Current synthesis from the research packet. Exact records and complete source artifacts remain visible below.
Design the canonical outcome/product schema and prove it against five target workflows.
research/actionmodel-builder-research-2026-08-26/outputs/first-principles-framework.mdresearch/actionmodel-builder-research-2026-08-26/phase-3/outputs/synthetic-pilot-specification.md[private local source withheld]A prompt is not a specification, so there is nothing to test the generated app against and nothing to say when it is done. A testable ProductSpec with acceptance fixtures turns "does this look right" into a check a machine can fail.
51 mined records. Search and inspect the full agent output; nothing is collapsed into a top-ten headline.
| Rank | Identity | What the agent found | Evidence | Source |
|---|---|---|---|---|
| — | ChatPRDai-prd | AI product-management platform that drafts and improves PRDs, one-pagers, user stories and tech specs from natural-language prompts. | Drelevant | Source ↗ |
| — | ChatPRD MCP Serverai-prd | Authenticated MCP endpoint exposing product documents to AI coding tools as live context. | Drelevant | Source ↗ |
| — | BuildBetterai-prd | Customer-intelligence platform that generates PRDs and scoping docs grounded in captured customer calls, tickets and Slack threads with citations. | Drelevant | Source ↗ |
| — | Figrai-prd | PRD generator that refuses the blank prompt: ingests existing product context first, then structures a PRD grounded in what the product actually does. | Drelevant | Source ↗ |
| — | Keeborgai-prd | Spec generator producing a multi-document stack formatted for AI-agent consumption with cross-document consistency checking. | Dadjacent | Source ↗ |
| — | ContextArkai-prd | Spec tool built for AI coding agents that emphasises non-goals and acceptance criteria to prevent scope creep in Cursor/Claude Code. | Drelevant | Source ↗ |
| — | IdeaPlan Forgeai-prd | AI document generation embedded in a broader PM operating system (feedback, roadmap, releases). | Dweak | Source ↗ |
| — | FreePRD.aiai-prd | Free unlimited PRD generation with no signup, positioned explicitly as a ChatPRD alternative. | Dweak | Source ↗ |
| — | FifthDraftai-prd | Free unlimited PRD generator requiring no account; pick product type, describe feature, receive structured output. | Dweak | Source ↗ |
| — | Taskade AI Software Development Proposal Generatorscoping | Template-driven AI generator producing software development proposals inside a general workspace tool. | Dweak | Source ↗ |
| — | Jama Connectreq-mgmt | Requirements/engineering management platform now repositioned as an 'Intelligent Engineering Management Platform' with spec-driven development for AI agents. | Drelevant | Source ↗ |
| — | Jama Connect Advisorreq-mgmt | NLP requirements-authoring assistant that checks the quality of individual requirement statements against INCOSE best practice and EARS syntax. | Drelevant | Source ↗ |
| — | EARS notation (Easy Approach to Requirements Syntax)req-mgmt | A constrained-natural-language grammar for requirements; not a product but the mechanism several commercial tools implement. | Drelevant | Source ↗ |
| — | IBM Engineering Requirements Management DOORS Nextreq-mgmt | Enterprise requirements management for regulated, long-lifecycle engineering with formal baselines and multi-level traceability. | Drelevant | Source ↗ |
| — | DOORS Next suspect-link change propagationreq-mgmt | Change-impact mechanism: editing a requirement automatically marks associated links as suspect. | Drelevant | Source ↗ |
| — | IBM Engineering Requirements Management DOORS (Classic)req-mgmt | The long-lived predecessor RM tool, still entrenched where organisations have long product lifecycles and historical investment. | Dadjacent | Source ↗ |
| — | Siemens Polarion ALMreq-mgmt | Full integration of requirements, change and test management in one ALM platform. | Dadjacent | Source ↗ |
| — | PTC Codebeamerreq-mgmt | Highly configurable ALM for complex regulated product organisations covering requirements, risks and verification. | Dadjacent | Source ↗ |
| — | Visure Requirements ALMreq-mgmt | Requirements ALM for safety-critical and highly regulated industries with bidirectional traceability across thousands of interconnected items. | Dadjacent | Source ↗ |
| — | Modern Requirements4DevOpsreq-mgmt | Requirements and traceability layer built directly inside Microsoft Azure DevOps rather than as a separate platform. | Dadjacent | Source ↗ |
| — | ReqSuite RMreq-mgmt | Requirements management aimed at medium-sized product developers, positioned as lighter-weight than DOORS/Polarion class tools. | Dadjacent | Source ↗ |
| — | Lovablebuilder-intake | Prompt-to-app builder generating frontend, backend, database, auth and integrations from natural-language description in a per-project chat. | Drelevant | Source ↗ |
| — | Lovable Knowledge (project & workspace context)builder-intake | Persistent plain-text instruction store the agent consults on every message — the closest thing in the builder segment to a durable spec. | Drelevant | Source ↗ |
| — | Replit Agent (Plan mode)builder-intake | Prompt-to-app agent with an explicit pre-build planning mode gated by user approval. | Drelevant | Source ↗ |
| — | Bolt.newbuilder-intake | In-browser prompt-to-full-stack-app builder offering an explicit choice between planning first and generating immediately. | Drelevant | Source ↗ |
| — | v0 by Vercelbuilder-intake | Prompt-to-UI generator focused on frontend components and pages. | Drelevant | Source ↗ |
| — | Base44builder-intake | Consumer-feeling AI app builder that turns a prompt into a structured project with screens, data models, authentication and core workflows. | Drelevant | Source ↗ |
| — | Replit Design Canvas / Design Modebuilder-intake | Visual mockup surface for exploring designs before committing to code. | Drelevant | Source ↗ |
| — | Softrbuilder-intake | No-code app builder over existing data sources (Airtable, Google Sheets, databases) with block-based page composition. | Dadjacent | Source ↗ |
| — | Glidebuilder-intake | Builds business apps from spreadsheet or database data with AI-assisted layout. | Dadjacent | Source ↗ |
| — | Bubblebuilder-intake | Visual full-stack no-code development platform with explicit data types and workflow logic. | Drelevant | Source ↗ |
| — | Mochabuilder-intake | AI app builder positioned against Lovable/Bolt/v0 for non-technical builders. | Dweak | Source ↗ |
| — | Magic Patternsbuilder-intake | AI prototyping tool for product teams generating UI from prompts. | Dweak | Source ↗ |
| — | Cursorbuilder-intake | AI code editor whose spec surface is rules files consumed before editing. | Dadjacent | Source ↗ |
| — | Proposifyscoping | Proposal platform whose AI drafts editable executive summaries, cover letters, scopes of work and project approaches from pasted discovery material. | Drelevant | Source ↗ |
| — | PandaDocscoping | Document automation platform covering SOW, MSA and proposal generation through to signature and payment. | Dweak | Source ↗ |
| — | Qwilrscoping | Proposal tool that outputs an interactive web page rather than a PDF or traditional document. | Dweak | Source ↗ |
| — | FlowEdgescoping | AI proposal/SOW/contract generator aimed at independent consultants, fractional executives and small agencies. | Dadjacent | Source ↗ |
| — | Loopioscoping | Enterprise RFP response platform with content library and AI-assisted question matching. | Dadjacent | Source ↗ |
| — | Responsive (formerly RFPIO)scoping | Enterprise RFP and response management with content library and AI question matching. | Dweak | Source ↗ |
| — | Forecastscoping | Professional-services platform with project scoping and estimation — phases, tasks, assignment, deadlines and placeholder-based pipeline scoping. | Dweak | Source ↗ |
| — | KuberAgent SOW & Project Proposal Generatorscoping | Free SOW and project proposal generator. | Dweak | Source ↗ |
| — | Galorath SEERscoping | Parametric software cost and effort estimation using sizing models. | Dadjacent | Source ↗ |
| — | Cucumber Studioacceptance | BDD collaboration platform positioning itself as the single source of truth where whole teams manage executable specifications together. | Drelevant | Source ↗ |
| — | Xray (BDD in Jira)acceptance | Jira-native test management storing Gherkin scenarios as Jira issues linked to requirement issues for coverage. | Drelevant | Source ↗ |
| — | Zephyr (Gherkin support)acceptance | Jira-based test management offering one home for manual, automated and BDD testing. | Dadjacent | Source ↗ |
| — | Tricentis qTestacceptance | Enterprise test management with BDD support, positioned for governance. | Dadjacent | Source ↗ |
| — | Reqnrollacceptance | Open-source Cucumber-style BDD framework for .NET; the community successor to the discontinued SpecFlow, led by SpecFlow's original creator. | Drelevant | Source ↗ |
| — | SpecFlow + LivingDocacceptance | Formerly the most widely used .NET BDD framework with living documentation generation; discontinued by Tricentis. | Drelevant | Source ↗ |
| — | ContextQAacceptance | AI-native test platform generating and self-healing tests from plain-English behaviour descriptions without a glue-code layer. | Dadjacent | Source ↗ |
| — | Cucumber (open-source core)acceptance | The de facto reference BDD implementation and the origin of the Gherkin Given/When/Then grammar. | Drelevant | Source ↗ |
60 mined records. Search and inspect the full agent output; nothing is collapsed into a top-ten headline.
