[{"data":1,"prerenderedAt":577},["ShallowReactive",2],{"footer-vacatures-en":3,"use-case-product-goed-opzetten-voor-ai-development-en":4,"content-by-keys-offers-en-vibe-code-kickstart,rescue-sprint":94,"content-by-keys-useCases-en-ai-toevoegen-aan-bestaande-software,ai-prototype-laten-bouwen":358,"content-by-keys-cases-en-":518,"content-by-keys-buyerTriggers-en-ai-laten-bouwen":519},[],{"id":5,"title":6,"body":7,"description":11,"desiredOutcome":14,"extension":26,"hero":27,"key":29,"meta":30,"navigation":31,"path":32,"problem":33,"proof":45,"recognition":57,"recommendedApproach":72,"relations":74,"seo":84,"stem":87,"summary":88,"visuals":89,"__hash__":93},"useCases_en\u002Fuse-cases\u002Fproduct-goed-opzetten-voor-ai-development.md","Set up a product properly for AI so our own team can then continue independently",{"type":8,"value":9,"toc":10},"minimark",[],{"title":11,"searchDepth":12,"depth":12,"links":13},"",2,[],{"intro":15,"items":16},"You want to build as much as possible yourself without early speed later turning into an incomprehensible codebase.\n",[17,20,23],{"title":18,"text":19},"A professional start","Stack, architecture, repository and data model together form a clear foundation.\n",{"title":21,"text":22},"AI gets good guardrails","Tests, conventions and instructions help coding tools stay within the intended structure.\n",{"title":24,"text":25},"The team can carry on itself","Deployment, documentation and way of working are set up for building on independently.\n","md",{"intro":28},"AI coding tools can speed you up enormously, especially when they work in a codebase with clear boundaries and feedback. We lay that foundation. After that you don't need to call us for every feature.\n","product-goed-opzetten-voor-ai-development",{},true,"\u002Fuse-cases\u002Fproduct-goed-opzetten-voor-ai-development",{"intro":34,"causes":35},"AI makes producing code cheap. That makes technical direction, feedback and project structure all the more important.\n",[36,39,42],{"title":37,"text":38},"The AI optimises for the next task","Without a clear architecture, each local solution needn't fit the bigger whole.\n",{"title":40,"text":41},"Errors can multiply quickly","A coding tool easily repeats a bad pattern in several places.\n",{"title":43,"text":44},"A good foundation costs much less later","Fixing auth, deployment and project structure is harder once the product is already large.\n",{"intro":46,"points":47},"This offer is meant to keep you from depending on an agency for the long term. We do the hard senior work properly and then step aside.\n",[48,51,54],{"title":49,"text":50},"Built for AI-assisted development","Structure and feedback help both people and coding agents make better changes.\n",{"title":52,"text":53},"One end-to-end path validated","Besides folders and architecture diagrams, we check that the foundation really works.\n",{"title":55,"text":56},"Handover is part of the product","The end goal is that you can carry on without day-to-day 9to5 capacity.\n",{"intro":58,"signals":59},"This fits when you deliberately want to develop yourself and mainly need senior engineering for the foundation.\n",[60,63,66,69],{"title":61,"text":62},"You want to build with Claude Code, Codex, Cursor, Lovable or Bolt","AI-assisted development becomes an important part of the way you work.\n",{"title":64,"text":65},"The product is more serious than a hobby project","Real users, business data or operational dependencies are coming.\n",{"title":67,"text":68},"You don't want to need a development agency from day one","Your own team should be able to do as much as possible independently.\n",{"title":70,"text":71},"You don't want to need a rescue later","You'd rather get architecture, auth and deployment right up front.\n",{"intro":73},"With the Vibe Code Kickstart we lay the foundation for one product or codebase professionally: architecture, project structure, data, auth, deployment, tests, AI coding guardrails and documentation. After that you build on yourselves.