[{"data":1,"prerenderedAt":472},["ShallowReactive",2],{"offer-build-integrate-en":3,"footer-vacatures-en":160,"content-by-keys-useCases-en-ai-agent-laten-bouwen,interne-ai-assistent-laten-ontwikkelen,bedrijfsproces-automatiseren-met-ai,ai-toevoegen-aan-bestaande-software":161,"content-by-keys-cases-en-":471},{"id":4,"title":5,"body":6,"catalogue":13,"cta":24,"description":10,"extension":29,"fit":30,"hero":38,"key":41,"meta":42,"navigation":43,"next":44,"outcome":57,"path":69,"price":70,"process":73,"proof":88,"relations":102,"scope":116,"seo":146,"stem":149,"summary":150,"summaryPanel":151,"visuals":156,"__hash__":159},"offers_en\u002Foffers\u002Fbuild-integrate.md","Build & Integrate",{"type":7,"value":8,"toc":9},"minimark",[],{"title":10,"searchDepth":11,"depth":11,"links":12},"",2,[],{"audience":14,"promise":15,"deliverables":16,"note":22,"visual":23},"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",[17,18,19,20,21],"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":25,"body":26,"primaryCta":27,"local":28},"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","md",{"title":31,"intro":32,"useCaseKeys":33},"When is this offer a fit?","When the desired outcome is clear enough to scope a professional implementation.\n",[34,35,36,37],"ai-agent-laten-bouwen","interne-ai-assistent-laten-ontwikkelen","bedrijfsproces-automatiseren-met-ai","ai-toevoegen-aan-bestaande-software",{"headline":39,"intro":40,"primaryCta":27},"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","build-integrate",{},true,{"title":45,"items":46},"What happens next?",[47,50,53],{"title":48,"text":49},"You take it over","That is what we work towards. We don't want you to keep needing us.\n",{"title":51,"text":52},"A new bounded question comes up later","Then we scope it again instead of automatically keeping capacity running.\n",{"title":54,"text":55,"offerKey":56},"Still too much technical uncertainty?","Then an AI Prototype Sprint or Reality Check before Build & Integrate may be wiser.\n","ai-prototype-sprint",{"title":58,"items":59},"Afterwards you have...",[60,63,66],{"title":61,"text":62},"Working software instead of a demo","The agreed functionality works end to end within the real technical environment.\n",{"title":64,"text":65},"Reliable integration with what is already there","Data, systems, permissions and human processes are part of the solution.\n",{"title":67,"text":68},"A product you can hand over","Architecture, code and key choices are documented well enough to continue independently.\n","\u002Foffers\u002Fbuild-integrate",{"label":71,"type":72},"Fixed price after scoping","scoped",{"title":74,"steps":75},"How it works.",[76,79,82,85],{"title":77,"text":78},"Scope + success criteria","We make exact enough what needs to work to agree on responsibility and price.\n",{"title":80,"text":81},"Architecture + integrations","We determine how AI, data, existing software, permissions and users come together.\n",{"title":83,"text":84},"Build + test","We implement the hard part and also test errors, edge cases and reliability.\n",{"title":86,"text":87},"Go live + hand over","We bring the solution to production in a controlled way, document it and hand it over.\n",{"title":89,"intro":90,"points":91,"caseKeys":101},"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",[92,95,98],{"title":93,"text":94},"The same people advise and build","Advice and execution sit with the same technical people.\n",{"title":96,"text":97},"Integrations are core work","We don't treat APIs, databases, auth and existing systems as an afterthought around the AI.\n",{"title":99,"text":100},"Production and handover are part of it","The work isn't done when the demo works, but when the solution is manageable.\n",[],{"buyerTriggerKeys":103,"useCaseKeys":106,"relatedOfferKeys":111,"caseKeys":115},[104,105],"ai-laten-bouwen","vastgelopen-met-ai",[34,35,36,37,107,108,109,110],"eigen-data-en-kennis-gebruiken-met-ai","documenten-en-mails-automatisch-verwerken","agentic-workflows-bestaande-software","tools-vervangen-door-maatwerkflow",[112,56,113,114],"ai-reality-check","vibe-code-rescue-audit","rescue-sprint",[],{"title":117,"intro":118,"activities":119,"deliverables":130,"exclusions":139},"What is included in this offer?","The scope is defined up front. Then you get a fixed price for the agreed result.\n",{"intro":120,"items":121},"The exact work differs per engagement, but we take responsibility for the complete technical result.\n",[122,123,124,125,126,127,128,129],"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":131,"items":132},"The deliverables are defined per scope and are part of the fixed price.\n",[133,134,135,136,137,138],"Working agreed functionality","Production-grade implementation","Required integrations","Relevant tests and quality checks","Technical documentation","Deployment and handover as scoped",{"intro":140,"items":141},"No unbounded consultancy and no feature list that keeps growing afterwards.