[{"data":1,"prerenderedAt":583},["ShallowReactive",2],{"footer-vacatures-en":3,"case-robos-ai-agents-die-echt-werk-doen-en":4,"content-by-keys-useCases-en-ai-agent-laten-bouwen,interne-ai-assistent-laten-ontwikkelen,processen-automatiseren-met-ai,eigen-data-en-kennis-gebruiken-met-ai,ai-toevoegen-aan-bestaande-software":186},[],{"id":5,"title":6,"approach":7,"body":22,"build":29,"card":42,"connections":47,"cta":60,"dataExamples":66,"description":26,"extension":67,"facts":68,"featured":83,"guardrails":66,"hero":84,"integrations":66,"key":89,"meta":90,"navigation":91,"offers":92,"order":27,"path":102,"proof":103,"relations":116,"result":137,"seo":149,"situation":152,"stem":165,"summary":166,"usecases":167,"visuals":179,"__hash__":185},"cases_en\u002Fcases\u002Frobos-ai-agents-die-echt-werk-doen.md","Robos: AI agents that do real work",{"title":8,"steps":9},"How do we build the Robos?",[10,13,16,19],{"title":11,"text":12},"One Robo, one clear problem","We do not start with the model but with the task. Helma does support, Mae works on software maintenance, Indie on incidents, Mark on marketing and Nola on meetings. This keeps the context small enough to understand and test well.\n",{"title":14,"text":15},"AI gets access to the right context","Depending on the task we use, among other things, Skills, vector stores, repository snapshots, live APIs, historical data, business rules and current information from connected systems.\n",{"title":17,"text":18},"Output becomes part of the workflow","A Robo delivers more than a suggestion. Output can end up in a helpdesk ticket, GitHub issue, incident record, marketing schedule, backlog or minutes with action items.\n",{"title":20,"text":21},"People stay where they add value","For us, human-in-the-loop is a design choice. Helma has answers reviewed, Indie has an incident adjusted or confirmed first, and Mark has review moments before customer-facing content goes ahead.\n",{"type":23,"value":24,"toc":25},"minimark",[],{"title":26,"searchDepth":27,"depth":27,"links":28},"",2,[],{"title":30,"intro":31,"points":32},"What did we build?","The Robos are separate tools and products, each with its own workflow and integrations. Not every Robo needs an application of its own. Together they form our internal lab for AI that actually has to work in production.\n",[33,36,39],{"title":34,"text":35},"Customers and marketing","Robo Helma combines support knowledge, customer context and technical information for customer answers. Robo Mark picks up signals from sources such as RSS, Slack and ideas, creates content, supports review and planning, publishes and uses performance as input for the next generation.\n",{"title":37,"text":38},"Engineering and operations","At fixed moments, Robo Mae analyses a commit-pinned snapshot of a repository, combines it with current first-party documentation and can create validated maintenance issues in GitHub. Robo Indie turns a Slack thread into a structured incident draft with an internal explanation, a customer-safe explanation and a workaround where available. Stanley works directly from ChatGPT: he watches our GitHub backlog and runs the weekly stand-up, so open issues do not go unnoticed.\n",{"title":40,"text":41},"Meetings, media and the Robo landscape","Robo Nola retrieves Google Meet recordings and uses its own Dutch ASR pipeline to create transcripts, summaries, action items and minutes. Robo Vidar is our video generation workspace for tools such as Seedance and Veo. Robo Dolly keeps track of active Robos and their history. Robo Rolf is the rollout Robo under construction; the current application deliberately contains only the technical foundation until the release workflow is defined sharply enough.\n",{"tag":43,"title":44,"summary":45,"metric":46},"AI agents","Robo's: AI agents that do real work","Specialist Robo's carry out specific tasks in support, software maintenance, marketing, incident management, meetings and other operational workflows.","AI connected to real knowledge, systems and actions, with clear boundaries.",{"title":48,"intro":49,"points":50},"The Robos are not isolated from each other","As more processes are automated, specialised agents can also use each other's controlled output. The result is a network of small systems with clear responsibilities instead of one big all-knowing super agent.\n",[51,54,57],{"title":52,"text":53},"Indie feeds Helma","Robo Indie is the source of truth for current incidents and offers a protected read-only API for it. Robo Helma can use that information when a support answer depends on a current outage.