| Rank | Identity | What the agent found | Evidence | Source |
|---|---|---|---|---|
| — | github/spec-kitspec-driven | CLI ('specify') that installs slash-command templates into 30+ AI coding agents, driving a gated phase flow from intent to implementation. Read the actual spec-template.md: it mandates prioritized (P1/P2/P3) INDEPENDENTLY TESTABLE user stories, each with Given/When/Then Acceptance Scenarios, then FR-### functional requirements, Key Entities, measurable SC-### Success Criteria, and an explicit Assumptions section. | Drelevant | Source ↗ |
| — | Fission-AI/OpenSpecspec-driven | Lightweight SDD layer that forces human+AI agreement on requirements BEFORE code. Centers on change-scoped 'deltas' rather than whole-codebase context, which is its main token-efficiency claim. | Drelevant | Source ↗ |
| — | bmad-code-org/BMAD-METHODspec-driven | Multi-agent 'agile team' simulation (analyst, PM, architect, SM, dev, QA, UX personas) covering full lifecycle with a Clarify -> Plan -> Build/verify -> Learn loop. | Drelevant | Source ↗ |
| — | buildermethods/agent-osspec-driven | Injects a codebase's OWN conventions into agent context. Four capabilities: Discover Standards (reverse-engineer conventions from real code), Deploy Standards, Shape Spec, Index Standards. Distinctive because most SDD tools assume greenfield. | Iadjacent | Source ↗ |
| — | gokulrajaram/ProductSpecspec-driven | An OPEN STANDARD (not a tool) for portable product specs readable by humans, reviewable by product tools, and executable by agents downstream. Explicitly declines to define taste or reviewer behavior — only structure and interoperability. | Drelevant | Source ↗ |
| — | FoundationAgents/MetaGPTprd-agent | Multi-agent framework encoding 'Code = SOP(Team)': one-line requirement in, PRD/user stories/competitive analysis/data structures/APIs/repo out, via product manager, architect, project manager, engineer roles. | Dadjacent | Source ↗ |
| — | cdeust/ai-prd-generatorprd-agent | Claude Code/Cowork plugin generating PRDs via a confidence-driven multi-choice clarification loop across 8 PRD types, with multi-judge verification. | Dadjacent | Source ↗ |
| — | anombyte93/prd-taskmasterprd-agent | Zero-config goal-to-tasks engine ('Atlas'): graded PRD validation, dependency-ordered task graph, evidence-gated execution. | Irelevant | Source ↗ |
| — | nurettincoban/ai-prd-workflowprd-agent | Structured PROMPT PIPELINE (shell, no runtime lock-in) turning vague ideas into implementable RFCs; assistant-agnostic. | Irelevant | Source ↗ |
| — | TechNomadCode/AI-Product-Development-Toolkitprd-agent | User-centered product development prompt templates and agent configurations (no code — a prompt library). | Iadjacent | Source ↗ |
| — | visual-req/visual-specprd-agent | Explicitly discovery-shaped: 'Give your short business requirement, follow instructions, ANSWER A FEW QUESTIONS, get your specification, prototypes, codes, tests.' Question-asking is the advertised core step. | Irelevant | Source ↗ |
| — | chaussky/ainalystprd-agent | AI assistant for business analysts working to the BABOK v3 methodology — i.e. grounded in a real, established requirements-engineering body of knowledge rather than ad-hoc prompt structure. | Irelevant | Source ↗ |
| — | ductienuit/SpecForgeprd-agent | Deliberately NOT a PRD generator (states so in its own description): a requirement-QUALITY skill pack that audits, scores, and improves existing specs before handoff. | Iadjacent | Source ↗ |
| — | Pimzino/spec-workflow-mcpspec-driven | MCP server exposing structured spec-driven workflow tools, with a real-time web dashboard and VSCode extension for monitoring spec progress — i.e. spec state as a live, inspectable service rather than files alone. | Irelevant | Source ↗ |
| — | gemini-cli-extensions/conductorspec-driven | Google-org plugin bringing specify/plan/implement SDD to Antigravity and Claude Code. | Iadjacent | Source ↗ |
| — | gotalab/cc-sddspec-driven | Minimal SDD harness whose framing is 'turn APPROVED specs into long-running autonomous implementation' — the approval gate is the product boundary. | Iadjacent | Source ↗ |
| — | shotgun-sh/shotgunspec-driven | Codebase-AWARE spec writing so agents don't derail — grounds the spec in existing code rather than treating it as greenfield. | Iadjacent | Source ↗ |
| — | Priivacy-ai/spec-kittyspec-driven | SDD with a Kanban dashboard, git worktrees, and auto-merge — spec state rendered as a board. | Iadjacent | Source ↗ |
| — | modu-ai/moai-adkspec-driven | SPEC-driven plan/run/sync harness with 'TRUST 5' quality gates and model+effort routing, single Go binary. | Iadjacent | Source ↗ |
| — | open-gsd/gsd-corespec-driven | 'Git. Ship. Done' core — meta-prompting and context-engineering system positioned as spec-driven development. | Iadjacent | Source ↗ |
| — | gsd-build/get-shit-donespec-driven | Lightweight meta-prompting/context-engineering and SDD system; the highest-starred of the GSD family. | Iweak | Source ↗ |
| — | useblocks/sphinx-needsspec-driven | Adds typed needs/requirements objects to Sphinx docs with IDs, links, and traceability — mature requirements-as-documentation tooling predating the LLM wave. | Irelevant | Source ↗ |
| — | bmw-software-engineering/trlcspec-driven | 'Treat Requirements Like Code' — a real typed requirements DSL with its own grammar and checker, used in automotive engineering. | Irelevant | Source ↗ |
| — | Agile-V/agile_v_skillsspec-driven | Agent skills for traceable requirements, independent verification, and explicit HUMAN APPROVAL GATES. | Iadjacent | Source ↗ |
| — | leocamello/spec-kit-v-modelspec-driven | V-Model extension for Spec Kit that ENFORCES paired generation of development specs and test specs — every requirement must be born with its verification. | Irelevant | Source ↗ |
| — | swingerman/engineerexecutable-spec | Methodology kit built on acceptance-test-FIRST specs with explicit checkpoints — bridges the spec-driven and executable-spec segments. | Irelevant | Source ↗ |
| — | cyanheads/survey-mcp-serverdialog | STRONGEST STRUCTURAL MATCH FOR ACTIONIST. MCP server that turns an LLM into an interviewer while the SERVER owns question state, eligibility, validation and progress. Eight tools: survey_list_available, survey_start_session, survey_get_question, survey_submit_response, survey_get_progress, survey_complete_session, survey_export_results, survey_resume_session. Each question returns 'currentlyEligible' + 'eligibilityReason' for transparency, plus a 'guidanceForLLM' field steering conversational delivery. | Drelevant | Source ↗ |
| — | oasis-surveys/oasis-platformdialog | Self-hosted platform for AI-conducted qualitative interviews at scale (voice-to-voice, modular STT->LLM->TTS, or text), built by/for survey researchers with methodological intent. Semi-structured mode: question guides with follow-up probes and transition logic, so the agent keeps a structured backbone while conversing naturally. | Drelevant | Source ↗ |
