AI Blocks › AI help by business › AI and automation businesses
AI and automation businesses: build agents and automations
Build, connect and test agents, chatbots and automations. Everything here is made for AI and automation owners.
- 1Pick a niche and offer
- 2Build agents and automations
- 3Get found
- 4Content and outreach
- 5Demos, proposals and pricing
- 6Set up, test and hand over
- 7Support and retainers
- 8Money, legal and team
Set up AI to work for you
- AI model routing plannerPlan which AI model handles each task in your app, with a spend cap, a backup model and a safe trial before any switch. Bring your setup.
- Agent prompt writerTurn a rough request into a clear AI agent prompt. Answer a few questions and get one prompt to copy, with exact names and paths filled in.
- Automation reliability reviewerReview an automation's triggers, inputs and failure paths. Get a process map, test checklist and recovery guide.
- AI agent team plannerPlan a software build run by a team of AI agents: the phases, who hands what to whom, pass or fail quality checks and when to stop and ask you.
- Multi-agent system architectDesign a team of AI agents that holds up in real use, with each agent's job, limits, failure plan and the points where a person signs off.
- AI agent workflow designerDescribe the job. Get a multi-agent design with handoffs, failure handling and cost limits.
- Prompt change managerSet up prompt versioning, tests and rollback for AI features already live. Get a prompt registry, eval plan and safe deploy steps for your team.
- AI task handover writerWrite a task handoff brief for another AI agent: goal, files it owns, limits and a done check. Plus a plan to track its progress.
- Automation governance plannerDecide if a business process should be automated. Get a verdict, the risks, a safe design with fallback and the tests to pass before go-live.
- Task automation builderTurn a repetitive task into a script, schedule or file watcher. Name the task and its trigger, and get a task automation with tests you can run.
- Routine task automation plannerPlan which repeat chores to automate. List your weekly tasks and get ranked picks, steps a new hire can run, and a small first version.
- Make your me.md and set it up in every AI you useAnswer a few questions or let your AI use what it remembers. Get your me.md and a short version set up in each AI.
- AI app quality reviewerSet useful test cases for an AI app change, plan feedback checks and rank the next fixes from real evidence.
- AI coding agent rules writerSet up an AI coding agent rules file and plan file so your agent works one test at a time and is told not to delete tests to pass.
- AI pilot decision checkerShare your pilot goals, baseline, real results and approval rules. Get checked findings, data gaps and a go-or-stop checklist result.
- AI task handover and risk plannerDescribe a role and its tasks. Get AI task options, hidden human duties, handoff notes and a failure-risk review.
- Prompt version and test plannerShare your prompt, task and examples. Get a clearer draft, test cases, observed comparisons where tools allow and a version record.
- Coding-agent project readiness reviewerShare your project code and needs. Get readiness findings, draft scoring rules and a preview of instructions for coding agents.
- Creative AI prompt writerName a creative task like copy, hooks, ads or a sales page. Get one ready-to-paste AI prompt filled with your facts and clear output rules.
- Multi-agent workflow plannerPlan a multi-agent workflow for a big task. You get a task graph with one owner per step, clear handoffs, approval points and checks.
- Prompt editorTurn a rough request into a clear prompt for any AI. Give it your idea and get a prompt improver result you can paste and use right away.
- Prompt and skill improvement testerTest a prompt or skill against agreed cases. Try one change at a time and keep fixes that avoid regressions.
- AI build-or-buy advisorShare your AI plan and usage for model choices, cost estimates, risk guidance, and hiring advice.
- AI memory routine designerShare your memory tool. Get rules for when AI looks up past work and saves key choices, fixes and lessons.
- AI prompt editorShare your rough prompt. Get a clearer version with the task, facts and requested result stated plainly.
- AI writing workflow plannerDescribe how your team writes. Get what AI should draft, what people own, and rules that keep your voice.
- Ask your AI what it knows about youPaste one prompt. Your AI asks first, then turns what it remembers about you into a me.md for you to check.
- Recurring AI task prompt builderTurn a recurring task or existing loop into a bounded prompt with checks and stop rules.
- AI pilot results reviewerReview actual pilot results against the approved baseline and checklist. Get evidence gaps and a go-or-stop result with the reasons.
- Agent loop designerSay the job you want repeated. Get a bounded AI loop with checks, stop rules and handoffs.
Connect AI to your tools
- n8n workflow reliability plannerDescribe the task and available n8n setup. Get a workflow plan with visible failures, recovery steps and reusable parts.
