[{"data":1,"prerenderedAt":590},["ShallowReactive",2],{"footer-vacatures-en":3,"use-case-tools-vervangen-door-maatwerkflow-en":4,"content-by-keys-offers-en-build-integrate,ai-reality-check":94,"content-by-keys-useCases-en-bedrijfsproces-automatiseren-met-ai,agentic-workflows-bestaande-software":378,"content-by-keys-cases-en-":532,"content-by-keys-buyerTriggers-en-ai-laten-bouwen":533},[],{"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\u002Ftools-vervangen-door-maatwerkflow.md","Replace several existing tools with one smart custom workflow",{"type":8,"value":9,"toc":10},"minimark",[],{"title":11,"searchDepth":12,"depth":12,"links":13},"",2,[],{"intro":15,"items":16},"You want to simplify the process without blindly rebuilding all existing systems.\n",[17,20,23],{"title":18,"text":19},"One clear workflow","Users no longer have to stitch different tools and intermediate steps together themselves.\n",{"title":21,"text":22},"Automation where it helps","Manual copying, checking and routing is removed as much as possible.\n",{"title":24,"text":25},"Keep what works well","Systems that add value can stay part of the new flow through integrations.\n","md",{"intro":28},"Sometimes the problem isn't too little software, but too much. Employees jump between tools, copy information and keep track of how it all fits together themselves. Then one targeted custom workflow can be simpler than yet another SaaS subscription.\n","tools-vervangen-door-maatwerkflow",{},true,"\u002Fuse-cases\u002Ftools-vervangen-door-maatwerkflow",{"intro":34,"causes":35},"Separate tools each optimise their own part of the process. As a result, the complexity often arises precisely between those tools.\n",[36,39,42],{"title":37,"text":38},"Integration is missing","Data and status have to be moved by hand from one system to another.\n",{"title":40,"text":41},"The process has adapted to the software","Employees follow extra steps because separate tools don't fit together well.\n",{"title":43,"text":44},"Otherwise AI becomes yet another tool","A standalone chatbot on top of the existing pile doesn't reduce fragmentation.\n",{"intro":46,"points":47},"We don't replace standard SaaS with custom software by default. Because we both build software and connect systems, we can choose per part what is technically and commercially wise.\n",[48,51,54],{"title":49,"text":50},"Build and integrate","A good existing system doesn't need to be rebuilt.\n",{"title":52,"text":53},"The process leads","The new flow is designed around how the work ideally runs.\n",{"title":55,"text":56},"AI only where it fits","Smart interpretation is combined with regular automation and integrations.\n",{"intro":58,"signals":59},"This question often arises after a process has been extended bit by bit with new tools over the years.\n",[60,63,66,69],{"title":61,"text":62},"Employees work in many systems for one task","The process keeps jumping between SaaS tools, spreadsheets, email and internal software.\n",{"title":64,"text":65},"Information is entered twice","The same data is kept or copied in several places.\n",{"title":67,"text":68},"Nobody has an overview of the whole flow","Each tool solves one part, but the employee manually keeps it all together.\n",{"title":70,"text":71},"Another new tool doesn't feel like the solution","The pile of software has by now become part of the problem itself.\n",{"intro":73},"With Build & Integrate we design and build the custom workflow around the actual process. We only replace what makes sense and connect the systems that are better kept. If scope and process are still not sharp enough, an AI Reality Check is the more logical first step.\n",{"buyerTriggerKeys":75,"primaryOfferKey":77,"offerKeys":78,"caseKeys":80,"relatedUseCaseKeys":81},[76],"ai-laten-bouwen","build-integrate",[77,79],"ai-reality-check",[],[82,83],"bedrijfsproces-automatiseren-met-ai","agentic-workflows-bestaande-software",{"title":85,"description":86},"Replace existing tools with a smart custom workflow | 9to5 software","Too many separate tools for one business process? 9to5 builds integrated custom workflows with automation, AI and connections to what should stay.\n","use-cases\u002Ftools-vervangen-door-maatwerkflow","The process has become fragmented across several tools, spreadsheets and manual handoffs. You want to bring it back to one coherent workflow.