\n",{"title":55,"text":56},"GitHub is a work environment for several agents","Mae uses GitHub to record maintenance work as concrete issues. Stanley uses the same backlog in a different way: watching what gets left behind and periodically bringing attention back to open work.\n",{"title":58,"text":59},"Dolly keeps the whole visible","Robo Dolly gives an internal overview of which Robos are active and stores their history. This keeps the growing landscape of specialised agents itself manageable too.\n",{"title":61,"body":62,"primaryCta":63,"secondaryCta":64,"local":65},"Which recurring task at your organisation deserves a Robo?","Show us which work now goes back and forth by hand between people and systems. We look at where AI can really take something over and what is needed to make that work reliably in production.\n","Book a call","View offer","Senior AI and software engineering from Delft, for organisations in Delft, The Hague, Rotterdam and the surrounding area.\n",null,"md",{"title":69,"items":70},"The case in brief",[71,74,77,80],{"label":72,"value":73},"Support","67% of Helma's answers usable right away",{"label":75,"value":76},"Software maintenance","Mae examines repositories and creates concrete issues",{"label":78,"value":79},"Marketing","Mark goes from signal to publication and feedback",{"label":81,"value":82},"Meetings","Nola creates Dutch transcripts and minutes",false,{"headline":85,"intro":86,"primaryCta":87,"secondaryCta":88},"AI that becomes part of the work, not a chatbot that gives advice.","An agent only gets interesting when it goes beyond generating text. Our Robos read information from real systems, make decisions within a defined task, create concrete output and move processes forward. Sometimes on their own, sometimes with a person as a checkpoint. That is how we are building, step by step, a team of specialised AI tools for our own work.\n","Meet the Robos","Tell us what you want to build","robos-ai-agents-die-echt-werk-doen",{},true,{"eyebrow":93,"primary":94},"Matching offer",{"key":95,"title":96,"text":97,"price":98,"result":99,"duration":100,"nextStep":101},"build-integrate","Build & Integrate","We design and build an AI agent around a concrete process, including the required knowledge sources, system integrations, guardrails and human-in-the-loop.\n","Fixed price after scoping","A production-ready AI workflow that is truly part of your process","Depends on scope","First we determine exactly which task the agent must carry out and which systems it needs","\u002Fcases\u002Frobos-ai-agents-die-echt-werk-doen",{"title":104,"intro":105,"points":106},"These are not standalone AI demos","Behind the Robos are ordinary software engineering principles: authentication, authorisation, queues, retries, structured output, tests, monitoring and explicit data boundaries. The language model is one part of the system, not the system itself.\n",[107,110,113],{"title":108,"text":109},"Measurable quality instead of AI magic","Robo Helma, for example, measures what support agents actually do with an AI draft. Currently 67% is sent directly, 18% slightly adjusted and 15% fully rewritten. That lets us keep improving in a targeted way.\n",{"title":111,"text":112},"Autonomy is earned per task","Within a preconfigured maintenance job, Mae may automatically publish a limited number of strictly validated GitHub issues. Indie, on the other hand, first creates a draft that an employee can adjust, cancel or confirm. The degree of autonomy follows the risk.\n",{"title":114,"text":115},"Not every agent needs an application of its own","Some Robos have a complete interface and backend of their own. Others can be deployed much more lightly. Stanley, for example, works as an agent in ChatGPT and uses GitHub as a work environment for backlog management and the weekly stand-up. The form follows the problem, not the other way around.\n",{"buyerTriggerKeys":117,"useCaseKeys":119,"offerKeys":125,"capabilityKeys":126},[118],"ai-laten-bouwen",[120,121,122,123,124],"ai-agent-laten-bouwen","interne-ai-assistent-laten-ontwikkelen","processen-automatiseren-met-ai","eigen-data-en-kennis-gebruiken-met-ai","ai-toevoegen-aan-bestaande-software",[95],[127,128,129,130,131,132,133,134,135,136],"ai-engineering","ai-agents","software-engineering","integrations","workflow-automation","retrieval","human-in-the-loop","evaluation","monitoring","security",{"title":138,"items":139},"What does this approach deliver?",[140,143,146],{"title":141,"text":142},"AI really takes over a defined piece of work","The Robos do not stop at analysis. They deliver a usable artefact or move a workflow forward: an answer, GitHub issue, incident, publication, backlog action or set of minutes.