- AI tool builderDescribe the job your AI needs to do. Get tool definitions, input checks, clear errors and code patterns for connecting the tools.
- n8n AI agent builderShare the job and n8n setup. Choose an agent or simpler node, then build tool, memory and review connections with checks.
- Tool connector builderShare API docs and the tasks your AI needs. Get an MCP server plan, tool definitions, setup steps and tests to run.
- MCP server plannerPlan an MCP server so your AI can use your app or API. Get named tools, typed inputs, error rules and a test plan a developer can build from.
- AI tool definition writerDescribe a tool’s job and limits. Get its name, input schema, side-effect rules and test cases, with unclear or risky parts flagged.
- AI tool set designerDescribe jobs, apps and limits. Get tool definitions with clear names, inputs, results and approval rules.
- MCP tool server builderDescribe the tools and data your AI needs. Build an MCP server with explicit permissions, schemas and verification steps.
- MCP tool set designerPlan your MCP tool set before you code. Give it the jobs your AI must do and get a short list of clear tools with plain descriptions.
- n8n workflow designerDescribe the automation and data flow. Choose an n8n pattern, map nodes and error paths, then prepare build and test steps.
- API to MCP server builderShare an OpenAPI spec. Get tool definitions and starter server code in Python or TypeScript, with checks and next build steps.
- Automation flow sketcherTurn a task you repeat into an automation plan for Zapier or Make. You get each step, filters, and what happens when it fails.
- n8n sub-workflow builderShare a long n8n workflow. Get reusable sub-workflows with clear inputs that your agents can also call.
- MCP server sign-in builderShare your MCP transport and identity setup. Build token checks, discovery and permissions, then test client sign-in.
- n8n failure handlerShare the workflow and failure cases. Add error paths, bounded retries and alert rules, then check response codes and recovery limits.
- Zapier and Make automation plannerDescribe the trigger, apps and result. Compare Zapier and Make patterns, map the steps and plan tests, costs and failure handling.
- Agent tool designerDescribe the agent’s jobs and tool problems. Get clear tool definitions, input and output rules, examples and recovery errors.
- Salesforce architect agentGet a Salesforce architecture plan with a data model, system links, decision records and the platform limits to check before you build.
- BIM and GIS integration plannerPlan how to bring a Revit or IFC model into GIS. Get a coordinate plan, attribute map, checks and an indoor or twin plan.
- Feishu integration plannerPlan a Feishu (Lark) bot, approval flow or data sync. Get the app plan, permission list, event setup and a launch test list.
- API connector builderName the service you need to reach and get working API connector code with sign-in, error handling and safe retries, ready to run.
- Google Ads OAuth setup plannerPlan your Google Cloud project, Ads API access and OAuth client. Get a setup checklist with field names, access limits and what to do next.
- MATLAB Python vision model connectorTurn a Python image model link into a MATLAB demo, with tests only when tools allow.
- Email parsing engineerTurn a messy email thread into who said what, decisions and tasks with owners. Or plan the pipeline that does it for many threads.
- Google Ads developer access checkerPlan a safe read-only test of your Google Ads API access, covering developer token, OAuth login and manager account, with no secret shown.
- MATLAB market data connectorShare your feed, series and dates. Get MATLAB code for Bloomberg, FRED, Haver or LSEG Datastream.
- MATLAB Python integration helperShare the Python library and MATLAB task. Get calls, data conversions and help with the correct Python environment.
- OAuth API access setup helperShare your app, provider and access needs. Get an OAuth flow design, implementation code and checks for tokens, redirects and error paths.
- ChatGPT app starter builderDescribe the app and its tools. It reviews current Apps SDK docs, plans the interaction and drafts a project scaffold for testing.
- Google Workspace command-line operatorRun Gmail, Drive, Sheets and Calendar jobs with the gws command line. Install it, sign in, then send, list, share or audit, with a check before changes.
Build and ship software
- Agent approval workflow builderPlan how an AI agent asks a person to approve an action: risk tiers, expiring requests, checked buttons and an audit log. Draft only.
- Agent task ownership workflow builderPlan a task table where one AI agent claims a task at a time, with expiring claims, blocked tasks and tests. Draft code only.
- AI app and chatbot builderDescribe the chatbot, document question answerer or tool-using agent you want. Get starter code for your AI app in Python with LangChain.
- Slack agent response builderTurn your AI agent's output into a safe Slack message with leak checks, size limits and a plan for each failure, before it posts to a client channel.
