Choose what to get done
In-house build-vs-buy tendency scorer
A founder weighing whether to sell an AI capability as a service gets a 0-6 in-house-tendency score and a build/buy verdict per the book's exact criteria, flagging capabilities customers will just build themselves.
Incident response runbook
A severity-tiered response playbook (roles, response targets, escalation, comms) so responders follow a plan instead of debating process mid-outage.
Input guard against prompt injection
A reusable guard that enforces type, length, and charset per field and rejects inputs smuggling section-break delimiters or fake instruction/role markers, before the LLM sees them.
Internally-consistent term sheet economics block
A structured JSON term sheet covering all required economic sections, with the valuation, price-per-share, and ownership figures internally consistent.
Investor due-diligence answer register
A category-balanced register of answers to standard investor due-diligence questions, structured as data-room-ready JSON, with category coverage, answered-count consistency, and per-answer length floors machine-checked.
Liquidation preference structure spec
The founder (or counsel) has a complete, parameterized specification of the liquidation-preference stack ready to drop into a term sheet or shareholders' agreement.
Logs, metrics, and traces instrumentation plan
A concrete plan covering all three observability pillars per service, plus an SLI for every golden signal, so you can actually see what your app is doing.
Maintainability index per module
The Maintainability Index (raw and 0-100 normalized) per module from Halstead volume, cyclomatic complexity, and lines of code, with a maintainability band.
Man-in-the-jungle intrigue narrative arc
Your backstory shaped into a four-beat intrigue arc (jungle, beasts, will he escape, held at the edge) that names your protagonist in the opening beat, puts your concrete stake in the beasts beat, poses a literal open question in the escape beat, and flags the final beat unresolved, ready to drop into a pitch.
MECE use-case modules with per-segment value
I get a modular packaging map where features are partitioned into non-overlapping use-case modules, no feature is left unassigned, and each module carries a t-shirt value per segment plus a base/add-on flag.
Milestone-gated grant tranche disbursement schedule
A milestone-gated disbursement schedule as structured JSON: total award, ordered tranches each with an amount, a gating performance milestone, a measurable success metric, and a target date, with tranche amounts summing to the total and dates strictly increasing.
Model router that sends each query to the right LLM
A routing function that dispatches each query to the right model by its type, normalizing case and falling back to a default for any unlisted type.