\n",{"buyerTriggerKeys":75,"primaryOfferKey":77,"offerKeys":78,"caseKeys":80,"relatedUseCaseKeys":81},[76],"ai-laten-bouwen","vibe-code-kickstart",[77,79],"rescue-sprint",[],[82,83],"ai-toevoegen-aan-bestaande-software","ai-prototype-laten-bouwen",{"title":85,"description":86},"Set up software properly for AI development | 9to5 software","Building software yourself with Claude Code, Codex, Cursor, Lovable or Bolt? 9to5 sets up architecture, repo, deployment, auth, tests and guardrails professionally.\n","use-cases\u002Fproduct-goed-opzetten-voor-ai-development","You want to build software quickly yourself with AI coding tools, but first lay a professional technical foundation.\n",{"hero":90,"problem":91,"proof":92},"sq-foundation-build","sq-guardrails-check","ls-system-assemble","AByEFSpPcWz-73ln6E45vyp8cZhZVEtQHqnwKbXhtag",[95,233],{"id":96,"title":97,"body":98,"catalogue":102,"cta":112,"description":11,"extension":26,"fit":117,"hero":122,"key":77,"meta":125,"navigation":31,"next":126,"outcome":139,"path":151,"price":152,"process":155,"proof":170,"relations":184,"scope":190,"seo":221,"stem":224,"summary":225,"summaryPanel":226,"visuals":231,"__hash__":232},"offers_en\u002Foffers\u002Fvibe-code-kickstart.md","Vibe Code Kickstart",{"type":8,"value":99,"toc":100},[],{"title":11,"searchDepth":12,"depth":12,"links":101},[],{"audience":103,"promise":104,"deliverables":105,"note":111,"visual":90},"For teams that want to keep building themselves with Claude Code, Codex, Cursor, Lovable, Bolt or similar AI tools.\n","We put the right foundation in place. Then you or your team can keep building independently.\n",[106,107,108,109,110],"Stack, architecture and project structure","Data, authentication and environments where needed","Deployment, logging and error handling","Test strategy and AI coding guardrails","One validated end-to-end flow + handover","A professional foundation. Then you build on it.",{"title":113,"body":114,"primaryCta":115,"local":116},"Building yourself, but starting right?","Tell us what you want to make and how you want to keep building afterwards.\n","Start a Vibe Code Kickstart","From Delft we help teams and entrepreneurs in the region get AI-assisted development off the ground in a technically sound way.\n",{"title":118,"intro":119,"useCaseKeys":120},"When is this offer a fit?","When you want to build yourself with AI tools, but don't want to gamble with the technical foundation.\n",[121,29],"vibe-coding-goed-beginnen",{"headline":123,"intro":124,"primaryCta":115},"We lay the foundation properly. Then you keep building.","AI coding tools make building software more accessible and faster. But the wrong technical foundation gets expensive later. We set up one product or codebase professionally, validate a working end-to-end flow and then hand it over to you.\n",{},{"title":127,"items":128},"What happens next?",[129,132,135],{"title":130,"text":131},"You keep building","That's the usual route. The Kickstart lets you pick up speed on your own afterwards.\n",{"title":133,"text":134,"offerKey":79},"Get stuck on something specific later?","Then a Rescue Sprint can resolve one concrete blocker.\n",{"title":136,"text":137,"offerKey":138},"Has the project gone off the rails technically?","Then a Vibe Code Rescue Audit first restores the overview.\n","vibe-code-rescue-audit",{"title":140,"items":141},"Afterwards you have...",[142,145,148],{"title":143,"text":144},"A professional technical foundation","Architecture, project structure, data, deployment and access are set up deliberately.\n",{"title":146,"text":147},"Guardrails for AI-assisted development","Tests, conventions and project instructions help coding agents work within the right boundaries.\n",{"title":149,"text":150},"A product you can take forward yourself","One end-to-end path works and the key technical choices are documented.\n","\u002Foffers\u002Fvibe-code-kickstart",{"label":153,"type":154},"€4,950 excl. VAT","fixed",{"title":156,"steps":157},"How it works.",[158,161,164,167],{"title":159,"text":160},"Sharpen product + way of working","We determine what you want to build yourself, with which tools and which technical requirements come with it.