Notebook session ended
This session ended after eight hours.
Sign in again to continue from where you left off.
Notebook gate offline
The sign-in service is not responding right now.
Wait a minute and try again, or read what is already public from the hub.
Foundational walk through the playbook project. Read top to bottom if you're new; no prior context assumed.
More about this project on the Playbook hub.
Use when: you are new to the playbook and need the whole shape before any detail; an agent session is about to take on recurring work and must decide whether a play covers it; explaining to someone why agents in this estate do not simply act on instructions
Use when: you are about to write a fact about a deck, decision or app into a play, card or prompt; two documents disagree and you need to know which one wins; deciding where a new piece of procedure or a new fact should live
Use when: drafting a new play or a new version of one; validate_plays.py failed and you need to know which rule and why; reviewing a play PR and deciding whether a PASS means what it seems to
Use when: a session is handed a job and must decide which play owns it; reading the router and unsure which version's row is in force; the same unplayed job has turned up for the second time
Use when: deciding whether an agent may finish a step alone; a step mixes reversible prep with an outward-facing act; an agent is blocked waiting for a signature
Use when: about to say a play run, task or fix is done; deciding whether a human signature is needed to close a run; reviewing someone else's run and deciding what to check
Use when: writing the false_pass column of an exit-criteria table; a check has been green for a long time and you are not sure it can go red; reviewing a run and deciding what to look at beyond the PASS
Use when: a play needs to change after it has merged; reading a play and unsure which of its versions' statements are in force; deciding whether a correction is worth a new version, given the ladder reset
Use when: a play, decision or spec awaits the operator's sign-off; you have been told to merge something that carries a sign-off line; checking whether a record was really signed by a human
Use when: the operator corrected you mid-session; a run needed a fix the play did not describe; deciding between amending a play and declining to
Use when: you need to know what phase the delegation programme is in and what closes it; deciding which requirement a piece of loop work serves; someone claims a play is trusted and you want the yardstick
Use when: writing, reading or validating a run record; a run failed or errored and you are tempted not to record it; computing anything about a play's history
Use when: turning a play's exit criteria into code; a reviewer is about to judge a run by reading prose; debugging why the loop's review check went red on a commit
Use when: a check has only ever been green; a play is one 'planted fault caught' short of the next ladder level; adding a new check and deciding how to prove it is not vacuous
Use when: someone asks how trusted a play is; planning what a play needs next to climb; an escape happened and you need to know what it costs
Use when: someone proposes letting an agent publish, deploy, change DNS, rotate credentials or move money unattended; a play's tier field is being edited; explaining why a highly reliable play still needs a human click
Use when: someone wants to show how trusted the delegation loop is; state.json or the devarno.si page disagrees with the ledger; deciding what may be published about the loop
Use when: you need to know exactly what the scheduled loop does between 06:17 and 18:17 UTC; debugging a tick that committed nothing, opened an unexpected issue or skipped a play; adding a new scheduled play and deciding where it plugs into the tick
Use when: deciding which identity may write, review, ratify or merge in the loop; a review check run is red, neutral or missing on a loop commit and you need to know why; designing a new agent write path and checking it does not reuse the doer's principal
Use when: a loop-exception issue opened and you need to know what condition raised it and what will close it; an exception issue has stayed open and you suspect it should have resolved; adding a new exception kind and deciding how it recovers
Use when: the loop may have stopped and you need to know which alarm should have fired; designing a watcher for any scheduled job and deciding what it may share with the job it watches; a kind:heartbeat-stale issue opened or PlaysLoopStale fired
Use when: onboarding a new org, DNS subject or IRINA target into the scheduled loop; a run refused with 'no card' and you need to know what a card must hold; checking whether a card is copying facts that belong in their own ledger
Use when: you need to find which play owns a job before doing any recurring work; getting a one-screen view of which plays are ratified, scheduled, or still stubs; explaining the shape of the catalogue: what is automated, what is human, what is capped
Use when: you want to see one play end to end, from card to score to exception, with every check explained; an org's health score moved and you need to know which inputs moved it; writing a new read-only sweep play and copying the pattern that already earned L3
Use when: an IRINA drain-time reading looks wrong and you need to know whether to believe it; an irina-reading exception opened and you must decide what, if anything, to do; building any play that checks a measuring tool rather than doing work
Use when: any write to a VPS deck (SPUTNIK, APOLLO, ODIN) or DNS that points at one is being planned; a domain, app, service or deck is leaving service, being renamed or folded into another; you need the shape of a GO document and what makes it spendable
Use when: work is blocked on a decision, phase close or play ratification that needs FLIGHT's signature; preparing the packet for the daily signing window; deciding the merge order of several sign-off-bearing PRs
Use when: a launch-to-revenue gate needs proof that real people want the product before money is switched on; a runbook is still marked DRAFT and a gate needs it walked; deciding what an agent may and may not do in work where the human is the instrument
Use when: you need the plan for taking the loop from 'runs' to 'independently proven', phase by phase; working on IRINA, the canary e2e, delegation contracts, Mac-lab journeys or the TOLL path proof; checking which RS-DL-003 phase a piece of work belongs to and what closes it
Use when: deciding how an app should take money, and in what order relative to other apps; working on TOLL P3, the estate gate graph, the demand gate, revenue integrity or per-app economics; explaining which money acts an agent may measure and propose, and which stay human for ever
Use when: bringing a new project, org or recurring job under the delegation loop; turning a job you keep doing by hand into a play that can earn autonomy; explaining to a collaborator, human or agent, how to start using the playbook on their own work
Use when: an agent session is starting work that might be covered by a play; you need the hard refusals in one place before acting; checking whether what you are about to call evidence would pass review