- Agent database setup plannerPlan the database your AI agents need. Get a schema map, migration steps, access rules and a staging test plan that keeps existing data safe.
- Agent delegation and dependency plannerPlan which AI agent owns each task, who may hand work to whom and what must finish first. Get a delegation plan and failure test cases.
- Agent prediction log builderGrade your AI agent's past predictions against what happened. Get a score log, a likely cause for each miss and lessons to review. Draft only.
- Agent role loader builderPlan a safer loader for your AI agent's role files, with checked fields, trimming that keeps the rules, clear failures and tests. Draft code only.
- Agent team builderPlan an AI agent team with roles, tasks and shared memory, built with CrewAI. Give it your jobs. You get code and config files to run.
- AI agent monitoring plannerDescribe your agent and failure questions. Get a monitoring plan for steps, latency, costs and errors, with privacy and retention rules.
- AI approval gate designerDescribe what your AI agent does. Get clear rules for which actions need a person to approve and when to escalate.
- Recoverable agent job queue builderPlan an AI agent job queue that survives crashes, with no repeated paid work, capped retries, lost-job recovery and a safe path for failed jobs.
- Scoped base agent builderPlan the smallest working AI agent for your codebase: job format, base class, an echo test handler and a smoke test, with every file named.
- Single-task agent heartbeat builderPlan a safe AI agent run loop: one task per run, no overlapping runs, time and cost limits, and a run record. Draft code only.
- Slack agent message router builderPlan how Slack messages reach the right AI agent, with scope checks, user permissions, bot-loop blocking and logged refusals. Draft code only.
- Small-sample pipeline builderDescribe a data or AI workflow. Get it working end to end on a tiny sample, then scaled with cost checks.
- LLM post-training plannerPlan an SFT, DPO or RL fine-tune of a language model, or find why a run went wrong. Get fair tests, a stop rule and a checkpoint check.
- Agent feedback review system plannerPlan how Slack reactions teach your AI agents. Get a four-way feedback log and lessons drafted for a person to review. Draft code only.
- Agent spending cap builderPlan hard spending caps for your AI agents. Hold cost before each call, stop at the limit and report real spend. Draft code only.
- Guaranteed format generatorSay what shape each answer must take. Get Python code that makes a local AI model return valid JSON, a fixed choice or matching text.
- Multi-agent findings brief builderTurn findings from several AI agents into one daily brief. Merge repeats, rank open issues and plan who handles each. Draft only.
- RAG pipeline implementation plannerPlan a RAG pipeline that finds the right passages in your documents: chunking, search setup and a question set to score each change.
- RAG pipeline designerShare your documents and test questions. Get a RAG design and retrieval scores to guide tuning.
Make your own skills
- AI skill library reviewerReview skill files for unclear triggers, structure gaps and risks. Get a ranked fix list and ideas for useful additions.
- AI skill builderDescribe what your AI should do. Get a skill folder with instructions, reference files and helper scripts.
- AI skill file checkerShare a complete SKILL.md file. Get quoted problems, suggested fixes, risky instructions and checks that passed.
- AI skill writing coachTurn a task you repeat into your own skill. Get a SKILL.md draft, a description that triggers, and a test plan. A skill-making guide for Claude.
- Reusable AI skill writerTurn a job you repeat into a repeat job skill file. Paste the job and get a draft with a trigger line, steps and three test prompts.
- Skill portability checkerShare your skill folder. Get mistakes that stop it loading in other AI tools, with fixes.
- Skill writer and reviewerWrite an AI skill from a job description, or review one you have. Get a clear trigger line, safety notes and a cleaner SKILL.md.
- Repeated work skill finderShare your screen history. Get tasks you repeat and draft skills to automate them.
- Prompt engineerDescribe the task and the answer format you need. Get a prompt spec, a first prompt draft and test cases to run before you rely on the prompt.
- AI instruction writerShare a skill or AI instruction file. Get clearer steps, reference links and completion checks, with repeated or stale rules trimmed.
- Agent procedure writerDescribe a repeatable job. Get a reusable procedure file with inputs, numbered steps, clear requirements and format checks.
- Book and document skill builderShare a book or document folder. Get agent instructions, chapter notes and a quick guide built from the source, with checks.
- Skill safety checkerShare a skill or bundle before you add it. Get risky code, data leaks and hidden payloads.
- Workflow spec interviewerShare the workflows you want to build. It asks focused questions and writes a clear spec for each one.