\n",{"hero":90,"problem":91,"proof":92},"sq-process-steps","sq-connect-nodes","ls-workflow-flow","mgSW-1h2BBXZlMWEViIVrX1-qaoPuBUr_YQ6D9XnX9A",[95,240],{"id":96,"title":97,"body":98,"catalogue":102,"cta":113,"description":11,"extension":26,"fit":118,"hero":125,"key":77,"meta":128,"navigation":31,"next":129,"outcome":142,"path":154,"price":155,"process":158,"proof":173,"relations":187,"scope":197,"seo":227,"stem":230,"summary":231,"summaryPanel":232,"visuals":237,"__hash__":239},"offers_en\u002Foffers\u002Fbuild-integrate.md","Build & Integrate",{"type":8,"value":99,"toc":100},[],{"title":11,"searchDepth":12,"depth":12,"links":101},[],{"audience":103,"promise":104,"deliverables":105,"note":111,"visual":112},"For organisations that know what needs to be built and want 9to5 to build and integrate it professionally.\n","Not an AI demo, but something that works with your real software, data, processes and people.\n",[106,107,108,109,110],"Architecture and production-ready implementation","Integrations with existing software and data","Permissions, error handling and human oversight","Tests, monitoring and deployment where relevant","Documentation and handover to your team","We define the scope together first, then agree a fixed price for the result.\n","ls-system-connect",{"title":114,"body":115,"primaryCta":116,"local":117},"Do you know what needs to be built?","Share the desired outcome and your existing technical context with us. If the scope is clear, we turn it into a fixed engagement.\n","Discuss what you need built","AI engineering and software implementation from Delft, for organisations in Delft, The Hague, Rotterdam and the surrounding area.\n",{"title":119,"intro":120,"useCaseKeys":121},"When is this offer a fit?","When the desired outcome is clear enough to scope a professional implementation.\n",[122,123,82,124],"ai-agent-laten-bouwen","interne-ai-assistent-laten-ontwikkelen","ai-toevoegen-aan-bestaande-software",{"headline":126,"intro":127,"primaryCta":116},"Not an AI demo, but something that works with your real software, data and people.","The problem and the desired direction are clear. Now it has to be built properly. We take on architecture, AI, integrations and production-grade engineering as one whole and hand it back over afterwards.\n",{},{"title":130,"items":131},"What happens next?",[132,135,138],{"title":133,"text":134},"You take it over","That is what we work towards. We don't want you to keep needing us.\n",{"title":136,"text":137},"A new bounded question comes up later","Then we scope it again instead of automatically keeping capacity running.\n",{"title":139,"text":140,"offerKey":141},"Still too much technical uncertainty?","Then an AI Prototype Sprint or Reality Check before Build & Integrate may be wiser.\n","ai-prototype-sprint",{"title":143,"items":144},"Afterwards you have...",[145,148,151],{"title":146,"text":147},"Working software instead of a demo","The agreed functionality works end to end within the real technical environment.\n",{"title":149,"text":150},"Reliable integration with what is already there","Data, systems, permissions and human processes are part of the solution.\n",{"title":152,"text":153},"A product you can hand over","Architecture, code and key choices are documented well enough to continue independently.\n","\u002Foffers\u002Fbuild-integrate",{"label":156,"type":157},"Fixed price after scoping","scoped",{"title":159,"steps":160},"How it works.",[161,164,167,170],{"title":162,"text":163},"Scope + success criteria","We make exact enough what needs to work to agree on responsibility and price.\n",{"title":165,"text":166},"Architecture + integrations","We determine how AI, data, existing software, permissions and users come together.\n",{"title":168,"text":169},"Build + test","We implement the hard part and also test errors, edge cases and reliability.\n",{"title":171,"text":172},"Go live + hand over","We bring the solution to production in a controlled way, document it and hand it over.\n",{"title":174,"intro":175,"points":176,"caseKeys":186},"Why should you believe this?","AI only becomes truly valuable when it works together with existing software, data and business processes. That is simply serious software engineering.\n",[177,180,183],{"title":178,"text":179},"The same people advise and build","Advice and execution sit with the same technical people.\n",{"title":181,"text":182},"Integrations are core work","We don't treat APIs, databases, auth and existing systems as an afterthought around the AI.\n",{"title":184,"text":185},"Production and handover are part of it","The work isn't done when the demo works, but when the solution is manageable.\n",[],{"buyerTriggerKeys":188,"useCaseKeys":190,"relatedOfferKeys":193,"caseKeys":196},[76,189],"vastgelopen-met-ai",[122,123,82,124,191,192,83,29],"eigen-data-en-kennis-gebruiken-met-ai","documenten-en-mails-automatisch-verwerken",[79,141,194,195],"vibe-code-rescue-audit","rescue-sprint",[],{"title":198,"intro":199,"activities":200,"deliverables":211,"exclusions":220},"What is included in this offer?","The scope is defined up front. Then you get a fixed price for the agreed result.