AI Workbench

AI Context Drift DetectorCompare your original goal, hard constraints, and the latest AI answer. Detect whether the AI is answering an old task, ignoring constraints, or inventing context. AI Agent Run Recovery PlannerPaste a stuck AI agent transcript, command output, or failure log. The tool identifies loops, permission blocks, test failures, stale context, and creates a recovery prompt. AI Requirements Test Case BuilderTurn a feature requirement, user story, or AI implementation plan into acceptance tests, edge cases, negative cases, mobile checks, privacy checks, and a test-writing prompt. AI Bug Repro Packet BuilderTurn fuzzy bug reports, user complaints, errors, and screenshot text into reproducible steps, expected and actual behavior, evidence, and a coding-agent repair prompt. AI File Context Map BuilderConvert a task, file list, and constraints into a coding-agent context map that separates entry points, likely owners, tests, assets, generated files, and do-not-touch areas. AI Instruction Conflict ResolverCompare system rules, personal preferences, and the current task to spot conflicts around language, deployment, privacy, scope, verbosity, and verification before sending instructions to AI. AI Design Feedback Brief BuilderTurn subjective design feedback like ugly, dated, not premium, incoherent, or hard to read into concrete UI issues, acceptance criteria, and a prompt for a design or coding agent. AI Data Extraction Schema BuilderConvert messy notes, tickets, meeting records, emails, or research snippets into target fields, a draft JSON schema, validation rules, and an extraction prompt. AI Research Task Packet BuilderTurn a vague research or decision question into a scoped AI research packet with search queries, source requirements, evidence table fields, and verification rules. AI Prompt Library CuratorTurn reusable prompts into prompt-library cards with variable slots, guardrails, version notes, acceptance criteria, and test cases. AI Output Rubric BuilderCreate reusable scoring rubrics for evaluating AI answers, code plans, SEO advice, research summaries, model comparisons, and generated content. AI Memory Update ExtractorExtract durable AI memory candidates from a conversation, separate temporary instructions from long-term preferences, and flag privacy risks before saving. AI Agent Permission GateCheck whether an AI agent should be allowed to browse, run commands, write files, deploy, access accounts, or touch production systems. AI Knowledge Base Chunking PlannerPlan chunk boundaries, metadata fields, exclusion rules, and redaction checks before turning docs, FAQs, transcripts, policies, or code into a RAG knowledge base. AI Image Prompt Brief BuilderTurn image purpose, visual direction, aspect ratio, exclusions, and rights constraints into a copy-ready image generation brief with alt text. AI Token and Cost PlannerEstimate AI prompt tokens, expected output tokens, monthly call volume, and model spend using your own per-million-token prices. AI Eval Dataset BuilderTurn an AI task, pass criteria, and real failures into a maintainable JSONL eval dataset with judge focus notes. AI Data Retention Policy BuilderDraft retention, consent, logging, training, deletion, and third-party sharing rules for AI features without sending data to a model. AI Automation ROI CalculatorEstimate whether an AI workflow is worth automating by comparing time saved, call frequency, build effort, monthly tool cost, payback time, and risk. AI Feature Threat Model BuilderBuild a threat model for AI chat, RAG, coding agents, tool use, logging, retrieval, and user-data flows before launch. AI Vendor Decision MatrixCompare AI models, vendors, and platforms across privacy, cost, quality, context, tool use, region, reliability, portability, and lock-in risk. AI Prompt Injection Test Suite BuilderGenerate local prompt-injection regression tests for AI chat, RAG, browser agents, tool-calling agents, support bots, and document workflows. AI Answer Grounding Evidence MapMap AI-answer claims to source excerpts, flag weak or missing evidence, and create a publish-before-review checklist without calling a model. AI Support Escalation Policy BuilderDraft escalation, forbidden-promise, sensitive-data, refund, account, security, and compliance boundaries for AI support bots and reply assistants. AI System Prompt Guardrail BuilderDraft product-ready system prompts with allowed behavior, forbidden behavior, refusal rules, escalation paths, evidence requirements, and output format. AI Tool-Call Contract BuilderCreate a tool-calling contract for AI agents: tool list, parameters, returns, errors, permission tiers, dry-run rules, human approval, audit