- Pattern to skill extractorTurn a fix you keep repeating into a reusable skill. Describe the pattern and get a skill folder with steps, notes and examples.
- Project skill finderFind the skills your project needs. Give it your project folder and get a ranked list of skills to add or update, based on how you really work.
- Skill file validatorShare a SKILL.md. Get structure, wording and naming problems to fix before you share it.
- Skill quality testerGive it a skill folder. Get structure and script checks, a quality score and a ranked fix list.
- Skill trigger auditorShare your skills. Get a grade for each on when it fires, and which skills block each other.
- Skill writerDescribe a job. Get draft skill instructions, test prompts and a trigger description to review.
Keep your code secure
- AI agent launch security reviewerShare agent code, design, tools and packages. Get permission, OWASP and dependency findings with an evidence check and ranked fixes.
- Agent injection evidence review assistantGet safe prompt injection test cases for your AI agent, a control gap list and retest records. Tests run only with the owner's written approval.
- GitHub AI workflow security checkerShare GitHub workflow files for a security report tracing outside text to AI agent steps.
- AI agent identity designerDesign how your AI agents prove who they are, what they may do and what they did, with a threat list, permission map and tamper-proof log.
- AI agent attack testerShare the agent and authorised test scope. Get a test plan, evidence-backed findings and retest results for checks that actually run.
- MCP server release reviewerShare the MCP server, settings and test access. Get code and permission findings, actual protocol-test results and a clear release-blocker list.
- AI spend limit checkerCheck code that calls paid AI services for spend limits. Get a cost cap on every call, a hard count on every loop and retry, and a list of caps to set.
- MCP attack risk reviewerShare your MCP server design or code. Find attack paths and plan or implement controls with clear evidence gaps.
- MCP package version checkerRead MCP configs without starting servers. Find npm package references that may resolve to different code after review.
- MCP server security reviewerReview your MCP server’s connections, sign-in, permissions and logs. Get control gaps, configuration examples and checks to run.
- Skill safety reviewerPoint it at a skill, MCP server or add-on. Get a read-only safety review before you install it.
Test and fix code
- Agent run evidence auditorShare logs from an AI agent run. Get each success claim checked against real proof, with gaps marked.
- AI agent release testerShare your agent, baseline and release rules. Get test cases, scoring rules, failure reports and a release memo tied to observed results.
- AI agent test framework designerDescribe your agent and success rules. Get a test framework with varied cases, scoring guides, a baseline and checks for regressions.
- MCP server test runnerTest your MCP server with real tasks and see if an AI picks the right tool. You get a scored report and fixes to try.
- Playwright browser automation scripterDescribe a browser task. Get a custom Playwright script and, when its browser setup is ready, run results and screenshots.
Design things people love
- AI assistant interface style guide writerDescribe your AI product. Get a style guide for a chat-first screen with few controls and clear outcomes.
Build a product people want
- Chatbot flow plannerDescribe your chatbot job. Get conversation flows with questions, error recovery and graceful fallbacks.
Ship and host your app
- MCP server publisherShare your server and release target. Deploy or package it with rollout checks, install instructions and version notes.
Specialists made for this stage
A specialist is a ready-made role for your AI, with its own methods and checks.
- AI model routing plannerPlan which AI model handles each task in your app, with a spend cap, a backup model and a safe trial before any switch. Bring your setup.
- Agent injection evidence review assistantGet safe prompt injection test cases for your AI agent, a control gap list and retest records. Tests run only with the owner's written approval.
- Multi-agent system architectDescribe the job you want a team of AI agents to do and the tools and data they could touch. You get a design to review before anyone builds it.
- AI identity designerDescribe the AI agents in your system and what each one can do. You get a design to review with a security engineer, not a live system.
- Automation reliability reviewerReview an automation's triggers, inputs and failure paths. Get a process map, test checklist and recovery guide.
- MCP server plannerPlan an MCP server so your AI can use your app or API. Get named tools, typed inputs, error rules and a test plan a developer can build from.
- n8n workflow reliability plannerGive it a plain description of the task: what starts it, what it reads, what it should do. You get an n8n workflow laid out step by step, with the right pattern.
- AI skill library reviewerReview skill files for unclear triggers, structure gaps and risks. Get a ranked fix list and ideas for useful additions.
- Automation governance plannerDecide if a business process should be automated. Get a verdict, the risks, a safe design with fallback and the tests to pass before go-live.
- LLM post-training plannerPlan an SFT, DPO or RL fine-tune of a language model, or find why a run went wrong. Get fair tests, a stop rule and a checkpoint check.
