Ingest: four steps from chatting to hands-off AI (guide No. 44) - #243
Merged
Conversation
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Co-Authored-By: Claude Fable 5 <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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Source
Austin Marchese · Boris Cherny's 4 Step Playbook to 10x Your AI Productivity (published today, auto-generated captions). The video is Marchese's non-engineer translation of Boris Cherny's "Steps of AI Adoption" (Anthropic, July 2026, published as a Claude artifact page and announced on his X). Cherny's quoted lines were verified against secondary write-ups of the post, since the artifact page itself could not be fetched.
Placement
New guide, No. 44: "Four steps from chatting to hands-off AI" · agents · broad · draft.
Most of the video's individual tactics already have guides, so they were cross-linked rather than re-taught: verification loops (Loop the agent until the work passes), taste standards (Why AI makes slop), permissions (Assume your agent uses every tool it has), skills from finished work (Capture the model's discipline), schedules (Automate a workflow as a Claude routine), report channels (Buzz), proactive agents (Make your agents proactive), model pinning (Stop hitting your token limit), iteration caps (Guardrails for hours-long agent runs), deciding what stays human (What still pays when AI does the work).
What no existing guide covered is the map itself: four steps, each defined by who watches what, each with a named bottleneck, where the bottleneck you feel is the diagnosis of which step you are on. That framework, the two-question copy-paste test, the contractor story against "faster if I do it myself", and the 80 percent rule for automation candidates are the guide's own material. The guide becomes a natural entry point that places a dozen catalogue guides on one progression.
Registry row added to
content/sources.md. Sponsor segment (Ask Your Work), giveaway, and buildpartner.ai plugin promos were not ingested.README plate unchanged: the plate counts published guides, and this one lands as a draft.
Checks
npm run buildpasses (em-dash gate, heading length, schema).Awaits editorial review. Merging is publishing.
🤖 Generated with Claude Code