\n",{"title":162,"text":163},"Lay the foundation","We set up architecture, data, auth, deployment and project structure properly.\n",{"title":165,"text":166},"Add guardrails","We set up tests, conventions and instructions so AI tools make better technical choices.\n",{"title":168,"text":169},"Validate + hand over","We build one end-to-end path, document the foundation and make sure you can continue on your own.\n",{"title":171,"intro":172,"points":173,"caseKeys":183},"Why should you believe this?","We have nothing against vibe coding. With a good engineering foundation you can build much more yourself before you need senior help again.\n",[174,177,180],{"title":175,"text":176},"Senior software engineering as the starting point","The foundation is set up as if the product will actually be used later.\n",{"title":178,"text":179},"Focused on AI-assisted development","The structure helps both people and coding agents understand the codebase.\n",{"title":181,"text":182},"Dependency is not the business model","The Kickstart has succeeded when you can carry on without us.\n",[],{"buyerTriggerKeys":185,"useCaseKeys":187,"relatedOfferKeys":188,"caseKeys":189},[186,76],"starten-met-ai",[121,29],[79,138],[],{"title":191,"intro":192,"activities":193,"deliverables":205,"exclusions":214},"What is included in this offer?","One bounded Kickstart for one product or codebase.\n",{"intro":194,"items":195},"We set up exactly the technical parts that keep speed from turning into chaos later.\n",[196,197,198,199,200,201,202,203,204],"Choosing the stack and architecture","Setting up the repository and project structure","Laying down the base data model","Authentication and authorisation where needed","Environments and deployment structure","Logging and error handling","Test strategy and technical conventions","Guardrails and instructions for AI coding tools","Validating one primary end-to-end flow",{"intro":206,"items":207},"A working technical foundation that is ready for you to build on.\n",[208,209,210,211,212,213],"Set-up codebase and project structure","Working base for deployment and environments","Technical documentation","AI development instructions and conventions","Validated primary flow","Handover explaining the key choices",{"intro":215,"items":216},"We lay the foundation and don't build the complete product within this Kickstart.\n",[217,218,219,220],"Fully worked-out product functionality","Unbounded feature development","Ongoing technical guidance or retainer","Extensive migration of an existing complex codebase",{"title":222,"description":223},"Vibe Code Kickstart | Set up AI coding properly | 9to5 software","Building software yourself with Claude Code, Codex, Cursor, Lovable or Bolt? 9to5 sets up architecture, deployment, auth, data, tests and AI coding guardrails professionally.\n","offers\u002Fvibe-code-kickstart","We set up the technical foundation properly. After that, you or your team keep building independently with Claude Code, Codex, Cursor, Lovable, Bolt or other AI coding tools.\n",{"qualifier":227,"result":228,"duration":229,"nextStep":230},"Fixed price · one product or codebase","A professional technical foundation with one working end-to-end flow","About two weeks","You or your team continue independently with AI coding tools",{"hero":90,"proof":91,"process":92},"e9euJh732-H8mgX6Ag-tYTMatUDDPi69gH_31YmK9Ms",{"id":234,"title":235,"body":236,"catalogue":240,"cta":241,"description":11,"extension":26,"fit":246,"hero":253,"key":79,"meta":256,"navigation":31,"next":257,"outcome":269,"path":280,"price":281,"process":284,"proof":298,"relations":311,"scope":317,"seo":344,"stem":347,"summary":348,"summaryPanel":349,"visuals":354,"__hash__":357},"offers_en\u002Foffers\u002Frescue-sprint.md","Rescue Sprint",{"type":8,"value":237,"toc":238},[],{"title":11,"searchDepth":12,"depth":12,"links":239},[],null,{"title":242,"body":243,"primaryCta":244,"local":245},"Do you know what's broken?","Share the technical problem with us. If it's sharp enough, we don't need to sell you an extra audit first.\n","Plan a Rescue Sprint","Temporary senior engineering from Delft, available for technical AI and software problems in the region.