# Work a problem through a named framework

> Work a problem through a named framework: 0 companies fully do it, 1 with a limit, 2 carry the tag. Every listing in Reasoning scaffolds with the reason and a source.

- Canonical: https://www.anchorterminal.com/niches/reasoning.apply-named-framework/
- Markdown: https://www.anchorterminal.com/niches/reasoning.apply-named-framework/index.md (~650 tokens)
- Slim: https://www.anchorterminal.com/niches/reasoning.apply-named-framework/index.min.md (~230 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/niches/reasoning.apply-named-framework/index.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-15

No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.

| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |
| --- | --- | --- | --- | --- |
| 0 | 1 | 2 | 10 | 1 |

## What counts as done

The scaffold accepts the named operation as documented, returns the framework's structure filled from the prompt, and rejects an unsupported operation with an error that names the valid ones.

How agents ask for it: do a pre-mortem; use first principles; run a decision matrix on these options; apply ReAct

## Does the job, with a limit

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

- **Clear Thought 1.5 (Waldzell AI)**: 37 operations in a zod enum, so an unknown one fails with InvalidParams listing valid values. But the README shows mdp_planning and decision_networks, which the enum rejects, field names are undocumented in the schema, and no ReAct mode exists (acc-26).

- not this job: Sequential Thinking (MCP reference server) (Model Context Protocol, a Series of LF Projects, LLC): One tool with one numbered-chain format; no operation parameter or named frameworks.

## What stops agents finishing

- README shows operations the schema rejects
- free-form parameters object with undocumented field names

## Around it

After: docs.write-report.

## Where this comes from

Weight 10 of 100 in Reasoning scaffolds: 1 of 28 accounts (a ReAct request); the rest rests on the Clear Thought README

As data: https://www.anchorterminal.com/api/v1/use-cases/reasoning.apply-named-framework.json, or the MCP tool get_use_case with id reasoning.apply-named-framework. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