logs, and rollback checks. AI Incident Postmortem BuilderTurn an AI hallucination, unsafe action, privacy leak, bad support reply, wrong deployment, or context drift into a postmortem, root-cause list, fix plan, and regression test prompt. AI Command Risk CheckerReview terminal commands suggested by AI before running them. Flag destructive commands, deploys, remote install scripts, secrets, permission changes, package installs, and cloud mutations. AI PRD Scope Brief BuilderTurn AI chats, rough product ideas, feature requests, and founder notes into a focused PRD, V0 scope, non-goals, acceptance criteria, risk notes, and launch metrics. AI Source Conflict ResolverOrganize conflicting AI answers, source excerpts, numbers, dates, and claims into a verification checklist with safer wording and next-source checks. AI Prompt Leak Risk CheckerCheck a prompt before publishing, sharing with teammates, saving to GitHub, or turning it into a reusable template. Flag secrets, system prompts, internal URLs, customer data, prompt-injection text, and overly specific personal context. AI Table Schema QACheck AI-generated Markdown tables, CSV, or JSON arrays before importing or publishing. Flag missing expected fields, duplicate headers, uneven rows, blank cells, placeholder values, and sensitive data. AI Automation Backlog PrioritizerRank AI feature and automation ideas by impact, frequency, effort, risk, privacy, and no-backend feasibility so you can choose what to build next. AI Use Disclosure BuilderGenerate practical AI-use disclosure statements for papers, blogs, client deliverables, product pages, and public content, including scope, human review, and boundary notes. AI Team Usage Policy BuilderCreate a lightweight AI usage policy for a small team, lab, school project, or product team, covering allowed use, forbidden data, approval gates, and review responsibilities. AI-generated Code License CheckerReview AI-generated code before merging by checking copied-source clues, open-source license risk, dependency installs, tests, secrets, and attribution notes. AI Assignment Integrity CheckerCheck whether AI use in coursework, papers, reports, or assignments is within a safer integrity boundary. Review course rules, disclosure, citation verification, personal contribution, and plagiarism-risk wording. AI Job Application Authenticity CheckerReview AI-rewritten resumes, cover letters, LinkedIn summaries, and application answers for exaggeration, generic AI language, keyword gaps, and private employer data. AI Client Deliverable Trust CheckerCheck AI-assisted client reports, consulting notes, proposals, SEO recommendations, project emails, and product deliverables for evidence gaps, overpromising, scope drift, and sensitive client data. AI Study Tutor Prompt BuilderBuild a personalized tutor prompt from your learning goal, current level, stuck point, exam deadline, and preferred teaching style so AI helps you learn without directly doing the assignment. AI Interview Practice Pack BuilderCreate a realistic AI interview practice pack from a target role, job description, real experience, skill boundaries, and practice focus, including interviewer prompts, follow-ups, and scoring criteria. AI Decision Memo BuilderTurn AI advice into a structured decision memo with options, decision criteria, assumptions, evidence to verify, risks, rollback conditions, and a small reversible pilot. SWOT Decision WorkbenchBuild and maintain a local-first SWOT project with subject, decision question, timeframe, scenario, quadrant cards, impact/control/urgency labels, and SO/WO/ST/WT action strategies. AI Delegation Brief BuilderCreate a safer task brief before handing work to ChatGPT, Claude, Codex, a coding agent, or another AI assistant, with scope, permissions, checkpoints, acceptance criteria, and ask-first boundaries. AI Subscription Stack PlannerPlan which AI tools are worth paying for by mapping weekly use cases, budget, privacy constraints, trial windows, cancellation rules, and what each subscription must replace. AI Conversation Debrief BuilderTurn one messy AI conversation into reusable lessons: what worked, what failed, what preference to save, and a next prompt patch for future chats. AI Paper Reading Packet BuilderBuild a paper-reading prompt packet from a title, abstract, research goal, and background level, so an AI assistant explains claims, methods, experiments, limitations, and reproduction steps without drifting into a generic summary. AI Translation Style Guide BuilderCreate a bilingual translation style guide for AI assistants with audience, tone, glossary, fixed terms, localization rules, and a two-pass review workflow. AI Flashcard Quiz Pack