\n",{"title":118,"intro":247,"useCaseKeys":248},"When the technical problem is sharp enough to fix right away.\n",[249,250,251,252],"vast-op-auth-database-of-rechten","ai-koppelen-aan-bestaande-systemen","tests-evals-monitoring-voor-ai","developmentteam-loopt-vast-met-ai",{"headline":254,"intro":255,"primaryCta":244},"One clear technical problem. One week of senior engineering.","You know where the problem is, but your team can't solve it or lacks exactly the specialist experience needed right now. We step in with focus, fix the hard part and make sure you can move forward again afterwards.\n",{},{"title":127,"items":258},[259,262,265],{"title":260,"text":261},"Done? Then we leave.","If you can continue independently, the Sprint has succeeded.\n",{"title":263,"text":264,"offerKey":79},"Another clear rescue goal?","Then you can use a next Sprint as a new fixed scope.\n",{"title":266,"text":267,"offerKey":268},"Turns out bigger than a Sprint?","Then we scope Build & Integrate. If the cause is unclear after all, the Rescue Audit comes first.\n","build-integrate",{"title":140,"items":270},[271,274,277],{"title":272,"text":273},"The concrete problem is tackled","The agreed technical blocker is solved or demonstrably moved forward.\n",{"title":275,"text":276},"The change is set up professionally","Where needed we add tests, evals, guardrails or production preconditions.\n",{"title":278,"text":279},"Your team can move forward again","Code, choices and follow-up are documented and technically handed over.\n","\u002Foffers\u002Frescue-sprint",{"label":282,"suffix":283,"type":154},"€5,950 excl. VAT","per Sprint",{"title":156,"steps":285},[286,289,292,295],{"title":287,"text":288},"Confirm the rescue goal","We check whether the problem is sharp enough for a Sprint.\n",{"title":290,"text":291},"Understand context + code","We read exactly enough to intervene responsibly.\n",{"title":293,"text":294},"Solve + test","We implement the fix and add the quality layer it needs.\n",{"title":296,"text":297},"Document + hand over","We record choices and make sure your team can continue independently again.\n",{"title":171,"intro":299,"points":300,"caseKeys":310},"This is exactly the kind of work senior engineers are valuable for: quickly understanding an unfamiliar codebase, solving the hard part and leaving again.\n",[301,304,307],{"title":302,"text":303},"Senior AI + software engineers","We step in where it gets complicated and leave when it's done.\n",{"title":305,"text":306},"We work in what is already there","We don't expect you to migrate everything to our favourite stack first.\n",{"title":308,"text":309},"Yours as soon as it's done","We document, hand over and leave as soon as you can continue on your own.\n",[],{"buyerTriggerKeys":312,"useCaseKeys":314,"relatedOfferKeys":315,"caseKeys":316},[313],"vastgelopen-met-ai",[249,250,251,252],[138,268],[],{"title":191,"intro":318,"activities":319,"deliverables":328,"exclusions":337},"One Sprint has one clear rescue goal. That boundary keeps it fast and honest.\n",{"intro":320,"items":321},"We do what is technically needed to tackle the agreed problem responsibly.\n",[322,323,324,325,326,327],"Understanding the relevant code and context","Reproducing and confirming the root cause","Implementing a targeted fix or technical improvement","Adding relevant tests, evals or checks","Adjusting integration, deployment or data where the goal requires it","Recording and handing over technical choices",{"intro":329,"items":330},"Working engineering in the existing codebase, not an advice document someone else still has to carry out.\n",[331,332,333,334,335,336],"Implemented technical change","Relevant tests or quality checks","Working code in the agreed environment","Documentation of key choices","Handover to your own team","Clarity about any remaining follow-up",{"intro":338,"items":339},"A Sprint is bounded and doesn't quietly turn into an open-ended project.