| — | Rettend/formatedialog | LLM-powered form builder for designing and running conversational, INTERVIEW-STYLE surveys — sits exactly on the form-engine/dialog boundary Actionist occupies. | Iweak | Source ↗ |
| — | AIinterviewing/ai-conversational-interviewing-LaTeCH-CLfL2025dialog | Replication material for a peer-reviewed paper on AI conversational interviewing transforming surveys — EVIDENCE rather than product. | Irelevant | Source ↗ |
| — | baptisteArno/typebot.iodialog | Mature self-hostable conversational form/chatbot builder — visual flow builder with branching logic, the closest commercial-grade analogue to a conversational intake product. | Drelevant | Source ↗ |
| — | surveyjs/survey-libraryform-engine | Framework-agnostic JSON-driven form/survey RENDERER with the richest conditional model in this segment: conditional visibility, branching, calculated values, expression logic, dynamic panels, repeating groups, carry-forward, and text piping. survey-core holds model/logic; survey-react-ui / survey-angular-ui / survey-vue3-ui / survey-js-ui render. | Drelevant | Source ↗ |
| — | formio/formio.jsform-engine | Plain-JS (ES6, no framework dependency) form renderer AND embedded form builder producing the JSON schema; single script tag embeddable, wizard mode via display:'wizard'. | Drelevant | Source ↗ |
| — | rjsf-team/react-jsonschema-formform-engine | Builds React forms declaratively from standard JSON Schema, with pluggable validators (@rjsf/validator-ajv8, -ata, -cfworker) and 10 UI themes (MUI, Ant, Chakra, Fluent, Bootstrap, DaisyUI, Mantine, Semantic, shadcn). | Drelevant | Source ↗ |
| — | eclipsesource/jsonformsform-engine | Cleanest architectural SEPARATION in this segment: a JSON Schema for DATA and a distinct UI Schema for LAYOUT, with a declarative rule system for show/hide. React, Angular and Vue renderers out of the box. | Drelevant | Source ↗ |
| — | alibaba/formilyform-engine | High-performance reactive form engine (JSON Schema and dynamic forms) for React, React Native, Vue 2 and Vue 3 — built around an observable form model so cross-field reactions scale. | Iadjacent | Source ↗ |
| — | formkit/formkitform-engine | Vue-first form framework whose schema system defines an entire form as a JSON object with validation and conditional logic; description now repositions it as 'The form framework for coding agents'. | Iadjacent | Source ↗ |
| — | vazco/uniformsform-engine | React forms from ANY schema — bridges for JSON Schema, SimpleSchema, Zod, GraphQL — schema-agnostic by design. | Irelevant | Source ↗ |
| — | formbricks/formbricksform-engine | 'Open Source Qualtrics Alternative' — survey platform with targeting, in-app/link surveys and analytics. | Drelevant | Source ↗ |
| — | OpnForm/OpnFormform-engine | 'Beautiful Open-Source Form Builder' (Laravel/PHP + Vue) with conditional logic and a drag-drop builder. | Dadjacent | Source ↗ |
| — | LimeSurvey/LimeSurveyform-engine | Long-established (2003-) survey platform with an unusually deep conditional/branching engine ('ExpressionScript') and complex question typology — the mature prior art for adaptive questionnaires. | Drelevant | Source ↗ |
| — | heyform/heyformform-engine | Open-source conversational-style form builder (Typeform-alike) with logic jumps and variables. | Iadjacent | Source ↗ |
| — | javahuang/SurveyKingform-engine | Self-hosted SurveyMonkey alternative (Java) with one-command deploy. | Iadjacent | Source ↗ |
| — | didi/xiaoju-surveyform-engine | DiDi's enterprise form builder and analytics platform for questionnaires, exams, polls and quizzes. | Iadjacent | Source ↗ |
| — | cucumber/cucumber-jsexecutable-spec | Reference implementation of the executable-spec idea in JS: plain-language .feature files that BOTH document and execute. Its stated purpose is communication and trust across roles, not just testing. | Drelevant | Source ↗ |
| — | getgauge/gaugeexecutable-spec | Cross-platform test automation authoring specs in business language using MARKDOWN rather than Gherkin — lower ceremony, and 'concepts' allow reusable step groupings. | Drelevant | Source ↗ |
| — | robotframework/robotframeworkexecutable-spec | Generic KEYWORD-DRIVEN automation framework for acceptance testing and ATDD/RPA; the keyword abstraction lets non-programmers compose tests from domain vocabulary. | Drelevant | Source ↗ |
| — | reqnroll/Reqnrollexecutable-spec | The living successor to SpecFlow for .NET (SpecFlow having stalled after the .NET Foundation transition); Cucumber-style Gherkin BDD with first-class Visual Studio tooling. | Drelevant | Source ↗ |
| — | karatelabs/karateexecutable-spec | Gherkin-syntax framework that notably ELIMINATES step definitions — the feature file itself is executable for API/contract testing, removing the glue-code maintenance burden that sinks most Cucumber adoptions. | Irelevant | Source ↗ |
| — | behave/behaveexecutable-spec | 'BDD, Python style' — the most widely used Python Gherkin runner. | Drelevant | Source ↗ |
| — | serenity-bdd/serenity-coreexecutable-spec | Wraps Cucumber/JUnit to produce rich LIVING DOCUMENTATION — reports that double as test results, requirements coverage and progress reporting, which is the strongest 'spec as artifact' story in this segment. | Drelevant | Source ↗ |
| — | vitalets/playwright-bddexecutable-spec | Runs Gherkin scenarios on the Playwright test runner, inheriting Playwright's parallelism, tracing and fixtures instead of Cucumber's runner. | Irelevant | Source ↗ |
| — | cucumber/godogexecutable-spec | Official Cucumber implementation for Go. | Iadjacent | Source ↗ |
| — | cucumber/gherkinexecutable-spec | THE parser and compiler for the Gherkin language itself — the canonical grammar and AST underlying every Cucumber-family tool. | Irelevant | Source ↗ |
| — | Behat/Behatexecutable-spec | BDD framework for PHP, one of the oldest continuously maintained Gherkin runners. | Iadjacent | Source ↗ |
| — | bencompton/jest-cucumberexecutable-spec | Executes Gherkin scenarios inside Jest, keeping feature files as the readable spec while reusing an existing unit-test runner. | Iadjacent | Source ↗ |
| — | serenity-js/serenity-jsexecutable-spec | TypeScript-native acceptance-testing framework adding the Screenplay pattern (actors, abilities, tasks) over Playwright/WebdriverIO/Cucumber, aimed at making acceptance suites scale. | Irelevant | Source ↗ |
| — | Codeception/Codeceptionexecutable-spec | Full-stack PHP testing framework with BDD-style scenario syntax and acceptance-testing focus. | Iweak | Source ↗ |
| — | jbehave/jbehave-coreexecutable-spec | The ORIGINAL BDD framework (Dan North lineage), Java. | Iweak | Source ↗ |
| — | Pimzino/claude-code-spec-workflowspec-driven | Automated Claude Code workflows implementing spec-driven development for new features (requirements -> design -> tasks). | Iweak | Source ↗ |
50 mined records. Search and inspect the full agent output; nothing is collapsed into a top-ten headline.