\n",{"intro":201,"items":202},"The exact work differs per engagement, but we take responsibility for the complete technical result.\n",[203,204,205,206,207,208,209,210],"Making scope and success criteria concrete","Designing the architecture","Implementing AI functionality or an agent flow","Building integrations with existing software and data","Setting up authentication, authorisation and data flows properly","Tests, evals, monitoring and error handling where relevant","Deployment and production setup","Documentation and technical handover",{"intro":212,"items":213},"The deliverables are defined per scope and are part of the fixed price.\n",[214,215,216,217,218,219],"Working agreed functionality","Production-grade implementation","Required integrations","Relevant tests and quality checks","Technical documentation","Deployment and handover as scoped",{"intro":221,"items":222},"No unbounded consultancy and no feature list that keeps growing afterwards.\n",[223,224,225,226],"Functionality outside the agreed scope","Ongoing retainer as a standard component","External model, API and hosting costs","Additional work without a new explicit scope and price",{"title":228,"description":229},"Have AI built and integrated | Build & Integrate | 9to5 software","Have an AI agent, internal tool, MCP integration or AI feature built with Claude or ChatGPT\u002FOpenAI and professionally integrated with your software, data and processes.\n","offers\u002Fbuild-integrate","You know what needs to be built. We build it professionally, connect it to your existing software and make sure it can be handed over production-ready.\n",{"qualifier":233,"result":234,"duration":235,"nextStep":236},"Fixed price after joint scoping","Working, integrated software your team can take over","Set in the scope","Handover to your team, or further development together",{"hero":91,"proof":238,"process":112},"sq-foundation-build","jlXsSL_a-hghGaOxvEHbZ2ARDUkoaAlfXaEkKLzQpSQ",{"id":241,"title":242,"body":243,"catalogue":247,"cta":258,"description":11,"extension":26,"fit":263,"hero":270,"key":79,"meta":273,"navigation":31,"next":274,"outcome":286,"path":297,"price":298,"process":301,"proof":315,"relations":328,"scope":337,"seo":364,"stem":367,"summary":368,"summaryPanel":369,"visuals":374,"__hash__":377},"offers_en\u002Foffers\u002Fai-reality-check.md","AI Reality Check",{"type":8,"value":244,"toc":245},[],{"title":11,"searchDepth":12,"depth":12,"links":246},[],{"audience":248,"promise":249,"deliverables":250,"note":256,"visual":257},"For organisations that first want to know what's technically sound and feasible.\n","In one compact engagement, you'll learn what to do, what to avoid and what's needed technically.\n",[251,252,253,254,255],"Technical feasibility and key risks","Build \u002F buy \u002F don't build","Recommended technical approach","What AI should and shouldn't do","A concrete next step","Decision document + discussion with a senior engineer.","sq-orient-options",{"title":259,"body":260,"primaryCta":261,"local":262},"Want to know what is wise first?","Share your AI question with us. If a Reality Check isn't needed, we'll tell you.\n","Book an AI Reality Check","Senior AI and software engineering from Delft, for organisations in Delft, The Hague, Rotterdam and the surrounding area.\n",{"title":119,"intro":264,"useCaseKeys":265},"When the main question is not yet how to build something, but what you should be building in the first place.\n",[266,267,268,269],"processen-automatiseren-met-ai","interne-ai-assistent-met-eigen-kennis","ai-idee-technisch-haalbaar","is-ai-nodig",{"headline":271,"intro":272,"primaryCta":261},"Know what to do with AI before you start building.","You see opportunities for AI, but first want to know what is wise. We examine one concrete process or up to three ideas and give you a well-founded technical direction. Even if the conclusion is that you are better off without AI.\n",{},{"title":130,"items":275},[276,279,283],{"title":277,"text":278,"offerKey":141},"Prove that it works first?","Then an AI Prototype Sprint is often the logical next step.\n",{"title":280,"text":281,"offerKey":282},"Keep building yourself?","Then a Vibe Code Kickstart lets us set up the technical foundation properly.\n","vibe-code-kickstart",{"title":284,"text":285,"offerKey":77},"Scope already clear enough?","Then we can go straight to Build & Integrate.\n",{"title":143,"items":287},[288,291,294],{"title":289,"text":290},"A clear technical direction","You know which approach is promising and which options you are better off leaving alone.