\n",[340,341,342,343],"Multiple separate rescue goals at once","Unbounded refactor of the whole codebase","Major new product features beyond the rescue goal","Automatic extension or retainer",{"title":345,"description":346},"Rescue Sprint | Senior AI & software engineering | 9to5 software","One week of senior engineering for a technical blocker in AI, an AI agent or vibe-coded software. Repair, test, document and hand over, €5,950 excl. VAT.\n","offers\u002Frescue-sprint","One week of senior engineering focused on one clear technical rescue goal. No retainer and no endless engagement.\n",{"qualifier":350,"result":351,"duration":352,"nextStep":353},"Per Sprint · one clear rescue goal","The agreed technical blocker solved, tested and handed over","One week","You take it over, or another Sprint for a new goal",{"hero":355,"proof":91,"process":356},"sq-tangle-knot","ls-rescue-repair","RBo-3uCvL4DWueBHoZFGrqKFPfwCZ1QLbywOlnLG0NY",[359,440],{"id":360,"title":361,"body":362,"description":11,"desiredOutcome":366,"extension":26,"hero":378,"key":82,"meta":380,"navigation":31,"path":381,"problem":382,"proof":394,"recognition":406,"recommendedApproach":421,"relations":423,"seo":431,"stem":434,"summary":435,"visuals":436,"__hash__":439},"useCases_en\u002Fuse-cases\u002Fai-toevoegen-aan-bestaande-software.md","Add AI to existing software, an app or SaaS",{"type":8,"value":363,"toc":364},[],{"title":11,"searchDepth":12,"depth":12,"links":365},[],{"intro":367,"items":368},"The new AI functionality should feel like part of the product, not like a chatbot glued on later.\n",[369,372,375],{"title":370,"text":371},"AI fits the existing user flow","The feature supports what users are already trying to do.\n",{"title":373,"text":374},"The existing architecture stays manageable","AI is integrated without needlessly adding a second technical world.\n",{"title":376,"text":377},"Production risks are covered","Costs, latency, errors and uncertain model behaviour get a place in the design.\n",{"intro":379},"You don't need to build a completely new AI product. Often most of the value lies in one smart feature inside software users already know. We make sure that feature fits the existing product technically.\n",{},"\u002Fuse-cases\u002Fai-toevoegen-aan-bestaande-software",{"intro":383,"causes":384},"Integrating a standalone AI API is easy. Designing AI as a reliable part of existing product software is another story.\n",[385,388,391],{"title":386,"text":387},"Existing software already has rules","Data, permissions, business logic and user expectations are largely fixed.\n",{"title":389,"text":390},"AI introduces other failure modes","Latency, incorrect output and variable costs have to be handled in existing flows.\n",{"title":392,"text":393},"The new feature can end up too detached","A separate AI system quickly leads to duplicated data and logic.\n",{"intro":395,"points":396},"Understanding and extending existing software is a big part of our work. So AI doesn't need a greenfield to be built well.\n",[397,400,403],{"title":398,"text":399},"Understand the existing architecture first","We design the AI feature around what already works.\n",{"title":401,"text":402},"Integration over isolation","Data, auth and business logic are not duplicated unnecessarily.\n",{"title":404,"text":405},"Production from the design onwards","Reliability and operational consequences count before the feature goes live.\n",{"intro":407,"signals":408},"The problem is usually not how to call a model, but how the new functionality should relate to the existing product.\n",[409,412,415,418],{"title":410,"text":411},"The feature needs existing product data","AI has to work with users, documents or other information already in the product.\n",{"title":413,"text":414},"Permissions must simply keep working","AI must not suddenly expose information or actions that are protected elsewhere.\n",{"title":416,"text":417},"The existing UX should stay in charge","Users want a better workflow, not necessarily a chat interface.\n",{"title":419,"text":420},"You don't want to rebuild the current product","The AI layer has to connect to what already works well technically.\n",{"intro":422},"With Build & Integrate we add the AI functionality to the existing codebase and systems in a targeted way. When the new component is technically risky or still uncertain in substance, an AI Prototype Sprint can first prove the core.