| Rank | Identity | What the agent found | Evidence | Source |
|---|---|---|---|---|
| — | inn-p02-001— | EARS-slotted requirement as the internal ProductSpec representation: trigger, precondition, system, response are mandatory slots so an unfilled slot is both the confidence signal and the next interview question | hypothesistop10 | com-b-013 EARS notation |
| — | inn-p02-002— | UNCOVERED as a computed state on every requirement: a ProductSpec cannot be called complete while any requirement lacks a linked acceptance criterion | hypothesistop10 | com-b-045 Xray |
| — | inn-p02-003— | Elicit into slots, emit Gherkin: close the disjointness by making elicitation write into an EARS structure whose temporal clause order maps mechanically onto Given/When/Then | hypothesistop10 | cross-survey gap (51 commercial + 60 OSS surfaces) |
| — | inn-p02-004— | NEEDS-CLARIFICATION markers embedded at the point of ambiguity, each carrying candidate answers, making unresolved intent countable and mechanically gateable | hypothesistop10 | oss-a-001 spec-kit |
| — | inn-p02-005— | Provenance pointer per requirement: every ProductSpec clause links to the client utterance or evidence item that produced it, converting scope disputes from opinion into lookup | hypothesistop10 | com-b-003 BuildBetter; com-a-002 Cloobot X |
| — | inn-p02-006— | Blocking Accept/Revise gate before any build: a spec the client never explicitly accepted is not a spec, and acceptance baselines the artifact | hypothesistop10 | com-b-024 Replit; com-b-014 DOORS Next baselining |
| — | inn-p02-007— | Change-scoped spec deltas (ADDED/MODIFIED/REMOVED against a baseline) so repeat engagements never re-elicit settled requirements | hypothesistop10 | oss-a-002 OpenSpec |
| — | inn-p02-008— | Maturity-typed spec artifacts (hypothesis → prd → committed proposal) so the same document graduates rather than being rewritten | hypothesistop10 | oss-a-005 ProductSpec artifact_type enum |
| — | inn-p02-009— | Suspect-link propagation: editing a requirement automatically flags dependent acceptance criteria and bindings as suspect, turning change impact into a work queue | hypothesistop10 | com-b-011 Jama; DOORS family |
| — | inn-p02-010— | Example-driven formulation: elicit one concrete example, then generalise into a criterion, instead of asking clients for abstract requirements they cannot articulate | hypothesistop10 | com-b-044 Cucumber three practices (discovery/formulation/automation) |
| — | inn-p02-011— | ProductSpec as a typed graph with a document as one rendering, rather than a document with links bolted on | hypothesiscandidate | com-b-011 Jama semantic product graph |
| — | inn-p02-012— | Non-goals as first-class mandatory fields, not prose asides — an unstated non-goal is the most common source of scope dispute | hypothesiscandidate | com-b-006; parts.json P02 owns non-goals |
| — | inn-p02-013— | Technology-agnostic measurable success criteria (SC-###) enforced by grammar, so 'make it feel fast' becomes verifiable without naming an implementation | hypothesistop10 | oss-a-001 spec-kit SC criteria |
| — | inn-p02-014— | Prototype for look-and-feel, ask for data and behaviour: a formal rule deciding when a mockup replaces a question | hypothesistop10 | com-b-024/com-b-026 builder-intake consensus |
| — | inn-p02-015— | Portable canonical spec format: plain, documented, and readable by something other than Actionist, so a tool's death does not strand the client | hypothesiscandidate | SpecFlow discontinuation; Gherkin survival |
| — | inn-p02-016— | Independently testable prioritised user stories (P1/P2/P3) where implementing only the top story still yields a viable slice | hypothesiscandidate | oss-a-001 spec-template.md |
| — | inn-p02-017— | Assumptions section as a mandatory artifact region recording every default chosen where the client was silent | hypothesiscandidate | oss-a-001 spec-kit Assumptions |
| — | inn-p02-018— | Role-differentiated interrogation as a coverage axis: analyst/architect/QA lenses ask structurally different questions; a spec is incomplete while an axis is unexamined | hypothesiscandidate | oss-a-003 BMAD personas |
| — | inn-p02-019— | Decision trace as a first-class validatable object beside the spec, answering 'why does the build not match what I asked for' | hypothesiscandidate | oss-a-005 decision-trace.schema.json |
| — | inn-p02-020— | Client review annotations captured as structured data rather than email, feeding directly into spec revisions | hypothesiscandidate | oss-a-005 review-annotation.schema.json |
| — | inn-p02-021— | Two-tier scope split: durable org conventions vs per-project facts, so client-wide preferences are stated once | hypothesiscandidate | com-b-023 Lovable Knowledge |
| — | inn-p02-022— | Structured selection over blob-stuffing: spec clauses selectable into a prompt by relevance rather than pasting the whole document and hoping | hypothesistop10 | com-b-023 documented degradation in long contexts |
| — | inn-p02-023— | Acceptance fixtures generated from the spec at acceptance time, becoming the P14 verification input without a second authoring pass | hypothesistop10 | parts.json P02 outputs AcceptanceFixtures; cucumber-js two-audience artifact |
| — | inn-p02-024— | Spec completeness score gating handoff to P12 composition: named, computed, and refusable rather than a judgement call | hypothesiscandidate | lane reasoning joining Xray UNCOVERED to the P02→P12 seam |
| — | inn-p02-025— | Implementation-independence linter: reject spec clauses naming a repository, database or framework, enforcing framework invariant 3 mechanically | hypothesistop10 | knowledge/00-MASTER-SYNTHESIS invariant; A-ledger |
| — | inn-p02-026— | Outcome statement that survives into acceptance, rejecting task-list-as-spec (which says what will be done, never what must be true afterwards) | hypothesistop10 | com-b-024 Replit spec-shape critique |
| — | inn-p02-027— | Authority clauses in the spec: every side-effecting requirement names who may approve it, inheriting the atom contract's authority family | hypothesiscandidate | 12-atom contract authority field; industry authority_boundary priors |
| — | inn-p02-028— | Failure-state enumeration as a mandatory spec region (what happens when the date passes, the record is missing, the payment is pending) | hypothesiscandidate | parts.json P02 owns failure states; Replit reviewer's reminder-date example |
| — | inn-p02-029— | Spec-level denominator capture: each requirement carries the volume it must handle, so composition can reject an under-scaled capability early | hypothesiscandidate | lane denominator discipline; inn-p01-016 |
| — | inn-p02-030— | Five-workflow proving harness: validate the ProductSpec schema against five concrete target workflows drawn from different archetypes before declaring it canonical | hypothesistop10 | parts.json P02 agent brief ('prove it against five target workflows') |
| — | inn-p02-031— | Industry-vocabulary rendering layer: the same canonical spec renders in the client's own terms (matters, jobs, cases, shipments) without changing the underlying structure | hypothesiscandidate | industry-discovery-priors.jsonl vocabulary layer |