\n",{"title":144,"text":145},"Integrations make the difference","The value comes from connecting AI to the systems where the work actually happens. A concrete example is Robo Helma, which can use current incident information from Robo Indie when answering support questions.\n",{"title":147,"text":148},"We learn from real production problems","Because we use the Robos ourselves, problems with context, permissions, retries, security, evaluation and human-in-the-loop do not first surface at a customer. We solve them while the system is really being used.\n",{"title":150,"description":151},"AI agents that do real work | Robos by 9to5 software","Case: how 9to5 software builds specialised AI agents for support, marketing, software maintenance, incident management and meetings. AI connected to real data, systems and workflows.\n",{"title":153,"intro":154,"points":155},"Why not just one AI assistant?","Many business processes seem suitable for AI, but in practice they have very different context, permissions, risks and actions. A generic assistant with a bit of access to everything quickly becomes hard to control. That is why we choose specialised Robos, each with a clear area of work.\n",[156,159,162],{"title":157,"text":158},"The work is spread over real systems","The information an agent needs is not in a single prompt. It lives in GitHub, Slack, product documentation, mailboxes, customer data, Google Calendar, Meet, Drive, RSS feeds and other operational systems.\n",{"title":160,"text":161},"Just generating an answer solves little","A maintenance agent must be able to deliver a usable GitHub issue. An incident agent must turn information into a manageable incident. The process has to actually move forward.\n",{"title":163,"text":164},"Every task needs different boundaries","Sometimes a Robo may act on its own. Sometimes an employee must review or confirm first. We design that boundary per workflow, instead of hoping afterwards that the model does the right thing.\n","cases\u002Frobos-ai-agents-die-echt-werk-doen","At 9to5 software we build specialised Robos that each carry out a concrete piece of work, not a collection of chatbots. Answering support, flagging software maintenance, logging incidents, creating marketing content, processing meetings or watching a GitHub backlog. Every Robo combines AI with real knowledge, systems, actions and clear boundaries.\n",{"title":168,"items":169},"Where is this relevant?",[170,173,176],{"title":171,"text":172},"We want an AI agent that actually takes action","AI that retrieves information, carries out a task and brings the result back into your existing process, instead of another chat window.\n",{"title":174,"text":175},"Our knowledge is spread over different systems","The agent must combine documentation, live data and applications without copying everything into one prompt or a new database.\n",{"title":177,"text":178},"We want to automate without losing control","Some steps may be automatic, others need human review. We design those boundaries explicitly into the workflow.\n",{"hero":180,"situation":181,"approach":182,"build":183,"proof":184,"teaser":180},"\u002Fmedia\u002Fproducts\u002Frobos\u002Fdolly-team.jpg","\u002Fmedia\u002Fproducts\u002Frobos\u002Fdolly-specialists.jpg","ls-agentic-loop","\u002Fmedia\u002Fscreenshots\u002Fnola-meeting-results.webp","\u002Fmedia\u002Fscreenshots\u002Fhelma-reporting.webp","JStSF95HQRC_lZNXV2vBOf21E2RAD0j6_-vIR6bl36M",[187,268,348,430,506],{"id":188,"title":189,"body":190,"description":26,"desiredOutcome":194,"extension":67,"hero":206,"key":120,"meta":208,"navigation":91,"path":209,"problem":210,"proof":222,"recognition":234,"recommendedApproach":249,"relations":251,"seo":259,"stem":262,"summary":263,"visuals":264,"__hash__":267},"useCases_en\u002Fuse-cases\u002Fai-agent-laten-bouwen.md","Have an AI agent built",{"type":23,"value":191,"toc":192},[],{"title":26,"searchDepth":27,"depth":27,"links":193},[],{"intro":195,"items":196},"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",[197,200,203],{"title":198,"text":199},"A working end-to-end flow","The agent can retrieve the relevant information, make decisions and take the right actions.