\n",{"buyerTriggerKeys":424,"primaryOfferKey":268,"offerKeys":425,"caseKeys":427,"relatedUseCaseKeys":428},[76],[268,426],"ai-prototype-sprint",[],[429,430],"agentic-workflows-bestaande-software","eigen-data-en-kennis-gebruiken-met-ai",{"title":432,"description":433},"Add AI to existing software or SaaS | 9to5 software","Add AI features (ChatGPT, Claude, OpenAI API) to existing software? 9to5 designs, builds and integrates AI into existing apps and SaaS products.\n","use-cases\u002Fai-toevoegen-aan-bestaande-software","The product already exists. Now you want to add AI functionality without losing sight of the existing architecture, user experience and reliability.\n",{"hero":437,"problem":90,"proof":438},"sq-connect-nodes","ls-system-connect","uIjq2lxyg3PeXyGhq82YeTX4j_ALcHznMSqDHe95r9k",{"id":441,"title":442,"body":443,"description":11,"desiredOutcome":447,"extension":26,"hero":459,"key":83,"meta":461,"navigation":31,"path":462,"problem":463,"proof":475,"recognition":487,"recommendedApproach":502,"relations":504,"seo":510,"stem":513,"summary":514,"visuals":515,"__hash__":517},"useCases_en\u002Fuse-cases\u002Fai-prototype-laten-bouwen.md","Build an AI concept or prototype quickly",{"type":8,"value":444,"toc":445},[],{"title":11,"searchDepth":12,"depth":12,"links":446},[],{"intro":448,"items":449},"You don't want slides about what AI could do. You want something that works, so you can make a real technical decision.\n",[450,453,456],{"title":451,"text":452},"A working core flow","The most important user flow works from start to finish.\n",{"title":454,"text":455},"Technical assumptions are tested","You see whether model, data and integrations work together well enough.\n",{"title":457,"text":458},"A clear follow-up decision","After the prototype you know better what production requires and whether building on makes sense.\n",{"intro":460},"Sometimes you know exactly what you want, but not yet whether it will work well enough technically. Then a full production project is too early. We first build the smallest serious prototype that lets you test the key assumptions.\n",{},"\u002Fuse-cases\u002Fai-prototype-laten-bouwen",{"intro":464,"causes":465},"A prototype should remove uncertainty. If it tries to be the full product already, it becomes unnecessarily slow and expensive.\n",[466,469,472],{"title":467,"text":468},"Scope grows easily","As soon as something works, ideas for accounts, dashboards and extra features appear.\n",{"title":470,"text":471},"Production requirements distract from the core question","The first goal is proving that the most important AI assumption works.\n",{"title":473,"text":474},"Technical feasibility is hard to predict on paper","Some model and data questions you simply have to try.\n",{"intro":476,"points":477},"We build a prototype so you can base a technical decision on it. It is as big as it needs to be to test the uncertainty honestly.\n",[478,481,484],{"title":479,"text":480},"Working instead of theoretical","The most important technical assumption is actually implemented.\n",{"title":482,"text":483},"Scope stays deliberately small","No complete product posing as a prototype.\n",{"title":485,"text":486},"The follow-up is a new choice","Even after a successful sprint you are not obliged to continue.\n",{"intro":488,"signals":489},"A prototype helps most when the biggest uncertainty is technical and won't go away with another meeting.\n",[490,493,496,499],{"title":491,"text":492},"The concept is already fairly sharp","You know which user needs to be able to solve which problem.\n",{"title":494,"text":495},"One technical assumption determines a lot","For example answer quality, document interpretation or agent behaviour.\n",{"title":497,"text":498},"Building in full right away feels too early","There is still too much uncertainty for a larger fixed scope.\n",{"title":500,"text":501},"A real demo would settle the discussion","Stakeholders can decide better when they actually see the system working.