| — | inn-p02-032— | Spec diffing at client sign-off: show exactly what changed since the last accepted baseline rather than re-presenting the whole document | hypothesiscandidate | oss-a-002 delta framing; DOORS baselining |
| — | inn-p02-033— | Evidence-grade labels on spec clauses (client-stated, observed, inferred, assumed) so a reader sees which requirements rest on inference | hypothesiscandidate | AGENTS.md evidence discipline applied to the spec artifact |
| — | inn-p02-034— | Refusal path in the spec: an explicit region recording what Actionist declined to build and why, preserving the non-goal decision rationale | hypothesiscandidate | lane reasoning; sweep-spec candidate admission rule |
| — | inn-p02-035— | Regulated-industry spec profile: healthcare/law/mortgage specs must name their excluded data classes as explicit constraints, inheriting the discovery-mode exclusion | hypothesiscandidate | industry priors; inn-p01-026 |
| — | inn-p02-036— | Single-mastering decision recorded in the spec: name once whether the spec or the repo masters acceptance scenarios, rejecting dual-mastering drift | hypothesiscandidate | com-b-045 Xray's own documented tension |
| — | inn-p02-037— | Spec-to-prompt compiler with receipts: record exactly which clauses were selected into which build prompt, so a build failure traces to a selection decision | hypothesiscandidate | lane reasoning joining inn-p02-022 to P12/P14 |
| — | inn-p02-038— | Client-readable acceptance rendering: generate Gherkin as an output artifact but never require the client to author it | hypothesistop10 | com-b-044 reject-mandatory-Gherkin finding; cucumber-js stakeholder-readability failure mode |
| — | inn-p02-039— | Estimation ranges rather than point estimates where scope is still soft, made honest by tying the range to unresolved slots | hypothesiscandidate | com-b-043 parametric estimation |
| — | inn-p02-040— | Zero-open-markers release gate: mechanically refuse to promote a spec to composition while any NEEDS-CLARIFICATION or UNCOVERED state remains | hypothesistop10 | oss-a-001 + com-b-045 combined |
| — | inn-p02-041— | Spec authored against the 12-atom vocabulary so every requirement declares which atom it instantiates, inheriting that atom's verification and recovery obligations | hypothesistop10 | niche-atom-block-join 12-atom contract |
| — | inn-p02-042— | Acceptance criteria written before implementation options are discussed, preventing the spec from being shaped by what happens to be easy to assemble | hypothesiscandidate | framework invariant 3; AutoSaaS spec-before-code |
| — | inn-p02-043— | Shadow-mode spec generation: draft the spec automatically from discovery, but require human formulation review before it becomes the client-facing artifact | hypothesiscandidate | oss-a-028 OASIS shadow mode applied to spec authoring |
| — | inn-p02-044— | Contradiction register inside the spec: when discovery produced conflicting requirements, record both with sources rather than silently choosing | hypothesiscandidate | inn-p01-006; phase-2 preserved-contradiction discipline |
| — | inn-p02-045— | Spec expiry: an accepted spec carries a validity window after which client circumstances must be re-confirmed before build | hypothesiscandidate | com-a-007 content decay; oss-b-044 bi-temporal validity |
| — | inn-p02-046— | Minimum viable ProductSpec defined by what composition actually needs, derived backwards from P12's inputs rather than forwards from documentation habit | hypothesistop10 | parts.json P02 open question 'what is the minimum ProductSpec'; P12 deps |
| — | inn-p02-047— | Per-statement quality gating at authoring time: check each requirement sentence for testability as it is written, making quality and testability the same operation | hypothesiscandidate | com-b-011 Advisor granularity (mechanism itself unverified) |
| — | inn-p02-048— | Explicit systems-of-record binding section: the spec names which client system owns each entity, carrying P01's SourceOfTruthConflict findings into composition | hypothesiscandidate | inn-p01-020; SISOCRM one-owner rule |
| — | inn-p02-049— | Spec artifacts are data, not instructions: content quoted from client documents is escaped so it cannot steer the downstream build agent | hypothesiscandidate | C04 stop condition; inn-p01-039 |
| — | inn-p02-050— | One-page client-facing rendering of a structurally rich spec, so rigour lives in the schema while the client reads something humane | hypothesiscandidate | lane reasoning; DOORS usability-tax warning |
121 mined records. Search and inspect the full agent output; nothing is collapsed into a top-ten headline.
| Rank | Identity | What the agent found | Evidence | Source |
|---|---|---|---|---|
| — | ChatPRDai-prd | AI product-management platform that drafts and improves PRDs, one-pagers, user stories and tech specs from natural-language prompts. | Drelevant | Source ↗ |
| — | ChatPRD MCP Serverai-prd | Authenticated MCP endpoint exposing product documents to AI coding tools as live context. | Drelevant | Source ↗ |
| — | BuildBetterai-prd | Customer-intelligence platform that generates PRDs and scoping docs grounded in captured customer calls, tickets and Slack threads with citations. | Drelevant | Source ↗ |
| — | Figrai-prd | PRD generator that refuses the blank prompt: ingests existing product context first, then structures a PRD grounded in what the product actually does. | Drelevant | Source ↗ |
| — | Keeborgai-prd | Spec generator producing a multi-document stack formatted for AI-agent consumption with cross-document consistency checking. | Dadjacent | Source ↗ |
| — | ContextArkai-prd | Spec tool built for AI coding agents that emphasises non-goals and acceptance criteria to prevent scope creep in Cursor/Claude Code. | Drelevant | Source ↗ |
| — | IdeaPlan Forgeai-prd | AI document generation embedded in a broader PM operating system (feedback, roadmap, releases). | Dweak | Source ↗ |
| — | FreePRD.aiai-prd | Free unlimited PRD generation with no signup, positioned explicitly as a ChatPRD alternative. | Dweak | Source ↗ |
| — | FifthDraftai-prd | Free unlimited PRD generator requiring no account; pick product type, describe feature, receive structured output. | Dweak | Source ↗ |
| — | Taskade AI Software Development Proposal Generatorscoping | Template-driven AI generator producing software development proposals inside a general workspace tool. | Dweak | Source ↗ |
| — | Jama Connectreq-mgmt | Requirements/engineering management platform now repositioned as an 'Intelligent Engineering Management Platform' with spec-driven development for AI agents. | Drelevant | Source ↗ |
| — | Jama Connect Advisorreq-mgmt | NLP requirements-authoring assistant that checks the quality of individual requirement statements against INCOSE best practice and EARS syntax. | Drelevant | Source ↗ |
| — | EARS notation (Easy Approach to Requirements Syntax)req-mgmt | A constrained-natural-language grammar for requirements; not a product but the mechanism several commercial tools implement. | Drelevant | Source ↗ |
| — | IBM Engineering Requirements Management DOORS Nextreq-mgmt | Enterprise requirements management for regulated, long-lifecycle engineering with formal baselines and multi-level traceability. | Drelevant | Source ↗ |
| — | DOORS Next suspect-link change propagationreq-mgmt | Change-impact mechanism: editing a requirement automatically marks associated links as suspect. | Drelevant | Source ↗ |