\n",{"title":292,"text":293},"The main uncertainties on the table","Integrations, data, reliability, risks and human oversight are made concrete enough to make a decision.\n",{"title":295,"text":296},"A logical next step","You know whether to build, buy, integrate, validate something first or stop.\n","\u002Foffers\u002Fai-reality-check",{"label":299,"type":300},"€1,950 excl. VAT","fixed",{"title":159,"steps":302},[303,306,309,312],{"title":304,"text":305},"Sharpen the question","We determine which decision you need to make and what a good result would be.\n",{"title":307,"text":308},"Understand the technical context","We look at processes, data, existing software, integrations and preconditions.\n",{"title":310,"text":311},"Test the options","We compare realistic routes on feasibility, risk and technical complexity.\n",{"title":313,"text":314},"Deliver decision + route","You get our conclusion, technical direction and a concrete next step.\n",{"title":174,"intro":316,"points":317,"caseKeys":327},"We don't advise from a fixed preference for AI or custom software. Because we build software ourselves, we can judge when building is wise and when it is not.\n",[318,321,324],{"title":319,"text":320},"Engineers look at the real system","We look at the AI idea and also at data, integrations, software and operations.\n",{"title":322,"text":323},"AI isn't always the answer","Plain automation, existing software or building nothing are real alternatives.\n",{"title":325,"text":326},"We can carry out the follow-up too","If building turns out to make sense, the advice doesn't have to go to another technical party first.\n",[],{"buyerTriggerKeys":329,"useCaseKeys":331,"relatedOfferKeys":335,"caseKeys":336},[330],"starten-met-ai",[266,267,268,269,332,333,334],"ai-betrouwbaar-genoeg","zelf-bouwen-of-software-kopen","ai-toevoegen-aan-bestaand-product",[141,282,77],[],{"title":198,"intro":338,"activities":339,"deliverables":348,"exclusions":357},"A bounded technical investigation with a concrete decision as the result.\n",{"intro":340,"items":341},"A senior engineer examines the actual question and the context around it.\n",[342,343,344,345,346,347],"Intake and sharpening the problem","Examining one concrete process or up to three AI ideas","Assessing feasibility, dependencies, integrations and risks","Comparing build, buy, integrate or not building","Determining where AI does and does not make sense","Taking human oversight and key preconditions into account",{"intro":349,"items":350},"Not a generic AI report, but a compact decision document that lets you move forward.\n",[253,351,352,353,354,355,356],"What AI should and should not do","Rough solution direction and relevant integrations","Main risks and assumptions","Build \u002F buy \u002F don't build advice","Indication of size and the next step","Review session with a senior engineer",{"intro":358,"items":359},"The Reality Check is meant to make a decision, not to build the whole system already.\n",[360,361,362,363],"Production-ready implementation","Fully worked-out UX or product design","Extensive organisation-wide AI strategy","Unbounded research into multiple processes or business units",{"title":365,"description":366},"AI Reality Check | Technical feasibility of AI | 9to5 software","A senior AI and software engineer assesses what is feasible and worthwhile: an AI agent, Claude, ChatGPT or conventional software? With an approach, risks and next step.\n","offers\u002Fai-reality-check","In a compact engagement we determine what is technically sensible and feasible, where the risks are and what a wise next step is.\n",{"qualifier":370,"result":371,"duration":372,"nextStep":373},"Fixed price · one process or up to three AI ideas","A reasoned technical direction and build \u002F buy \u002F don't build advice","About two weeks","Build, validate with a prototype first, or deliberately stop",{"hero":257,"proof":375,"process":376},"sq-guardrails-check","ls-route-converge","yAAdWR1HeTz_g1hVnQ1w2rPY4-tRkksM8Ro6yjOmeok",[379,455],{"id":380,"title":381,"body":382,"description":11,"desiredOutcome":386,"extension":26,"hero":398,"key":82,"meta":400,"navigation":31,"path":401,"problem":402,"proof":414,"recognition":426,"recommendedApproach":441,"relations":443,"seo":448,"stem":451,"summary":452,"visuals":453,"__hash__":454},"useCases_en\u002Fuse-cases\u002Fbedrijfsproces-automatiseren-met-ai.md","Automate a business process with AI",{"type":8,"value":383,"toc":384},[],{"title":11,"searchDepth":12,"depth":12,"links":385},[],{"intro":387,"items":388},"You don't want as much AI as possible. You want less manual work, fewer errors and a process that stays technically manageable.