\n",{"title":201,"text":202},"Control over what it may do","Permissions, validation and human oversight limit its autonomy where needed.\n",{"title":204,"text":205},"Manageable in production","Errors, model behaviour, costs and tool calls are visible enough to use the agent responsibly.\n",{"intro":207},"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":211,"causes":212},"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",[213,216,219],{"title":214,"text":215},"Autonomy introduces risk","A wrong model decision can have consequences outside the chat interface.\n",{"title":217,"text":218},"Integrations determine the real value","Without good access to existing data and systems, the agent remains mostly a demonstration.\n",{"title":220,"text":221},"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":223,"points":224},"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",[225,228,231],{"title":226,"text":227},"Agents and regular software","Tooling, APIs, data, auth and error handling belong to the same solution.\n",{"title":229,"text":230},"Human-in-the-loop where needed","Not every process gets better with maximum autonomy.\n",{"title":232,"text":233},"No black box left behind","We document the important choices so the system stays transferable.\n",{"intro":235,"signals":236},"The use case is often already clear. The technical challenge is running the complete workflow reliably.\n",[237,240,243,246],{"title":238,"text":239},"The agent has to do more than answer","It has to retrieve data, call systems or actually change something.\n",{"title":241,"text":242},"Several tools or systems are involved","The workflow runs across APIs, databases or existing business software.\n",{"title":244,"text":245},"Not every action may run automatically","For critical steps a user must be able to check or approve.\n",{"title":247,"text":248},"A simple prompt is not enough","State, context, error handling and tool use become part of the technical design.\n",{"intro":250},"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":252,"primaryOfferKey":95,"offerKeys":253,"caseKeys":255,"relatedUseCaseKeys":256},[118],[95,254],"ai-prototype-sprint",[],[257,258],"agentic-workflows-bestaande-software","bedrijfsproces-automatiseren-met-ai",{"title":260,"description":261},"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":265,"problem":266,"proof":182},"sq-process-steps","sq-guardrails-check","Sz6OZV7bqm5zl00ThdeWnUL9u1nZHw5GFlz7cgVRcnE",{"id":269,"title":270,"body":271,"description":26,"desiredOutcome":275,"extension":67,"hero":287,"key":121,"meta":289,"navigation":91,"path":290,"problem":291,"proof":303,"recognition":315,"recommendedApproach":330,"relations":332,"seo":338,"stem":341,"summary":342,"visuals":343,"__hash__":347},"useCases_en\u002Fuse-cases\u002Finterne-ai-assistent-laten-ontwikkelen.md","Have an internal AI assistant developed",{"type":23,"value":272,"toc":273},[],{"title":26,"searchDepth":27,"depth":27,"links":274},[],{"intro":276,"items":277},"Employees should get to the right information faster without creating a new knowledge problem with unreliable answers.\n",[278,281,284],{"title":279,"text":280},"Answers based on your own sources","The assistant uses relevant internal documents, data and knowledge.\n",{"title":282,"text":283},"Sources stay verifiable","Users can see where important information comes from.\n",{"title":285,"text":286},"Access follows existing permissions","The assistant doesn't reveal information the user normally isn't allowed to see.\n",{"intro":288},"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":292,"causes":293},"An internal AI assistant is mainly an information and integration challenge around a language model.\n",[294,297,300],{"title":295,"text":296},"Knowledge is scattered","Documents, databases and other systems each have their own structure.\n",{"title":298,"text":299},"A model doesn't know what is true","Without good retrieval and source selection, convincing-sounding nonsense can appear.\n",{"title":301,"text":302},"Permissions have to carry through","Central access to knowledge must not bypass existing security boundaries.\n",{"intro":304,"points":305},"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",[306,309,312],{"title":307,"text":308},"Your own data as part of the design","We start with the sources and users, not with an arbitrary model.\n",{"title":310,"text":311},"Integrations are part of it","The assistant can connect to existing software instead of becoming a new information silo.