| — | IBM Engineering Requirements Management DOORS (Classic)req-mgmt | The long-lived predecessor RM tool, still entrenched where organisations have long product lifecycles and historical investment. | Dadjacent | Source ↗ |
| — | Siemens Polarion ALMreq-mgmt | Full integration of requirements, change and test management in one ALM platform. | Dadjacent | Source ↗ |
| — | PTC Codebeamerreq-mgmt | Highly configurable ALM for complex regulated product organisations covering requirements, risks and verification. | Dadjacent | Source ↗ |
| — | Visure Requirements ALMreq-mgmt | Requirements ALM for safety-critical and highly regulated industries with bidirectional traceability across thousands of interconnected items. | Dadjacent | Source ↗ |
| — | Modern Requirements4DevOpsreq-mgmt | Requirements and traceability layer built directly inside Microsoft Azure DevOps rather than as a separate platform. | Dadjacent | Source ↗ |
| — | ReqSuite RMreq-mgmt | Requirements management aimed at medium-sized product developers, positioned as lighter-weight than DOORS/Polarion class tools. | Dadjacent | Source ↗ |
| — | Lovablebuilder-intake | Prompt-to-app builder generating frontend, backend, database, auth and integrations from natural-language description in a per-project chat. | Drelevant | Source ↗ |
| — | Lovable Knowledge (project & workspace context)builder-intake | Persistent plain-text instruction store the agent consults on every message — the closest thing in the builder segment to a durable spec. | Drelevant | Source ↗ |
| — | Replit Agent (Plan mode)builder-intake | Prompt-to-app agent with an explicit pre-build planning mode gated by user approval. | Drelevant | Source ↗ |
| — | Bolt.newbuilder-intake | In-browser prompt-to-full-stack-app builder offering an explicit choice between planning first and generating immediately. | Drelevant | Source ↗ |
| — | v0 by Vercelbuilder-intake | Prompt-to-UI generator focused on frontend components and pages. | Drelevant | Source ↗ |
| — | Base44builder-intake | Consumer-feeling AI app builder that turns a prompt into a structured project with screens, data models, authentication and core workflows. | Drelevant | Source ↗ |
| — | Replit Design Canvas / Design Modebuilder-intake | Visual mockup surface for exploring designs before committing to code. | Drelevant | Source ↗ |
| — | Softrbuilder-intake | No-code app builder over existing data sources (Airtable, Google Sheets, databases) with block-based page composition. | Dadjacent | Source ↗ |
| — | Glidebuilder-intake | Builds business apps from spreadsheet or database data with AI-assisted layout. | Dadjacent | Source ↗ |
| — | Bubblebuilder-intake | Visual full-stack no-code development platform with explicit data types and workflow logic. | Drelevant | Source ↗ |
| — | Mochabuilder-intake | AI app builder positioned against Lovable/Bolt/v0 for non-technical builders. | Dweak | Source ↗ |
| — | Magic Patternsbuilder-intake | AI prototyping tool for product teams generating UI from prompts. | Dweak | Source ↗ |
| — | Cursorbuilder-intake | AI code editor whose spec surface is rules files consumed before editing. | Dadjacent | Source ↗ |
| — | Proposifyscoping | Proposal platform whose AI drafts editable executive summaries, cover letters, scopes of work and project approaches from pasted discovery material. | Drelevant | Source ↗ |
| — | PandaDocscoping | Document automation platform covering SOW, MSA and proposal generation through to signature and payment. | Dweak | Source ↗ |
| — | Qwilrscoping | Proposal tool that outputs an interactive web page rather than a PDF or traditional document. | Dweak | Source ↗ |
| — | FlowEdgescoping | AI proposal/SOW/contract generator aimed at independent consultants, fractional executives and small agencies. | Dadjacent | Source ↗ |
| — | Loopioscoping | Enterprise RFP response platform with content library and AI-assisted question matching. | Dadjacent | Source ↗ |
| — | Responsive (formerly RFPIO)scoping | Enterprise RFP and response management with content library and AI question matching. | Dweak | Source ↗ |
| — | Forecastscoping | Professional-services platform with project scoping and estimation — phases, tasks, assignment, deadlines and placeholder-based pipeline scoping. | Dweak | Source ↗ |
| — | KuberAgent SOW & Project Proposal Generatorscoping | Free SOW and project proposal generator. | Dweak | Source ↗ |
| — | Galorath SEERscoping | Parametric software cost and effort estimation using sizing models. | Dadjacent | Source ↗ |
| — | Cucumber Studioacceptance | BDD collaboration platform positioning itself as the single source of truth where whole teams manage executable specifications together. | Drelevant | Source ↗ |
| — | Xray (BDD in Jira)acceptance | Jira-native test management storing Gherkin scenarios as Jira issues linked to requirement issues for coverage. | Drelevant | Source ↗ |
| — | Zephyr (Gherkin support)acceptance | Jira-based test management offering one home for manual, automated and BDD testing. | Dadjacent | Source ↗ |
| — | Tricentis qTestacceptance | Enterprise test management with BDD support, positioned for governance. | Dadjacent | Source ↗ |
| — | Reqnrollacceptance | Open-source Cucumber-style BDD framework for .NET; the community successor to the discontinued SpecFlow, led by SpecFlow's original creator. | Drelevant | Source ↗ |
| — | SpecFlow + LivingDocacceptance | Formerly the most widely used .NET BDD framework with living documentation generation; discontinued by Tricentis. | Drelevant | Source ↗ |
| — | ContextQAacceptance | AI-native test platform generating and self-healing tests from plain-English behaviour descriptions without a glue-code layer. | Dadjacent | Source ↗ |
| — | Cucumber (open-source core)acceptance | The de facto reference BDD implementation and the origin of the Gherkin Given/When/Then grammar. | Drelevant | Source ↗ |
| — | github/spec-kitspec-driven | CLI ('specify') that installs slash-command templates into 30+ AI coding agents, driving a gated phase flow from intent to implementation. Read the actual spec-template.md: it mandates prioritized (P1/P2/P3) INDEPENDENTLY TESTABLE user stories, each with Given/When/Then Acceptance Scenarios, then FR-### functional requirements, Key Entities, measurable SC-### Success Criteria, and an explicit Assumptions section. | Drelevant | Source ↗ |
| — | Fission-AI/OpenSpecspec-driven | Lightweight SDD layer that forces human+AI agreement on requirements BEFORE code. Centers on change-scoped 'deltas' rather than whole-codebase context, which is its main token-efficiency claim. | Drelevant | Source ↗ |
| — | bmad-code-org/BMAD-METHODspec-driven | Multi-agent 'agile team' simulation (analyst, PM, architect, SM, dev, QA, UX personas) covering full lifecycle with a Clarify -> Plan -> Build/verify -> Learn loop. | Drelevant | Source ↗ |
| — | buildermethods/agent-osspec-driven | Injects a codebase's OWN conventions into agent context. Four capabilities: Discover Standards (reverse-engineer conventions from real code), Deploy Standards, Shape Spec, Index Standards. Distinctive because most SDD tools assume greenfield. | Iadjacent | Source ↗ |