\n",{"intro":503},"The AI Prototype Sprint is the primary route here: one clear use case, one working end-to-end flow and at most the most important integrations. Afterwards you get not only the prototype but also advice on a possible production version.\n",{"buyerTriggerKeys":505,"primaryOfferKey":426,"offerKeys":506,"caseKeys":507,"relatedUseCaseKeys":508},[76],[426,268],[],[509,82],"ai-agent-laten-bouwen",{"title":511,"description":512},"Have an AI prototype built | 9to5 software","Validate an AI concept quickly with a working prototype? 9to5 builds an end-to-end AI prototype that tests the most important technical assumptions.\n","use-cases\u002Fai-prototype-laten-bouwen","The idea is concrete enough to build, but you first want to show that the most important technical assumption actually works.\n",{"hero":90,"problem":516,"proof":92},"sq-orient-options","2TwZUJkbgDuCmkqkRlk3otdKXvT8Qwxjs8j3pKfpC-M",[],[520],{"id":521,"title":522,"approach":523,"body":538,"cta":542,"description":11,"extension":26,"hero":545,"key":76,"label":547,"meta":548,"navigation":31,"path":549,"proof":550,"relations":562,"seo":570,"stem":573,"summary":574,"visuals":575,"__hash__":576},"buyerTriggers_en\u002Fbuyer-triggers\u002Fai-laten-bouwen.md","We know what we want. Now it needs to be built.",{"title":524,"steps":525},"From a clear scope to something that really works.",[526,529,532,535],{"title":527,"text":528},"Define the scope and success criteria","We make it clear what needs to work, who it is for and when it is good enough to go live.\n",{"title":530,"text":531},"Set up the architecture and integrations","We determine how AI, data, existing software, permissions and integrations should work together technically.\n",{"title":533,"text":534},"Build and test","We implement the difficult part and test more than the happy path, including reliability, errors and human oversight where needed.\n",{"title":536,"text":537},"Bring it into production and hand over","We launch it properly, document the important decisions and make sure your team can carry on independently.\n",{"type":8,"value":539,"toc":540},[],{"title":11,"searchDepth":12,"depth":12,"links":541},[],{"title":543,"body":544},"Know what needs to be built?","Explain what you need and which systems it should work with. We'll quickly tell you how to build it properly and what a logical first step would be.\n",{"intro":546},"You know what needs to be built. We help you build it properly, connect it to your existing systems and get it running reliably in production, using Claude, ChatGPT\u002FOpenAI, Codex or MCP where appropriate. We step in, build, document and hand over, without an open-ended staffing commitment.\n","Build with AI",{},"\u002Fbuyer-triggers\u002Fai-laten-bouwen",{"intro":551,"points":552},"AI is only really useful when it works with existing software, data and business processes. We build that as software engineering, not as a standalone demo.\n",[553,556,559],{"title":554,"text":555},"Integrations are central to our work","We treat APIs, databases, permissions and existing systems as core parts of the solution, not extras around the AI.\n",{"title":557,"text":558},"Reliable beyond the happy path","We also test errors, edge cases and human oversight where needed.\n",{"title":560,"text":561},"Production and handover are part of the job","The work is done when the solution is live, documented and manageable for your team.\n",{"useCaseKeys":563,"offerKeys":568,"caseKeys":569},[509,564,565,82,430,566,83,29,429,567],"interne-ai-assistent-laten-ontwikkelen","bedrijfsproces-automatiseren-met-ai","documenten-en-mails-automatisch-verwerken","tools-vervangen-door-maatwerkflow",[268,426,77],[],{"title":571,"description":572},"AI agent development and integration | 9to5 software","Have senior engineers build an AI agent, MCP integration, assistant or automation with Claude, ChatGPT\u002FOpenAI or Codex. From scope to production.\n","buyer-triggers\u002Fai-laten-bouwen","The problem and direction are clear. Now it needs to be built properly, integrated and brought into production.\n",{"hero":90,"proof":92,"approach":92},"ShT4oNEyuY5KbwbXvOuC2vEuCmku084FYvyfv89UAyM",1792049912342]