\n",[142,143,144,145],"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":147,"description":148},"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":152,"result":153,"duration":154,"nextStep":155},"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":157,"proof":158,"process":23},"sq-connect-nodes","sq-foundation-build","jlXsSL_a-hghGaOxvEHbZ2ARDUkoaAlfXaEkKLzQpSQ",[],[162,241,318,395],{"id":163,"title":164,"body":165,"description":10,"desiredOutcome":169,"extension":29,"hero":181,"key":34,"meta":183,"navigation":43,"path":184,"problem":185,"proof":197,"recognition":209,"recommendedApproach":224,"relations":226,"seo":231,"stem":234,"summary":235,"visuals":236,"__hash__":240},"useCases_en\u002Fuse-cases\u002Fai-agent-laten-bouwen.md","Have an AI agent built",{"type":7,"value":166,"toc":167},[],{"title":10,"searchDepth":11,"depth":11,"links":168},[],{"intro":170,"items":171},"You don't want a standalone AI demo, but an agent that performs a clear task and fits the software and processes that already exist.\n",[172,175,178],{"title":173,"text":174},"A working end-to-end flow","The agent can retrieve the relevant information, make decisions and take the right actions.\n",{"title":176,"text":177},"Control over what it may do","Permissions, validation and human oversight limit its autonomy where needed.\n",{"title":179,"text":180},"Manageable in production","Errors, model behaviour, costs and tool calls are visible enough to use the agent responsibly.\n",{"intro":182},"An agent that only gives clever answers won't do much for you. It becomes useful when it can retrieve information, make choices and safely take actions in your existing systems. We build that whole technical setup.\n",{},"\u002Fuse-cases\u002Fai-agent-laten-bouwen",{"intro":186,"causes":187},"An AI agent is more than a prompt with a few functions. It is a software system in which unpredictable models are allowed to take real actions.\n",[188,191,194],{"title":189,"text":190},"Autonomy introduces risk","A wrong model decision can have consequences outside the chat interface.\n",{"title":192,"text":193},"Integrations determine the real value","Without good access to existing data and systems, the agent remains mostly a demonstration.\n",{"title":195,"text":196},"Reliability is built around the model","Validation, retries, state, logging and human-in-the-loop are often just as important as the choice of model.\n",{"intro":198,"points":199},"9to5 software combines AI engineering with senior software engineering. So next to the smart part, we also build the technical environment you need to use an agent seriously.\n",[200,203,206],{"title":201,"text":202},"Agents and regular software","Tooling, APIs, data, auth and error handling belong to the same solution.\n",{"title":204,"text":205},"Human-in-the-loop where needed","Not every process gets better with maximum autonomy.\n",{"title":207,"text":208},"No black box left behind","We document the important choices so the system stays transferable.\n",{"intro":210,"signals":211},"The use case is often already clear. The technical challenge is running the complete workflow reliably.\n",[212,215,218,221],{"title":213,"text":214},"The agent has to do more than answer","It has to retrieve data, call systems or actually change something.\n",{"title":216,"text":217},"Several tools or systems are involved","The workflow runs across APIs, databases or existing business software.\n",{"title":219,"text":220},"Not every action may run automatically","For critical steps a user must be able to check or approve.\n",{"title":222,"text":223},"A simple prompt is not enough","State, context, error handling and tool use become part of the technical design.\n",{"intro":225},"With Build & Integrate we design and build the complete agent flow: architecture, tools, integrations, permissions, guardrails and production behaviour. When a new or uncertain agent concept first needs to be proven technically, an AI Prototype Sprint can be a more logical first step.\n",{"buyerTriggerKeys":227,"primaryOfferKey":41,"offerKeys":228,"caseKeys":229,"relatedUseCaseKeys":230},[104],[41,56],[],[109,36],{"title":232,"description":233},"AI agent development (Claude, ChatGPT, MCP) | 9to5 software","Need an AI agent for a serious business process? 9to5 builds agents with Claude or OpenAI, MCP tools and integrations with your existing software and data.\n","use-cases\u002Fai-agent-laten-bouwen","You know which task or workflow the agent has to perform. Now it needs to be designed well, connected and made reliable enough for real use.\n",{"hero":237,"problem":238,"proof":239},"sq-process-steps","sq-guardrails-check","ls-agentic-loop","Sz6OZV7bqm5zl00ThdeWnUL9u1nZHw5GFlz7cgVRcnE",{"id":242,"title":243,"body":244,"description":10,"desiredOutcome":248,"extension":29,"hero":260,"key":35,"meta":262,"navigation":43,"path":263,"problem":264,"proof":276,"recognition":288,"recommendedApproach":303,"relations":305,"seo":310,"stem":313,"summary":314,"visuals":315,"__hash__":317},"useCases_en\u002Fuse-cases\u002Finterne-ai-assistent-laten-ontwikkelen.md","Have an internal AI assistant developed",{"type":7,"value":245,"toc":246},[],{"title":10,"searchDepth":11,"depth":11,"links":247},[],{"intro":249,"items":250},"Employees should get to the right information faster without creating a new knowledge problem with unreliable answers.