\n",[389,392,395],{"title":390,"text":391},"Less repetitive work","Predictable or time-consuming steps are carried out automatically.\n",{"title":393,"text":394},"AI only where it adds something","Interpretation and unstructured information go to AI; fixed rules stay regular software.\n",{"title":396,"text":397},"People stay in control","Critical exceptions or decisions can deliberately stay with an employee.\n",{"intro":399},"Not every process gets better with a fully autonomous agent. Sometimes the best solution is regular automation with one smart AI step in between. We build the workflow that fits the process.\n",{},"\u002Fuse-cases\u002Fbedrijfsproces-automatiseren-met-ai",{"intro":403,"causes":404},"AI automation works best when you first technically split the process into deterministic and non-deterministic steps.\n",[405,408,411],{"title":406,"text":407},"Not every step needs AI","Using a language model for fixed rules makes processes more expensive and less predictable.\n",{"title":409,"text":410},"Exceptions determine reliability","The system has to know when continuing automatically is not wise.\n",{"title":412,"text":413},"Integrations are part of the process","The workflow has to be able to read and write in the systems employees already use today.\n",{"intro":415,"points":416},"For us AI is one tool within software automation. So we don't make a process artificially agentic when a simpler design is more reliable.\n",[417,420,423],{"title":418,"text":419},"Process before technology","The desired outcome determines which steps need AI.\n",{"title":421,"text":422},"Existing systems stay usable","Integrations prevent an automation from becoming yet another standalone system.\n",{"title":424,"text":425},"Human oversight is part of the design","We explicitly design where exceptions should go to an employee.\n",{"intro":427,"signals":428},"Processes with a lot of copying, checking, interpreting and passing on are a good fit.\n",[429,432,435,438],{"title":430,"text":431},"People move information between systems","A large part of the work consists of reading, retyping or classifying.\n",{"title":433,"text":434},"The same decision rules keep coming back","A workflow usually follows a fixed pattern with a limited number of exceptions.\n",{"title":436,"text":437},"Unstructured information blocks classic automation","Emails, documents or free text first have to be interpreted.\n",{"title":439,"text":440},"Existing software has to stay part of it","You don't want to replace all current systems to make one process smarter.\n",{"intro":442},"With Build & Integrate we design and build the complete workflow around the existing process. If there is technical uncertainty about a crucial AI step, we can validate it first in an AI Prototype Sprint.\n",{"buyerTriggerKeys":444,"primaryOfferKey":77,"offerKeys":445,"caseKeys":446,"relatedUseCaseKeys":447},[76],[77,141],[],[192,29],{"title":449,"description":450},"Automate a business process with AI | 9to5 software","Automating a business process with AI? 9to5 builds workflows that practically combine AI, existing software, data and human oversight.\n","use-cases\u002Fbedrijfsproces-automatiseren-met-ai","The process is clear and contains work that could be smarter or largely automatic. Now it has to become a reliable technical workflow.\n",{"hero":90,"problem":375,"proof":92},"-G_t_-Jsnlyir8qFMNtC3gxskycjna1O6PRo9qtkdak",{"id":456,"title":457,"body":458,"description":11,"desiredOutcome":462,"extension":26,"hero":474,"key":83,"meta":476,"navigation":31,"path":477,"problem":478,"proof":490,"recognition":502,"recommendedApproach":517,"relations":519,"seo":524,"stem":527,"summary":528,"visuals":529,"__hash__":531},"useCases_en\u002Fuse-cases\u002Fagentic-workflows-bestaande-software.md","Extend existing software with agentic workflows",{"type":8,"value":459,"toc":460},[],{"title":11,"searchDepth":12,"depth":12,"links":461},[],{"intro":463,"items":464},"You want to make an existing workflow smarter without redesigning the rest of the product.\n",[465,468,471],{"title":466,"text":467},"Handle more work automatically","Within clear boundaries, the workflow can gather information and take actions itself.\n",{"title":469,"text":470},"Existing software stays in charge","The agent uses current data, APIs, auth and business logic.\n",{"title":472,"text":473},"Autonomy stays controllable","Critical steps can be validated or put in front of a user.\n",{"intro":475},"Not every product needs to become an AI-first product. Sometimes a single agentic workflow is exactly enough: an existing process in which software independently performs a few smart steps before a user takes over again.