| 79 | | * We start product selection projects with a (physical or virtual) "round table" kick-off workshop to understand the big picture and collect the key requirements. |
| 80 | | * To round this information out, we keep contact with your different stakeholders and user groups to identify more details. This also includes the IT department to make sure the new system follows your IT policies and can be seamlessly integrated into your existing infrastructure. |
| 81 | | * We document the requirements in tabular form and agree on them with you. |
| 82 | | * Based on the confirmed requirements, we choose possible candidates and sort out products that are surely non-matching from the systems that we know about. Per category, these are 30 to almost 100, depending on the category. We evaluate public information as well as our experience with the vendor or product from previous selection projects. |
| 83 | | * Depending on the relative and absolute adequacy of the products in the list, we try to cut the list down to 2 or 3 candidates. If there are more candidates, we try to get more details from vendors to have a decision base. |
| 84 | | * We discuss the use cases and requirements with the remaining vendors to have a reliable how your business requirements will be solved. |
| 85 | | * We organize online or presence product presentations with all remaining vendors, if possible, all in the same week. |
| 86 | | * After the meetings, we discuss the findings with you and moderate your decision process. |
| 87 | | * Finally, we document the product selection for you, including a management summary for your internal communication. |
| 88 | | * Optionally, we moderate the fulfillment project with the software vendor you have chosen to make sure the system matches what was discussed before and layed down in the vendor's proposal. |
| | 81 | * In the first place, we can help you sorting out your questions and identifying powers, limits and possible applications in your environment. |
| | 82 | * We can help you integrate software products you are using with AI services, particularly GPT. |
| | 83 | * OpenAI, the company behind ChatGPT, offer a number of different pay-per-use models with the API - we can help you find the right plan and its configuration for you, and structure a data model suitable for the solution. |
| | 84 | * We have significant experience with so-called //prompt engineering//, expressing a task in a way that an AI can handle it best. Basically, it can be seen as a software development technique - telling a machine what to do in an optimally efficient way. |
| | 85 | * While ChatGPT's natural language capabilities cope well with incomplete or confusing input, it is still more efficient to reduce a chat to one particular task. In the above DITA example, instead of asking for the final result, it works better to first gather the information as a list, then let it structure it and clean up the language, then turn it to a DITA task and then add the hazardstatements. If this happens over the API, it can be hidden from the user that there are multiple processing steps. |
| | 86 | * In image generators like Stable Diffusion, it's important to group and emphasize the features desired in the picture. Also, generating attractive images is an iterative task where the user generates some images until there is a good starting point, then feeds the good results back in and emphasizes new properties in the prompt. |