\n",{"title":313,"text":314},"Reliability over magic","Sources, uncertainty and limits may stay visible to the user.\n",{"intro":316,"signals":317},"The need is usually clear when a lot of valuable knowledge does exist, but is hard to find or scattered.\n",[318,321,324,327],{"title":319,"text":320},"Employees keep searching for the same information","Answers are spread across documents, systems and colleagues.\n",{"title":322,"text":323},"A general chatbot doesn't know your context","Good answers require access to organisation-specific information.\n",{"title":325,"text":326},"Sources change regularly","The solution has to work with current knowledge without baking everything into a model.\n",{"title":328,"text":329},"Not everyone may see everything","Roles, teams or clients have different access rights.\n",{"intro":331},"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":333,"primaryOfferKey":95,"offerKeys":334,"caseKeys":335,"relatedUseCaseKeys":336},[118],[95,254],[],[123,337],"documenten-en-mails-automatisch-verwerken",{"title":339,"description":340},"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":344,"problem":345,"proof":346},"sq-knowledge-filter","sq-connect-nodes","ls-system-connect","_peqkPNQXiEZoQx11qqN8kY_wuZT1mvO0j1tCcY3dno",{"id":349,"title":350,"body":351,"description":26,"desiredOutcome":355,"extension":67,"hero":367,"key":122,"meta":369,"navigation":91,"path":370,"problem":371,"proof":383,"recognition":395,"recommendedApproach":410,"relations":412,"seo":421,"stem":424,"summary":425,"visuals":426,"__hash__":429},"useCases_en\u002Fuse-cases\u002Fprocessen-automatiseren-met-ai.md","Which processes are suitable for AI or automation?",{"type":23,"value":352,"toc":353},[],{"title":26,"searchDepth":27,"depth":27,"links":354},[],{"intro":356,"items":357},"You don't want to end up with a list of twenty AI ideas. You want to know where a technical investment actually makes sense.\n",[358,361,364],{"title":359,"text":360},"The best opportunities first","You know which processes combine enough value, volume and technical feasibility to explore further.\n",{"title":362,"text":363},"AI where it's needed","We distinguish between AI, regular automation, existing software and simple integrations.\n",{"title":365,"text":366},"A concrete next step","You know which question to validate or build first, or which not to pursue any further.\n",{"intro":368},"Maybe you see opportunities for AI everywhere. Or so many that you don't know where to start. We help determine which processes are interesting, which technology fits them and which ideas you're better off leaving alone.\n",{},"\u002Fuse-cases\u002Fprocessen-automatiseren-met-ai",{"intro":372,"causes":373},"Not every annoying process is automatically a good AI problem. The value lies in the combination of process, data, technical feasibility and impact.\n",[374,377,380],{"title":375,"text":376},"AI is taken as the starting point too quickly","A fixed rule, integration or existing tool can sometimes solve the same problem more simply and reliably.\n",{"title":378,"text":379},"The real bottleneck is still unclear","What looks like manual work at first sight may be caused by a poor process or a missing integration.\n",{"title":381,"text":382},"Feasibility differs per task","Some tasks tolerate uncertainty, others require virtually error-free behaviour.\n",{"intro":384,"points":385},"We start with the problem you're trying to solve, and only then ask which AI model fits. Sometimes the best technical conclusion is that part of it doesn't need AI at all.\n",[386,389,392],{"title":387,"text":388},"Software engineering before AI hype","We also compare AI with automation, integrations and existing software.\n",{"title":390,"text":391},"Technical feasibility counts from the start","Data, systems and operational constraints are part of the assessment.\n",{"title":393,"text":394},"We can build the follow-up too","The advice doesn't have to be translated again by another technical party afterwards.\n",{"intro":396,"signals":397},"This question often comes up when there is clear inefficiency, but it's not yet clear which technical solution fits it best.\n",[398,401,404,407],{"title":399,"text":400},"Lots of repetitive knowledge work","Employees keep reading, checking, summarising or classifying similar information.\n",{"title":402,"text":403},"Information is copied over by hand","Data moves via people from email, documents or spreadsheets into other systems.