\n",{},"\u002Fuse-cases\u002Fagentic-workflows-bestaande-software",{"intro":479,"causes":480},"Adding an agent to existing software is mainly an architecture question: how much freedom does it get and which existing rules stay in charge?\n",[481,484,487],{"title":482,"text":483},"The agent has to work within existing domain rules","AI should not re-implement existing business logic in a different way.\n",{"title":485,"text":486},"Tool use has to be safe","A wrong answer is different from a wrong write or delete action.\n",{"title":488,"text":489},"State has to stay explicit","Long workflows need to know what has already happened and what still has to happen.\n",{"intro":491,"points":492},"Agentic workflows sit where AI meets existing software. That is where our experience with software architecture, integrations and AI engineering comes together.\n",[493,496,499],{"title":494,"text":495},"Building on what exists","The agent builds on existing systems and rules.\n",{"title":497,"text":498},"Autonomy within limits","Tools, permissions and human-in-the-loop are designed deliberately.\n",{"title":500,"text":501},"Built for production too","Retries, logging, state and error handling are part of the build.\n",{"intro":503,"signals":504},"Agentic workflows pay off most when an existing feature currently takes several manual or half-manual steps.\n",[505,508,511,514],{"title":506,"text":507},"A user has to take many intermediate steps","Fetching, comparing and passing on information takes unnecessary interaction.\n",{"title":509,"text":510},"The next step depends on context","A fixed workflow is too rigid, but full human handling is not always necessary.\n",{"title":512,"text":513},"The software already has usable APIs","Many of the required actions already exist technically, but are now triggered by hand.\n",{"title":515,"text":516},"Full autonomy is not required","The workflow may run on its own until a logical checkpoint or decision moment.\n",{"intro":518},"With Build & Integrate we design the agentic workflow as an extension of the existing software. We reuse current APIs and domain logic where possible and only build the new orchestration layer that is needed.\n",{"buyerTriggerKeys":520,"primaryOfferKey":77,"offerKeys":521,"caseKeys":522,"relatedUseCaseKeys":523},[76],[77,141],[],[122,124],{"title":525,"description":526},"Add agentic workflows to existing software | 9to5 software","Add agentic workflows or AI agents (Claude, OpenAI) to existing software? 9to5 builds controlled agent flows around your data, APIs and MCP tools.\n","use-cases\u002Fagentic-workflows-bestaande-software","Your existing software already does a lot well, but some workflows could be smarter if AI gathered information and carried out next steps on its own.\n",{"hero":90,"problem":91,"proof":530},"ls-agentic-loop","l-LSbU1lEyqddJX5i8k4FjICWCwevjAMP1tFWXQP80s",[],[534],{"id":535,"title":536,"approach":537,"body":552,"cta":556,"description":11,"extension":26,"hero":559,"key":76,"label":561,"meta":562,"navigation":31,"path":563,"proof":564,"relations":576,"seo":582,"stem":585,"summary":586,"visuals":587,"__hash__":589},"buyerTriggers_en\u002Fbuyer-triggers\u002Fai-laten-bouwen.md","We know what we want. Now it needs to be built.",{"title":538,"steps":539},"From a clear scope to something that really works.",[540,543,546,549],{"title":541,"text":542},"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":544,"text":545},"Set up the architecture and integrations","We determine how AI, data, existing software, permissions and integrations should work together technically.\n",{"title":547,"text":548},"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":550,"text":551},"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":553,"toc":554},[],{"title":11,"searchDepth":12,"depth":12,"links":555},[],{"title":557,"body":558},"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":560},"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":565,"points":566},"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",[567,570,573],{"title":568,"text":569},"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":571,"text":572},"Reliable beyond the happy path","We also test errors, edge cases and human oversight where needed.\n",{"title":574,"text":575},"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":577,"offerKeys":580,"caseKeys":581},[122,123,82,124,191,192,578,579,83,29],"ai-prototype-laten-bouwen","product-goed-opzetten-voor-ai-development",[77,141,282],[],{"title":583,"description":584},"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":238,"proof":588,"approach":588},"ls-system-assemble","ShT4oNEyuY5KbwbXvOuC2vEuCmku084FYvyfv89UAyM",1792049912615]