docs: add first cept consultation example#1
Merged
Conversation
…ipped Real consultation, lightly trimmed. Shows what cept is for: outside-in steering when an agent is about to commit to a reasonable-sounding-but- wrong move. The agent had read the project's guardrails and was still about to violate them; cept's output wasn't new facts, just a second pair of eyes without the agent's momentum. Linked from the README under a new Examples section. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
examples/01-slack-eidos-personality.md— a real cept consultation, lightly trimmed, showing what cept is for: outside-in steering when an agent is about to commit to a reasonable-sounding-but-wrong move.Why
The agent had read the project's vision, guardrails, and tasks — and was still about to violate them by writing a persona before deploying the bot. Cept's output didn't contain new facts. It just held up a mirror.
That's the use case worth documenting. The blind-spot section was the bonus (two real technical risks the agent had missed because it was busy planning the persona).
Test plan
🤖 Generated with Claude Code