BuilderTurn study material, concepts, mistakes, and exam goals into a prompt for AI-generated active-recall flashcards, Anki tables, quizzes, and mistake-review prompts. AI Verification Sprint PlannerTurn AI answers or advice into a timeboxed verification sprint with prioritized claims, evidence types, source checks, stop rules, and human-confirmation gates. AI Knowledge Base Note BuilderTurn useful AI conversation lessons into a durable personal knowledge-base note with scope, confidence, review date, privacy boundaries, and a reusable prompt patch. AI Experiment Plan BuilderConvert AI suggestions into a small reversible experiment with one variable, baseline, metric, sample, observation window, stop rule, and rollback plan. AI Personal Writing Voice Brief BuilderCreate a personal writing voice brief for AI assistants from your sample text, audience, purpose, and do-not-say rules, so generated writing sounds less generic and more like you. AI Presentation Outline Brief BuilderTurn a topic, audience, duration, core takeaway, and source material into a slide-outline prompt with narrative spine, slide purposes, visual suggestions, and verification notes. AI Feedback Revision Plan BuilderConvert advisor, client, reviewer, teacher, teammate, or user feedback into a prioritized revision plan with must-fix items, clarification questions, proof of done, and a safe revision prompt. AI Project Instructions BuilderCreate project-level instructions for ChatGPT Projects, Claude Projects, Codex, custom GPTs, or team AI workspaces, with context, preferences, permissions, acceptance criteria, and privacy boundaries. AI Model Migration Brief BuilderMove an AI task from ChatGPT, Claude, Codex, Gemini, Perplexity, or another assistant into a clean continuation brief that preserves only the needed context and safety boundaries. AI Correction Notice BuilderDraft a responsible correction notice when AI-assisted content was wrong, including what happened, who was affected, what was fixed, and how recurrence will be prevented. AI Answer Evidence Pack BuilderTurn an AI answer, source excerpts, and intended use into a traceable evidence pack with claim-to-source mapping, missing-evidence flags, and pre-publish decisions. AI Prompt Diff ExplainerCompare an old prompt and a new prompt, identify changed dimensions such as output format, safety boundaries, evidence rules, tone, and workflow steps, then create a regression test plan. AI Fact-Check Queue BuilderSplit AI claims into a P0/P1/P2 verification queue with preferred source types, suggested search queries, and rules for marking unsupported claims as unverified. AI Follow-up Question Pack BuilderTurn an AI answer into the next questions you should ask before trusting it, including assumptions, missing evidence, time-sensitive claims, execution risks, and privacy reminders. AI Prompt Compression Brief BuilderCompress long prompts, chat summaries, meeting notes, or task context into a smaller continuation brief that preserves goals, constraints, privacy boundaries, and output format. AI Hallucination Stress Test BuilderCreate a stress-test prompt for an AI answer, challenging absolute claims, stale facts, unsupported recommendations, risky actions, privacy exposure, and missing uncertainty. AI Source Request Prompt BuilderTurn unsupported AI answers or drafts into a copyable prompt that asks a browsing AI or human researcher for traceable sources, source dates, access dates, excerpts, and unverified labels. AI Rewrite Drift CheckerCompare original text with an AI rewrite before sending, publishing, or submitting it. Flag missing numbers, added claims, weakened caveats, stronger promises, and privacy risk. AI Uncertainty LabelerAdd practical uncertainty labels to AI claims: supported, partly supported, unverified, needs current source, needs expert or primary source, and downgrade wording. AI Human Review Log BuilderCreate a lightweight human review log for AI-assisted content, including what was checked, what remains uncertain, final decision, ownership note, and residual risk. AI Context Injection CleanerClean and wrap untrusted web pages, GitHub issues, emails, comments, or README excerpts before pasting them into AI. Flag prompt injection, hidden instructions, secret-exfiltration requests, and risky tool commands. AI Source Quality RankerRank sources from AI answers or search results by authority, freshness, traceability, commercial bias, and whether they are strong enough to support important claims. AI Answer Checklist ConverterTurn long AI advice into a practical checklist with actions, proof-of-done, risk notes, and pre-execution checks so users do not blindly follow polished recommendations. AI Answer