\n",[251,254,257],{"title":252,"text":253},"Answers based on your own sources","The assistant uses relevant internal documents, data and knowledge.\n",{"title":255,"text":256},"Sources stay verifiable","Users can see where important information comes from.\n",{"title":258,"text":259},"Access follows existing permissions","The assistant doesn't reveal information the user normally isn't allowed to see.\n",{"intro":261},"An internal assistant only becomes truly useful when it knows your context, can find sources and only shows information a user is allowed to see. We build the technology behind that experience.\n",{},"\u002Fuse-cases\u002Finterne-ai-assistent-laten-ontwikkelen",{"intro":265,"causes":266},"An internal AI assistant is mainly an information and integration challenge around a language model.\n",[267,270,273],{"title":268,"text":269},"Knowledge is scattered","Documents, databases and other systems each have their own structure.\n",{"title":271,"text":272},"A model doesn't know what is true","Without good retrieval and source selection, convincing-sounding nonsense can appear.\n",{"title":274,"text":275},"Permissions have to carry through","Central access to knowledge must not bypass existing security boundaries.\n",{"intro":277,"points":278},"The chat window is the easy part. Whether employees can rely on the assistant depends on how data, permissions, retrieval and AI are connected.\n",[279,282,285],{"title":280,"text":281},"Your own data as part of the design","We start with the sources and users, not with an arbitrary model.\n",{"title":283,"text":284},"Integrations are part of it","The assistant can connect to existing software instead of becoming a new information silo.\n",{"title":286,"text":287},"Reliability over magic","Sources, uncertainty and limits may stay visible to the user.\n",{"intro":289,"signals":290},"The need is usually clear when a lot of valuable knowledge does exist, but is hard to find or scattered.\n",[291,294,297,300],{"title":292,"text":293},"Employees keep searching for the same information","Answers are spread across documents, systems and colleagues.\n",{"title":295,"text":296},"A general chatbot doesn't know your context","Good answers require access to organisation-specific information.\n",{"title":298,"text":299},"Sources change regularly","The solution has to work with current knowledge without baking everything into a model.\n",{"title":301,"text":302},"Not everyone may see everything","Roles, teams or clients have different access rights.\n",{"intro":304},"With Build & Integrate we build the assistant around your real sources, access model and usage situations. If it's still uncertain whether retrieval and answer quality will work well enough, we can first validate that core in an AI Prototype Sprint.\n",{"buyerTriggerKeys":306,"primaryOfferKey":41,"offerKeys":307,"caseKeys":308,"relatedUseCaseKeys":309},[104],[41,56],[],[107,108],{"title":311,"description":312},"Have an internal AI assistant developed | 9to5 software","Need an internal AI assistant or your own ChatGPT built on your knowledge and systems? 9to5 builds secure, integrated AI assistants for serious internal use.\n","use-cases\u002Finterne-ai-assistent-laten-ontwikkelen","You want to give employees faster access to internal knowledge, documents and systems through an assistant that fits your organisation.\n",{"hero":316,"problem":157,"proof":23},"sq-knowledge-filter","_peqkPNQXiEZoQx11qqN8kY_wuZT1mvO0j1tCcY3dno",{"id":319,"title":320,"body":321,"description":10,"desiredOutcome":325,"extension":29,"hero":337,"key":36,"meta":339,"navigation":43,"path":340,"problem":341,"proof":353,"recognition":365,"recommendedApproach":380,"relations":382,"seo":387,"stem":390,"summary":391,"visuals":392,"__hash__":394},"useCases_en\u002Fuse-cases\u002Fbedrijfsproces-automatiseren-met-ai.md","Automate a business process with AI",{"type":7,"value":322,"toc":323},[],{"title":10,"searchDepth":11,"depth":11,"links":324},[],{"intro":326,"items":327},"You don't want as much AI as possible. You want less manual work, fewer errors and a process that stays technically manageable.\n",[328,331,334],{"title":329,"text":330},"Less repetitive work","Predictable or time-consuming steps are carried out automatically.\n",{"title":332,"text":333},"AI only where it adds something","Interpretation and unstructured information go to AI; fixed rules stay regular software.\n",{"title":335,"text":336},"People stay in control","Critical exceptions or decisions can deliberately stay with an employee.\n",{"intro":338},"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":342,"causes":343},"AI automation works best when you first technically split the process into deterministic and non-deterministic steps.\n",[344,347,350],{"title":345,"text":346},"Not every step needs AI","Using a language model for fixed rules makes processes more expensive and less predictable.