Choose what to get done
Influencer pay ceiling
A value-based pay ceiling per influencer (from order value, margin, and conversion rate), with a within-budget verdict.
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.
Integration adoption rate with a build-next ranking
Per-integration adoption rate over the overlapping base it can actually serve, health-flagged, plus a build-next ranking by addressable market.
Interview panel coverage plan
A structured interview-loop plan mapping interviewers to competencies, sized per the research, with a dissenter assigned.
Job requisition spec
A complete requisition: responsibilities with success metrics, a must-have skills list capped to avoid the unicorn trap, a valid comp range, and a clean biased-language screen.
Liquidation Preference vs Convert Election Calculator
The founder can predict, deterministically, what each preferred holder will choose at any exit value and the resulting proceeds split.
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.
Love-vs-like product diagnostic instrument
A measurement instrument that tells love from like across five signals (repeat use, fanatical users, the would-miss test, organic referral, willingness to pay), each with a metric, a numeric threshold, and a data source.
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.
Map a price waterfall from list to pocket price and flag leakage
I get a price waterfall that ties my pocket price back to my list price through named, quantified leaks, so I can see exactly where realized revenue is lost.
Market sizing (TAM / SAM / SOM) with the adequacy check
TAM grossed up from a partial-coverage database count, SAM and SOM by your fractions, and a check that SOM clears 2x your revenue objective.
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.