Choose what to get done
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.
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.
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.
OpenAPI endpoint reference
A complete, well-formed reference for one endpoint: method, path, parameters (with every path placeholder covered), the required status codes, and a consistent request body.
Pre/Post-Money Cap Table With Option Pool
The founder has a fully-reconciled pre- and post-money cap table, with the option pool shuffle baked in, ready to attach to a term sheet.
Press list of reporters to pitch
A deduplicated press contact list built to your brief: every row carries a reporter name, a publication, a valid-format email address, and a sample-article link, with duplicate emails and single-source padding screened out.
Project a Weekly Growth-Target Schedule
A pure function that, given a starting metric value, a weekly growth rate, and a number of weeks, returns the compounded target for each week and the final value, mirroring the YC forward-looking growth graph practice.
Rank product features with a collaborative weighted scorecard
A product team prioritizing a roadmap gets each feature's weighted value, cost normalized to the most expensive feature, absolute value, and a deterministic rank, computed exactly per the CWS formula.
Release readiness gate checklist
Categorized, criterion-bearing release gates with a consistent blocking verdict, marrying governance with automation instead of a change-board bottleneck.
Requirements traceability matrix
A matrix linking every requirement to its tests (and back), with computed orphans and a coverage percentage that clears your bar.
Score AI model process and tool maturity into bands
A team assessing whether an AI model is mature enough to sell as a service gets a process-maturity band and a tool/system-maturity band computed directly from per-phase level scores, ready to feed the AIaaS feasibility decision.