Contradiction DetectorCheck an AI answer for internal contradictions, opposing advice, certainty flips, and numbers that need separate verification before you act on it. AI Decision Reversal Test BuilderBefore accepting an AI recommendation, create tests for what evidence, cost, user signal, freshness issue, or high-impact risk would reverse or downgrade the decision. AI Scope Creep DetectorCompare your original request with an AI-generated plan and catch added backend work, AI APIs, payments, rewrites, external services, compliance scope, or other unapproved expansions. AI Answer Omission CheckerCompare your original request with an AI answer and find missed questions, weakly covered requirements, ignored constraints, and follow-up prompts to recover the missing parts. AI Assumption Ledger BuilderExtract the explicit and hidden assumptions behind AI advice, classify high-impact premises, and create a ledger of what to verify, ask, or accept before acting. AI Overpromise Risk ScannerScan AI-generated copy or recommendations for guarantees, revenue promises, ranking claims, no-risk wording, professional-advice certainty, and safer rewrite directions. AI Personal Fit CheckerCheck whether an AI answer follows your custom instructions, language preference, tone, format, evidence rules, and project-specific boundaries. AI Context Budget PrioritizerWhen you cannot paste everything into AI, rank context chunks by task relevance, token cost, debugging value, constraints, and privacy risk before sending. AI Advice Safe Mode RewriterRewrite risky AI advice into small, reversible, human-confirmed steps with pre-checks, failure signals, and rollback notes before you execute it. AI User Intent Preservation CheckerCompare an original user request with an AI answer to catch changed goals, ignored language rules, missed format constraints, and added scope before you trust the result. AI Clarifying Question GateDecide whether an AI task should be answered directly or should first ask about context, permissions, risks, success criteria, current information, and forbidden actions. AI Preference Patch BuilderTurn one unsatisfying AI answer, correction, or style complaint into reusable custom-instruction patches for future AI chats and projects. AI Trust Calibration MeterDecide whether an AI answer can be used directly, needs verification, or should not be trusted based on evidence, stakes, high-impact topics, overconfidence, freshness, and privacy signals. AI-to-Human Handoff Brief BuilderWhen AI is stuck, looping, or the risk is too high, turn the problem, AI attempts, failure points, evidence, and open questions into a concise human handoff brief. AI Iteration Stop Rule BuilderSet done criteria, max attempts, repeated-error stop conditions, rollback gates, and human approval points before an AI or agent keeps iterating. AI Multi-Chat Context MergerMerge scattered ChatGPT, Claude, Gemini, Codex, or agent conversations into one continuation pack with goals, constraints, decisions, conflicts, evidence, and next actions. AI Citation Link Sanity CheckerCheck AI-provided URLs, DOIs, markdown links, bare domains, tracking parameters, placeholders, fake-looking citations, and missing access dates before publishing or trusting sources. AI Recurring Failure Pattern DetectorPaste repeated unsatisfying AI answers or corrections and turn them into stable preference rules, banned patterns, and regression prompts for future chats. AI Chat Export CleanerClean long ChatGPT, Claude, Gemini, Codex, or agent chat exports into a portable context pack with decisions, constraints, evidence, failed paths, next actions, and open questions. AI Personal Style DNA BuilderExtract a reusable AI response style protocol from writing samples you like, banned phrases, audience, tone, sentence length, language mix, and evidence preferences. AI Messy Request Prompt CompilerTurn a brain dump, vague request, chat fragment, product idea, or coding task into a structured prompt with goals, inputs, constraints, risks, acceptance criteria, and clarification questions. Prompt Version Test PlannerCompare Prompt A and Prompt B, detect structural changes, and create test cases, scoring rubrics, and a judge prompt before making a new prompt your default. AI Claim & Citation CheckerReview AI answers and drafts for claims, numbers, time-sensitive statements, and source gaps before publishing or citing them. AI Answer Quality CheckerReview AI answers for vague advice, missing steps, unsupported claims, overconfidence, weak verification, and rewrite priorities before publishing or acting on them. AI Answer Compare MatrixCompare two or three AI answers for directness, actionability, evidence, uncertainty, safety, and