\n",{"title":348,"text":349},"Exceptions determine reliability","The system has to know when continuing automatically is not wise.\n",{"title":351,"text":352},"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":354,"points":355},"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",[356,359,362],{"title":357,"text":358},"Process before technology","The desired outcome determines which steps need AI.\n",{"title":360,"text":361},"Existing systems stay usable","Integrations prevent an automation from becoming yet another standalone system.\n",{"title":363,"text":364},"Human oversight is part of the design","We explicitly design where exceptions should go to an employee.\n",{"intro":366,"signals":367},"Processes with a lot of copying, checking, interpreting and passing on are a good fit.\n",[368,371,374,377],{"title":369,"text":370},"People move information between systems","A large part of the work consists of reading, retyping or classifying.\n",{"title":372,"text":373},"The same decision rules keep coming back","A workflow usually follows a fixed pattern with a limited number of exceptions.\n",{"title":375,"text":376},"Unstructured information blocks classic automation","Emails, documents or free text first have to be interpreted.\n",{"title":378,"text":379},"Existing software has to stay part of it","You don't want to replace all current systems to make one process smarter.\n",{"intro":381},"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":383,"primaryOfferKey":41,"offerKeys":384,"caseKeys":385,"relatedUseCaseKeys":386},[104],[41,56],[],[108,110],{"title":388,"description":389},"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":237,"problem":238,"proof":393},"ls-workflow-flow","-G_t_-Jsnlyir8qFMNtC3gxskycjna1O6PRo9qtkdak",{"id":396,"title":397,"body":398,"description":10,"desiredOutcome":402,"extension":29,"hero":414,"key":37,"meta":416,"navigation":43,"path":417,"problem":418,"proof":430,"recognition":442,"recommendedApproach":457,"relations":459,"seo":464,"stem":467,"summary":468,"visuals":469,"__hash__":470},"useCases_en\u002Fuse-cases\u002Fai-toevoegen-aan-bestaande-software.md","Add AI to existing software, an app or SaaS",{"type":7,"value":399,"toc":400},[],{"title":10,"searchDepth":11,"depth":11,"links":401},[],{"intro":403,"items":404},"The new AI functionality should feel like part of the product, not like a chatbot glued on later.\n",[405,408,411],{"title":406,"text":407},"AI fits the existing user flow","The feature supports what users are already trying to do.\n",{"title":409,"text":410},"The existing architecture stays manageable","AI is integrated without needlessly adding a second technical world.\n",{"title":412,"text":413},"Production risks are covered","Costs, latency, errors and uncertain model behaviour get a place in the design.\n",{"intro":415},"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":419,"causes":420},"Integrating a standalone AI API is easy. Designing AI as a reliable part of existing product software is another story.\n",[421,424,427],{"title":422,"text":423},"Existing software already has rules","Data, permissions, business logic and user expectations are largely fixed.\n",{"title":425,"text":426},"AI introduces other failure modes","Latency, incorrect output and variable costs have to be handled in existing flows.\n",{"title":428,"text":429},"The new feature can end up too detached","A separate AI system quickly leads to duplicated data and logic.\n",{"intro":431,"points":432},"Understanding and extending existing software is a big part of our work. So AI doesn't need a greenfield to be built well.\n",[433,436,439],{"title":434,"text":435},"Understand the existing architecture first","We design the AI feature around what already works.\n",{"title":437,"text":438},"Integration over isolation","Data, auth and business logic are not duplicated unnecessarily.\n",{"title":440,"text":441},"Production from the design onwards","Reliability and operational consequences count before the feature goes live.\n",{"intro":443,"signals":444},"The problem is usually not how to call a model, but how the new functionality should relate to the existing product.\n",[445,448,451,454],{"title":446,"text":447},"The feature needs existing product data","AI has to work with users, documents or other information already in the product.\n",{"title":449,"text":450},"Permissions must simply keep working","AI must not suddenly expose information or actions that are protected elsewhere.\n",{"title":452,"text":453},"The existing UX should stay in charge","Users want a better workflow, not necessarily a chat interface.\n",{"title":455,"text":456},"You don't want to rebuild the current product","The AI layer has to connect to what already works well technically.\n",{"intro":458},"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":460,"primaryOfferKey":41,"offerKeys":461,"caseKeys":462,"relatedUseCaseKeys":463},[104],[41,56],[],[109,107],{"title":465,"description":466},"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":157,"problem":158,"proof":23},"uIjq2lxyg3PeXyGhq82YeTX4j_ALcHznMSqDHe95r9k",[],1792049910231]