\n",{"title":405,"text":406},"There are many AI ideas at once","Different teams see opportunities, but nobody knows which are the most interesting technically and commercially.\n",{"title":408,"text":409},"You don't want to automate for the sake of it","The solution has to demonstrably reduce time, errors or friction.\n",{"intro":411},"In an AI Reality Check we examine up to three ideas or one concrete process. We assess value, technical feasibility, data, integrations, risks and build versus buy. If one part then needs to be proven in practice, an AI Prototype Sprint can be the logical next step.\n",{"buyerTriggerKeys":413,"primaryOfferKey":415,"offerKeys":416,"caseKeys":417,"relatedUseCaseKeys":418},[414],"starten-met-ai","ai-reality-check",[415,254],[],[419,420],"is-ai-nodig","zelf-bouwen-of-software-kopen",{"title":422,"description":423},"Which processes are suitable for AI or automation? | 9to5 software","Find out which business processes are suitable for AI or automation. 9to5 examines processes, systems, data and technical feasibility.\n","use-cases\u002Fprocessen-automatiseren-met-ai","You see opportunities to make manual work smarter, but first want to know where AI actually adds value and where regular automation fits better.\n",{"hero":265,"problem":427,"proof":428},"sq-orient-options","ls-workflow-flow","Z9mZqpG5Qyu0wkGGaYeR4PecFC7nvQXcfsPeGf6UX80",{"id":431,"title":432,"body":433,"description":26,"desiredOutcome":437,"extension":67,"hero":449,"key":123,"meta":451,"navigation":91,"path":452,"problem":453,"proof":465,"recognition":477,"recommendedApproach":492,"relations":494,"seo":499,"stem":502,"summary":503,"visuals":504,"__hash__":505},"useCases_en\u002Fuse-cases\u002Feigen-data-en-kennis-gebruiken-met-ai.md","Make your own documents, data and knowledge usable for AI",{"type":23,"value":434,"toc":435},[],{"title":26,"searchDepth":27,"depth":27,"links":436},[],{"intro":438,"items":439},"You want to give AI access to relevant information of your own without putting everything into one uncontrollable data bin.\n",[440,443,446],{"title":441,"text":442},"Relevant information at the right moment","The AI only gets the context needed for the current task.\n",{"title":444,"text":445},"Sources stay traceable","Important output can be traced back to the underlying information.\n",{"title":447,"text":448},"Permissions and freshness stay intact","Users only see what they are allowed to see, and changes in sources can carry through into the solution.\n",{"intro":450},"A language model doesn't know your organisation by itself. If AI has to work with your own documents, product data or internal knowledge, that information has to be made available at the right moment and with the right permissions.\n",{},"\u002Fuse-cases\u002Feigen-data-en-kennis-gebruiken-met-ai",{"intro":454,"causes":455},"\"Giving our own data to AI\" sounds like one technical step, but usually consists of selection, retrieval, permissions and quality control.\n",[456,459,462],{"title":457,"text":458},"More context is not automatically better","A model actually gives worse answers when too much irrelevant information is included.\n",{"title":460,"text":461},"Sources have different structures","A PDF, a relational database and a ticketing system each call for a different approach.\n",{"title":463,"text":464},"Data permissions don't disappear with AI","Retrieval has to respect the same access that applies elsewhere in the organisation.\n",{"intro":466,"points":467},"The quality of an AI solution is often determined more by the context you provide than by the newest model. That's why we treat retrieval and data integration as fully-fledged engineering.\n",[468,471,474],{"title":469,"text":470},"Source and use case belong together","We don't just index everything because we can.\n",{"title":472,"text":473},"Existing permissions stay in charge","AI must not become a way around the access model.\n",{"title":475,"text":476},"No unnecessary platform layer","We only choose technical components the real problem requires.\n",{"intro":478,"signals":479},"This question arises when general AI works well, but business-specific context is missing.\n",[480,483,486,489],{"title":481,"text":482},"Knowledge is spread across many sources","Documents, databases and other systems each hold part of the context.\n",{"title":484,"text":485},"Copying into a prompt doesn't scale","Adding information by hand works for a demo, but not for structural use.