AI-sounding filler before choosing which one to trust. AI Advice Risk TriagePaste AI advice before acting on it. The tool flags irreversible actions, account changes, commands, high-impact topics, stale facts, and creates a verification checklist. AI Output Action Plan ExtractorTurn AI answers and long recommendations into a concrete action table with owners, proof of completion, risk flags, and a follow-up prompt. AI Prompt Failure DiagnoserDiagnose why an AI answer ignored your request, sounded vague, hallucinated, missed constraints, or used the wrong tone, then copy a repaired prompt. AI Long Context SplitterSplit long transcripts, notes, research excerpts, logs, and chat history into AI-ready packets with per-packet instructions and a final synthesis prompt. AI Fact-check Brief BuilderTurn AI answers, article drafts, and research notes into a fact-check brief with claims, preferred source types, search queries, and a no-hallucination verification prompt. AI Slop CleanerRemove generic AI filler, wrapper phrases, overconfident wording, and mechanical closings from AI-generated text before publishing or sending it. AI Output Publishing Review WorkflowA practical workflow for reviewing AI-generated text before publishing, sending, or adding it to public documentation. AI Safety Redaction StudioCreate a safer, reviewable version of logs, bug reports, prompts, and examples before sharing them with AI assistants, GitHub issues, teammates, or public pages. Website Launch AuditorCheck a website launch checklist for SEO, privacy, AdSense readiness, analytics, navigation, mobile readiness, content depth, and trust signals before promotion. GitHub Repo Trust CheckerAnalyze a public GitHub repository for maintenance, license, README quality, dependency files, tests, scripts, security signals, and common risk patterns before reuse. AI Code Change ReviewerReview AI-generated diffs, code snippets, and change summaries for secrets, injection risk, auth changes, production impact, broad edits, and missing tests. Prompt Injection ScannerScan web text, retrieved snippets, and third-party prompts for common prompt injection and instruction override patterns. Data RedactorReplace sensitive-looking snippets in logs, JSON, URLs, and support text with clear redaction labels or partial masks. Agent Handoff BuilderTurn messy project notes, changed files, commands, blockers, and next steps into a clean handoff pack for another AI agent or future you. AI Chat Continuation PackTurn a long ChatGPT, Claude, Gemini, or Codex conversation into a compact continuation pack for a fresh AI session. AI Personal Instructions BuilderCreate reusable personal instructions for ChatGPT, Claude, Gemini, or Codex from your role, goals, response style, boundaries, and recurring preferences. AI Memory & Custom Instructions AuditAudit AI memory, custom instructions, and saved preferences for oversharing, contradictions, stale details, risky defaults, and privacy exposure. AI Prompt Failure DiagnoserDiagnose why an AI answer ignored your request, sounded vague, hallucinated, missed constraints, or used the wrong tone, then copy a repaired prompt. AI Long Context SplitterSplit long transcripts, notes, research excerpts, logs, and chat history into AI-ready packets with per-packet instructions and a final synthesis prompt. AI Fact-check Brief BuilderTurn AI answers, article drafts, and research notes into a fact-check brief with claims, preferred source types, search queries, and a no-hallucination verification prompt. AI Meeting Notes OrganizerExtract decisions, action items, open questions, risks, dates, and a follow-up prompt from meeting notes or transcript snippets before sharing them with AI or teammates. AI Email Reply CheckerReview email drafts and support replies for tone, clarity, next steps, overpromising, sensitive data, and rewrite priorities before sending. AI Task Brief BuilderTurn vague requests into a structured task brief with goal, context, constraints, inputs, output format, acceptance criteria, and an AI-ready execution prompt. AI Skill BuilderTurn a task description into a reviewed SKILL.md draft, agent prompt, trigger list, boundaries, and pre-install checklist. AI Skill InspectorInspect SKILL.md structure, trigger boundaries, referenced files, and common safety signals before trusting a Skill repository. Prompt & Token ToolkitEstimate prompt tokens, clean long context, and split large text into practical AI-ready chunks. AI Skill Safety Toolkit WorkflowA workflow for reviewing AI Skill repositories before installing, forking, or adapting them. Why Local-First Browser Tools MatterDecide which data belongs in browser-local utilities.