| — | gokulrajaram/ProductSpecspec-driven | An OPEN STANDARD (not a tool) for portable product specs readable by humans, reviewable by product tools, and executable by agents downstream. Explicitly declines to define taste or reviewer behavior — only structure and interoperability. | Drelevant | Source ↗ |
| — | FoundationAgents/MetaGPTprd-agent | Multi-agent framework encoding 'Code = SOP(Team)': one-line requirement in, PRD/user stories/competitive analysis/data structures/APIs/repo out, via product manager, architect, project manager, engineer roles. | Dadjacent | Source ↗ |
| — | cdeust/ai-prd-generatorprd-agent | Claude Code/Cowork plugin generating PRDs via a confidence-driven multi-choice clarification loop across 8 PRD types, with multi-judge verification. | Dadjacent | Source ↗ |
| — | anombyte93/prd-taskmasterprd-agent | Zero-config goal-to-tasks engine ('Atlas'): graded PRD validation, dependency-ordered task graph, evidence-gated execution. | Irelevant | Source ↗ |
| — | nurettincoban/ai-prd-workflowprd-agent | Structured PROMPT PIPELINE (shell, no runtime lock-in) turning vague ideas into implementable RFCs; assistant-agnostic. | Irelevant | Source ↗ |
| — | TechNomadCode/AI-Product-Development-Toolkitprd-agent | User-centered product development prompt templates and agent configurations (no code — a prompt library). | Iadjacent | Source ↗ |
| — | visual-req/visual-specprd-agent | Explicitly discovery-shaped: 'Give your short business requirement, follow instructions, ANSWER A FEW QUESTIONS, get your specification, prototypes, codes, tests.' Question-asking is the advertised core step. | Irelevant | Source ↗ |
| — | chaussky/ainalystprd-agent | AI assistant for business analysts working to the BABOK v3 methodology — i.e. grounded in a real, established requirements-engineering body of knowledge rather than ad-hoc prompt structure. | Irelevant | Source ↗ |
| — | ductienuit/SpecForgeprd-agent | Deliberately NOT a PRD generator (states so in its own description): a requirement-QUALITY skill pack that audits, scores, and improves existing specs before handoff. | Iadjacent | Source ↗ |
| — | Pimzino/spec-workflow-mcpspec-driven | MCP server exposing structured spec-driven workflow tools, with a real-time web dashboard and VSCode extension for monitoring spec progress — i.e. spec state as a live, inspectable service rather than files alone. | Irelevant | Source ↗ |
| — | gemini-cli-extensions/conductorspec-driven | Google-org plugin bringing specify/plan/implement SDD to Antigravity and Claude Code. | Iadjacent | Source ↗ |
| — | gotalab/cc-sddspec-driven | Minimal SDD harness whose framing is 'turn APPROVED specs into long-running autonomous implementation' — the approval gate is the product boundary. | Iadjacent | Source ↗ |
| — | shotgun-sh/shotgunspec-driven | Codebase-AWARE spec writing so agents don't derail — grounds the spec in existing code rather than treating it as greenfield. | Iadjacent | Source ↗ |
| — | Priivacy-ai/spec-kittyspec-driven | SDD with a Kanban dashboard, git worktrees, and auto-merge — spec state rendered as a board. | Iadjacent | Source ↗ |
| — | modu-ai/moai-adkspec-driven | SPEC-driven plan/run/sync harness with 'TRUST 5' quality gates and model+effort routing, single Go binary. | Iadjacent | Source ↗ |
| — | open-gsd/gsd-corespec-driven | 'Git. Ship. Done' core — meta-prompting and context-engineering system positioned as spec-driven development. | Iadjacent | Source ↗ |
| — | gsd-build/get-shit-donespec-driven | Lightweight meta-prompting/context-engineering and SDD system; the highest-starred of the GSD family. | Iweak | Source ↗ |
| — | useblocks/sphinx-needsspec-driven | Adds typed needs/requirements objects to Sphinx docs with IDs, links, and traceability — mature requirements-as-documentation tooling predating the LLM wave. | Irelevant | Source ↗ |
| — | bmw-software-engineering/trlcspec-driven | 'Treat Requirements Like Code' — a real typed requirements DSL with its own grammar and checker, used in automotive engineering. | Irelevant | Source ↗ |
| — | Agile-V/agile_v_skillsspec-driven | Agent skills for traceable requirements, independent verification, and explicit HUMAN APPROVAL GATES. | Iadjacent | Source ↗ |
| — | leocamello/spec-kit-v-modelspec-driven | V-Model extension for Spec Kit that ENFORCES paired generation of development specs and test specs — every requirement must be born with its verification. | Irelevant | Source ↗ |
| — | swingerman/engineerexecutable-spec | Methodology kit built on acceptance-test-FIRST specs with explicit checkpoints — bridges the spec-driven and executable-spec segments. | Irelevant | Source ↗ |
| — | cyanheads/survey-mcp-serverdialog | STRONGEST STRUCTURAL MATCH FOR ACTIONIST. MCP server that turns an LLM into an interviewer while the SERVER owns question state, eligibility, validation and progress. Eight tools: survey_list_available, survey_start_session, survey_get_question, survey_submit_response, survey_get_progress, survey_complete_session, survey_export_results, survey_resume_session. Each question returns 'currentlyEligible' + 'eligibilityReason' for transparency, plus a 'guidanceForLLM' field steering conversational delivery. | Drelevant | Source ↗ |
| — | oasis-surveys/oasis-platformdialog | Self-hosted platform for AI-conducted qualitative interviews at scale (voice-to-voice, modular STT->LLM->TTS, or text), built by/for survey researchers with methodological intent. Semi-structured mode: question guides with follow-up probes and transition logic, so the agent keeps a structured backbone while conversing naturally. | Drelevant | Source ↗ |
| — | Rettend/formatedialog | LLM-powered form builder for designing and running conversational, INTERVIEW-STYLE surveys — sits exactly on the form-engine/dialog boundary Actionist occupies. | Iweak | Source ↗ |
| — | AIinterviewing/ai-conversational-interviewing-LaTeCH-CLfL2025dialog | Replication material for a peer-reviewed paper on AI conversational interviewing transforming surveys — EVIDENCE rather than product. | Irelevant | Source ↗ |
| — | baptisteArno/typebot.iodialog | Mature self-hostable conversational form/chatbot builder — visual flow builder with branching logic, the closest commercial-grade analogue to a conversational intake product. | Drelevant | Source ↗ |
| — | surveyjs/survey-libraryform-engine | Framework-agnostic JSON-driven form/survey RENDERER with the richest conditional model in this segment: conditional visibility, branching, calculated values, expression logic, dynamic panels, repeating groups, carry-forward, and text piping. survey-core holds model/logic; survey-react-ui / survey-angular-ui / survey-vue3-ui / survey-js-ui render. | Drelevant | Source ↗ |
| — | formio/formio.jsform-engine | Plain-JS (ES6, no framework dependency) form renderer AND embedded form builder producing the JSON schema; single script tag embeddable, wizard mode via display:'wizard'. | Drelevant | Source ↗ |
| — | rjsf-team/react-jsonschema-formform-engine | Builds React forms declaratively from standard JSON Schema, with pluggable validators (@rjsf/validator-ajv8, -ata, -cfworker) and 10 UI themes (MUI, Ant, Chakra, Fluent, Bootstrap, DaisyUI, Mantine, Semantic, shadcn). | Drelevant | Source ↗ |
