsheetStatus body whose status is generating or not_requested.
Both endpoints accept asOfDate and versionId to target a specific run. Default to the active version’s latest completed run. Request a factsheet after refinement to capture the updated state.
When polling, disable redirect following so you can tell a 302 (ready) from a 200 (still generating).

​
Archive a strategy

DELETE /strategies/{strategyId} archives the strategy rather than destroying it: it returns 204, is hidden from reads, and is scheduled for permanent deletion after a 30-day grace window.
  • List archived strategies still inside the window with GET /strategies/archived. Each carries archived_at and permanent_delete_at.
  • Restore one with POST /strategies/{strategyId}/revive. This returns the revived strategy with archived_at and permanent_delete_at reset to null.
Once the grace window has elapsed, a background job permanently purges the strategy and POST /strategies/{strategyId}/revive returns 410 Gone. Revive before then if you need it back.

​
Status codes

The strategy’s top-level status is a discrete code for the active version’s latest live run, not a raw percentage: status is run-scoped: by default it reflects the active version’s latest live run. For per-version or per-date detail, read GET /strategies/{strategyId}/versions/{versionId}.

​
Error handling

  • Strategy not found: list your strategies to confirm the ID. An archived strategy is reachable only via GET /strategies/archived and POST /strategies/{strategyId}/revive.
  • Empty holdings: the strategy may still be processing. Check GET /strategies/{strategyId}; if its status is not 100, wait for the run to finish.
  • Update / submit fails: the error message usually means the exclusions need adjustment. Revise and resubmit.