---
id: "concept-outcome-driven-prompting"
type: "concept"
source_timestamps: ["00:07:15", "00:07:40"]
tags: ["prompt-engineering", "best-practices", "model-interaction"]
related: ["concept-bitter-lesson-llms", "claim-procedural-prompting-degrades", "action-delete-procedural-prompts"]
definition: "A prompting paradigm that specifies only the desired end state and constraints, omitting all procedural steps to allow the model to determine the optimal execution path."
sources: ["s44-claude-mythos"]
sourceVaultSlug: "s44-claude-mythos"
originDay: 44
---
# Outcome-Driven Prompting

## Definition

A prompting paradigm that specifies **only the desired end state and constraints**, omitting all procedural steps so the model determines the optimal execution path itself.

## The shift

Prior generations required step-by-step instructions:

> *"First, read the document. Second, extract the key points. Third, format them into a list."*

At the capability level posited for [[concept-claude-mythos|Claude Mythos]], this procedural prompting becomes an anti-pattern. See [[contrarian-complex-prompting-antipattern]] and [[claim-procedural-prompting-degrades]].

## What outcome-driven prompts contain

1. **The 'what'** — a precise definition of success
2. **Constraints** — policies, formats, edge cases that must be respected
3. **Tools / resources** — what the model has access to
4. *(Omitted)* The 'how' — never specified

## Worked example

Instead of a 3,000-token prompt detailing how to handle a customer service ticket:

> *"Resolve this customer's issue using our policy database; the customer must leave satisfied, and the resolution must comply with our return policy."*

## Benefits asserted in the source

- Lower token consumption
- Lower inference cost
- Removes human-engineered logic as a bottleneck
- Lets the model exercise its full reasoning capability

## Speaker's directive

[[quote-let-go|"You got to let go of the process with these models."]] — see [[entity-nate-b-jones|Nate B. Jones]].

## Operational tie-ins

Outcome-driven prompting pairs with [[concept-single-eval-gate]] (one rigorous final check) and [[concept-model-driven-retrieval]] (let the model find its own context). All three are pillars of the [[framework-mythos-readiness]].


## Related across days
- [[concept-spec-driven-development]]
- [[concept-bitter-lesson-llms]]
- [[concept-specification-precision]]