| — | eclipsesource/jsonformsform-engine | Cleanest architectural SEPARATION in this segment: a JSON Schema for DATA and a distinct UI Schema for LAYOUT, with a declarative rule system for show/hide. React, Angular and Vue renderers out of the box. | Drelevant | Source ↗ |
| — | alibaba/formilyform-engine | High-performance reactive form engine (JSON Schema and dynamic forms) for React, React Native, Vue 2 and Vue 3 — built around an observable form model so cross-field reactions scale. | Iadjacent | Source ↗ |
| — | formkit/formkitform-engine | Vue-first form framework whose schema system defines an entire form as a JSON object with validation and conditional logic; description now repositions it as 'The form framework for coding agents'. | Iadjacent | Source ↗ |
| — | vazco/uniformsform-engine | React forms from ANY schema — bridges for JSON Schema, SimpleSchema, Zod, GraphQL — schema-agnostic by design. | Irelevant | Source ↗ |
| — | formbricks/formbricksform-engine | 'Open Source Qualtrics Alternative' — survey platform with targeting, in-app/link surveys and analytics. | Drelevant | Source ↗ |
| — | OpnForm/OpnFormform-engine | 'Beautiful Open-Source Form Builder' (Laravel/PHP + Vue) with conditional logic and a drag-drop builder. | Dadjacent | Source ↗ |
| — | LimeSurvey/LimeSurveyform-engine | Long-established (2003-) survey platform with an unusually deep conditional/branching engine ('ExpressionScript') and complex question typology — the mature prior art for adaptive questionnaires. | Drelevant | Source ↗ |
| — | heyform/heyformform-engine | Open-source conversational-style form builder (Typeform-alike) with logic jumps and variables. | Iadjacent | Source ↗ |
| — | javahuang/SurveyKingform-engine | Self-hosted SurveyMonkey alternative (Java) with one-command deploy. | Iadjacent | Source ↗ |
| — | didi/xiaoju-surveyform-engine | DiDi's enterprise form builder and analytics platform for questionnaires, exams, polls and quizzes. | Iadjacent | Source ↗ |
| — | cucumber/cucumber-jsexecutable-spec | Reference implementation of the executable-spec idea in JS: plain-language .feature files that BOTH document and execute. Its stated purpose is communication and trust across roles, not just testing. | Drelevant | Source ↗ |
| — | getgauge/gaugeexecutable-spec | Cross-platform test automation authoring specs in business language using MARKDOWN rather than Gherkin — lower ceremony, and 'concepts' allow reusable step groupings. | Drelevant | Source ↗ |
| — | robotframework/robotframeworkexecutable-spec | Generic KEYWORD-DRIVEN automation framework for acceptance testing and ATDD/RPA; the keyword abstraction lets non-programmers compose tests from domain vocabulary. | Drelevant | Source ↗ |
| — | reqnroll/Reqnrollexecutable-spec | The living successor to SpecFlow for .NET (SpecFlow having stalled after the .NET Foundation transition); Cucumber-style Gherkin BDD with first-class Visual Studio tooling. | Drelevant | Source ↗ |
| — | karatelabs/karateexecutable-spec | Gherkin-syntax framework that notably ELIMINATES step definitions — the feature file itself is executable for API/contract testing, removing the glue-code maintenance burden that sinks most Cucumber adoptions. | Irelevant | Source ↗ |
| — | behave/behaveexecutable-spec | 'BDD, Python style' — the most widely used Python Gherkin runner. | Drelevant | Source ↗ |
| — | serenity-bdd/serenity-coreexecutable-spec | Wraps Cucumber/JUnit to produce rich LIVING DOCUMENTATION — reports that double as test results, requirements coverage and progress reporting, which is the strongest 'spec as artifact' story in this segment. | Drelevant | Source ↗ |
| — | vitalets/playwright-bddexecutable-spec | Runs Gherkin scenarios on the Playwright test runner, inheriting Playwright's parallelism, tracing and fixtures instead of Cucumber's runner. | Irelevant | Source ↗ |
| — | cucumber/godogexecutable-spec | Official Cucumber implementation for Go. | Iadjacent | Source ↗ |
| — | cucumber/gherkinexecutable-spec | THE parser and compiler for the Gherkin language itself — the canonical grammar and AST underlying every Cucumber-family tool. | Irelevant | Source ↗ |
| — | Behat/Behatexecutable-spec | BDD framework for PHP, one of the oldest continuously maintained Gherkin runners. | Iadjacent | Source ↗ |
| — | bencompton/jest-cucumberexecutable-spec | Executes Gherkin scenarios inside Jest, keeping feature files as the readable spec while reusing an existing unit-test runner. | Iadjacent | Source ↗ |
| — | serenity-js/serenity-jsexecutable-spec | TypeScript-native acceptance-testing framework adding the Screenplay pattern (actors, abilities, tasks) over Playwright/WebdriverIO/Cucumber, aimed at making acceptance suites scale. | Irelevant | Source ↗ |
| — | Codeception/Codeceptionexecutable-spec | Full-stack PHP testing framework with BDD-style scenario syntax and acceptance-testing focus. | Iweak | Source ↗ |
| — | jbehave/jbehave-coreexecutable-spec | The ORIGINAL BDD framework (Dan North lineage), Java. | Iweak | Source ↗ |
| — | Pimzino/claude-code-spec-workflowspec-driven | Automated Claude Code workflows implementing spec-driven development for new features (requirements -> design -> tasks). | Iweak | Source ↗ |
| — | industry-atom-specifications.mdlocal-estate | 17 industry bounded specs, 66 use cases, 12 atoms, 170-cell readiness trace; all cells readiness_unexecuted | Erelevant | research/actionmodel-builder-research-2026-08-26/phase-2/outputs/industry-atom-specifications.md |
| — | niche-atom-block-join.mdlocal-estate | 12-atom contract schema, use-case→atom map, archetype priority scoring, preserved catalogue contradictions | Erelevant | research/actionmodel-builder-research-2026-08-26/expansion/outputs/niche-atom-block-join.md |
| — | actionist-solutions-sweep-spec-2026-08-26.mdlocal-estate | solution_atom discovery record; builder decomposition items 1-2 are P01/P02 restated | Erelevant | research/actionist-solutions-sweep-spec-2026-08-26.md |
| — | autosaas-method.mdlocal-estate | opportunity-intake gate and spec-constitution field list; procedural design, never measured | Erelevant | [private local source withheld] |
| — | 00-MASTER-SYNTHESIS.mdlocal-estate | nine irreducible jobs; jobs 1-2 are this lane; demand compression thesis | Erelevant | knowledge/00-MASTER-SYNTHESIS.md |
| — | 02-ASSUMPTION-LEDGER.mdlocal-estate | A01/A02/A17/A22/A38 bound this lane's claims | Erelevant | knowledge/02-ASSUMPTION-LEDGER.md |
| — | parts.jsonlocal-estate | P01/P02 theses, owned outputs and open questions | Erelevant | site/system-map/data/parts.json |
| — | first-principles-framework.mdlocal-estate | C01/C02 atomic capabilities = demand normalization and requirement elicitation | Erelevant | research/actionmodel-builder-research-2026-08-26/outputs/first-principles-framework.md |
| — | synthetic-pilot-specification.mdlocal-estate | pre-registered fixture/state-machine discipline reused for acceptance design | Erelevant | research/actionmodel-builder-research-2026-08-26/phase-3/outputs/synthetic-pilot-specification.md |
| — | public-signals-wave-11.mdlocal-estate | public signal classes A/B/C and their explicit limits | Erelevant | research/actionmodel-builder-research-2026-08-26/expansion/wave-11/outputs/public-signals-wave-11.md |
Source: site/system-map/data/parts.json#P02 · preserved research datasets remain inline below their source-backed synthesis.