- MCP server release reviewerGive it your MCP server code. You get code and settings findings.
- RAG pipeline implementation plannerDescribe your documents and the questions people ask. You get a build plan and a score sheet.
- Prompt engineerDescribe the task and the answer format you need. Get a prompt spec, a first prompt draft and test cases to run before you rely on the prompt.
- AI app quality reviewerSet useful test cases for an AI app change, plan feedback checks and rank the next fixes from real evidence.
- AI pilot decision checkerShare your pilot goals, baseline, real results and approval rules. Get checked findings, data gaps and a go-or-stop checklist result.
- AI task handover and risk plannerDescribe a role and its tasks. Get AI task options, hidden human duties, handoff notes and a failure-risk review.
- me.md setup guideAnswer a few questions or let your AI use what it remembers. Get your me.md and a short version set up in each AI.
- Prompt and skill improvement testerTest a prompt or skill against agreed cases. Try one change at a time and keep fixes that avoid regressions.
- Prompt version and test plannerShare your prompt, task and examples. Get a clearer draft, test cases, observed comparisons where tools allow and a version record.
- AI pilot results reviewerShare the pilot goal, approved baseline, real cases and results, budget and decision checklist. You get an evidence brief, gaps and a go-or-stop result.
- AI team plannerGive it a written project spec. You get the phases, the handoffs, the pass or fail gates and the retry limits.
- BIM and GIS integration plannerPlan how to bring a Revit or IFC model into GIS. Get a coordinate plan, attribute map, checks and an indoor or twin plan.
- Coding-agent project readiness reviewerShare your project code and needs. Get readiness findings, draft scoring rules and a preview of instructions for coding agents.
- Feishu integration plannerPlan a Feishu (Lark) bot, approval flow or data sync. Get the app plan, permission list, event setup and a launch test list.
- Campaign copy writerGet campaign copy checked against your approved claims. Every claim is tied to its proof, gaps are flagged and a checkpoint is saved.
- Creative evidence reviewerCheck ad creative against your brief and product facts. Get ranked issues, a pass or fix call per check and a checkpoint.
- Email parsing engineerTurn a messy email thread into who said what, decisions and tasks with owners. Or plan the pipeline that does it for many threads.
- Google Ads results reviewerReview your Google Ads results against your targets. Get ranked findings, tracking gaps, proposed changes and a checkpoint for your next review.
- Meta Ads results reviewerReview your Meta Ads results against your targets. Get ranked findings, tracking gaps, proposed fixes and a checkpoint for the next review.
- Salesforce architectDescribe your Salesforce setup, your problem and the systems that must connect to it. You get decision records and a list of limits to check.
- Specialist findings coordinatorCombine findings from several specialists into one decision brief. Settle clashes, rank next steps and get a checkpoint with owners.
Also useful to any business
- API security repair reviewerReview API sign-in, access and input checks, make fixes and review the tests and change risk before writing the pull request.
- API service and test builderShare the service spec, code environment and limits. Get a starter project, service code, route tests and API docs, with actual run results.
- Qdrant model migration and search-test plannerShare your current search setup, new model and query examples. Get a migration plan, relevance checks, monitoring and rollback gates.
- System model estimatorFit a system model from your input and output data. Get a MATLAB model, fit scores on held-out data, and a side-by-side check of model types.
- AI feature plannerGet a plan to add an AI feature to your product, from data check to launch, with bias tests, monitoring and a retraining trigger.
- AI-written code security reviewerPaste AI-written app code. Get a ranked list of leaked keys, open database rules and prompt injection holes, each with the fix and a rescan list.
- API platform engineer agentGet a plan for a public or partner API with contract rules, a breaking-change list, a versioning policy, rate limits and an SDK plan.
- Backend architect agentGet a backend design with a right-sized setup, data tables, an API outline, a failure plan and a safe way to change the database.
- Spatial data engineer agentPlan a pipeline that turns messy map data into clean, standard files, with coordinate fixes, field rules, quality checks and a repeatable run.
- Agent AI cost tracker builderPlan a wrapper for your agent's AI calls that checks the budget first, then records tokens and cost on every call, so spend is never a surprise.
- AI app instruction and spending safeguardsShare your app code and test setup. Get proposed code safeguards, test gaps, spending limits and an attack-test report where checks can run.
- AI data extractor builderSay what data to pull from AI answers. Get code that returns checked, typed results instead of free text.