\n",{"title":487,"text":488},"Information changes regularly","A static dataset quickly becomes outdated.\n",{"title":490,"text":491},"Not all knowledge is for everyone","Access rules from existing systems have to be preserved.\n",{"intro":493},"With Build & Integrate we build the technical layer that gives AI targeted access to your data and knowledge. If feasibility or answer quality is still uncertain, an AI Prototype Sprint can first validate the most important sources and use case.\n",{"buyerTriggerKeys":495,"primaryOfferKey":95,"offerKeys":496,"caseKeys":497,"relatedUseCaseKeys":498},[118],[95,254],[],[121,124],{"title":500,"description":501},"Use your own data and knowledge with AI | 9to5 software","Put your own documents and databases to work with AI? 9to5 builds RAG, retrieval, integrations and AI workflows around your existing information.\n","use-cases\u002Feigen-data-en-kennis-gebruiken-met-ai","The valuable information is already there. Now AI has to be able to work with it reliably, securely and practically.\n",{"hero":344,"problem":345,"proof":346},"rQE5CNfHzt2_sDfHXKyafJGMwiRmtAudJssA1bEegxQ",{"id":507,"title":508,"body":509,"description":26,"desiredOutcome":513,"extension":67,"hero":525,"key":124,"meta":527,"navigation":91,"path":528,"problem":529,"proof":541,"recognition":553,"recommendedApproach":568,"relations":570,"seo":575,"stem":578,"summary":579,"visuals":580,"__hash__":582},"useCases_en\u002Fuse-cases\u002Fai-toevoegen-aan-bestaande-software.md","Add AI to existing software, an app or SaaS",{"type":23,"value":510,"toc":511},[],{"title":26,"searchDepth":27,"depth":27,"links":512},[],{"intro":514,"items":515},"The new AI functionality should feel like part of the product, not like a chatbot glued on later.\n",[516,519,522],{"title":517,"text":518},"AI fits the existing user flow","The feature supports what users are already trying to do.\n",{"title":520,"text":521},"The existing architecture stays manageable","AI is integrated without needlessly adding a second technical world.\n",{"title":523,"text":524},"Production risks are covered","Costs, latency, errors and uncertain model behaviour get a place in the design.\n",{"intro":526},"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":530,"causes":531},"Integrating a standalone AI API is easy. Designing AI as a reliable part of existing product software is another story.\n",[532,535,538],{"title":533,"text":534},"Existing software already has rules","Data, permissions, business logic and user expectations are largely fixed.\n",{"title":536,"text":537},"AI introduces other failure modes","Latency, incorrect output and variable costs have to be handled in existing flows.\n",{"title":539,"text":540},"The new feature can end up too detached","A separate AI system quickly leads to duplicated data and logic.\n",{"intro":542,"points":543},"Understanding and extending existing software is a big part of our work. So AI doesn't need a greenfield to be built well.\n",[544,547,550],{"title":545,"text":546},"Understand the existing architecture first","We design the AI feature around what already works.\n",{"title":548,"text":549},"Integration over isolation","Data, auth and business logic are not duplicated unnecessarily.\n",{"title":551,"text":552},"Production from the design onwards","Reliability and operational consequences count before the feature goes live.\n",{"intro":554,"signals":555},"The problem is usually not how to call a model, but how the new functionality should relate to the existing product.\n",[556,559,562,565],{"title":557,"text":558},"The feature needs existing product data","AI has to work with users, documents or other information already in the product.\n",{"title":560,"text":561},"Permissions must simply keep working","AI must not suddenly expose information or actions that are protected elsewhere.\n",{"title":563,"text":564},"The existing UX should stay in charge","Users want a better workflow, not necessarily a chat interface.\n",{"title":566,"text":567},"You don't want to rebuild the current product","The AI layer has to connect to what already works well technically.\n",{"intro":569},"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":571,"primaryOfferKey":95,"offerKeys":572,"caseKeys":573,"relatedUseCaseKeys":574},[118],[95,254],[],[257,123],{"title":576,"description":577},"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":345,"problem":581,"proof":346},"sq-foundation-build","uIjq2lxyg3PeXyGhq82YeTX4j_ALcHznMSqDHe95r9k",1792049913698]